CN111406224B - Target credibility determining method, target identifying method, system, vehicle and storage medium - Google Patents

Abstract

A method for determining target credibility, a method for target identification, a system, a movable platform, and a storage medium. The method for determining target credibility includes: obtaining detection information of a detection target and information of Doppler units around the detection target (S201); determining the credibility of the type of the detection target based on the detection information of the detection target and the information of Doppler units around the detection target (S202). The method for identifying a target includes: detecting the same detection target multiple times; determining the current credibility of the detection target based on the current detection result of the detection target and the previous credibility of the detection target; and determining that the detection target is a specific target type based on the current credibility. The method uses radar to determine the credibility of the detection target and determines whether the detection target is a specific target type, thereby improving the accuracy of identifying the target type.

Description

A method for determining target credibility, a method for identifying a target, a system, a vehicle and a storage medium

The disclosure of this patent document contains material that is subject to copyright protection. The copyright is reserved by the copyright owner. The copyright owner has no objection to the facsimile reproduction by anyone of the patent document or the patent disclosure as it exists in the official records and files of the Patent and Trademark Office.

Technical Field

The embodiments of the present application relate to the field of unmanned driving technology, and in particular to a target credibility determination method, a target recognition method, a system, a radar, a movable platform, and a storage medium.

Background technique

With the development of the unmanned driving industry, assisted driving and autonomous driving have become current research hotspots. In the field of assisted driving and autonomous driving, target recognition is crucial to the realization of unmanned driving. For example, after effective recognition of different types of targets such as pedestrians, vehicles, and road signs, functions such as deceleration and avoidance, emergency parking, obstacle detours, lane changes, and automatic stop at stations can be performed according to specific scenarios.

In traditional technology, visual sensors are mainly used to collect images of targets to identify targets. However, visual sensors do not have the characteristics of all-day and all-weather when identifying targets. For example, in weak light, rain, snow, fog and haze, the effect of visual sensors in collecting images is not good, which will significantly reduce the effect of visual sensors on target recognition. At this time, if you rely solely on visual sensors, there may be a large number of scenarios where autonomous driving fails. Compared with visual sensors, millimeter-wave radars have the advantages of working all day and all weather, but related technologies have not yet achieved effective identification of targets through millimeter-wave radars.

Summary of the invention

Embodiments of the present application provide a target credibility determination method, a target recognition method, a system, a radar, a movable platform, and a storage medium.

In a first aspect, an embodiment of the present application provides a method for determining target credibility, the method comprising:

Acquire detection information of a detection target and information of Doppler units around the detection target;

The reliability of the type of the detection target is determined according to the detection information of the detection target and information of Doppler units around the detection target.

In a second aspect, an embodiment of the present application provides a target recognition method, the method comprising:

Detect the same detection target multiple times;

Determining the current credibility of the detection target according to the current detection result of the detection target and the last credibility of the detection target;

According to the current credibility, the detection target is determined to be a specific target type.

In a third aspect, an embodiment of the present application provides a target credibility determination system, the system comprising one or more processors, working together or individually, the processors being configured to perform the following operations:

Acquire detection information of a detection target and information of Doppler units around the detection target;

The reliability of the type of the detection target is determined according to the detection information of the detection target and information of Doppler units around the detection target.

In a fourth aspect, an embodiment of the present application provides a target recognition system, the system comprising one or more processors, working together or individually, the processors being configured to perform the following operations:

Detect the same detection target multiple times;

Determining the current credibility of the detection target according to the current detection result of the detection target and the last credibility of the detection target;

According to the current credibility, the detection target is determined to be a specific target type.

In a fifth aspect, an embodiment of the present application provides a radar, the radar comprising:

An antenna, wherein the antenna is used to obtain an echo signal;

A processor is communicatively connected to the antenna, and is used to execute the method described in any technical solution of the first aspect and/or the second aspect of the present application.

In a sixth aspect, an embodiment of the present application provides a movable platform, the movable platform comprising:

Body;

A power system, installed in the machine body, for providing power;

And the radar described in any technical solution in the fifth aspect of the present application.

In the seventh aspect, an embodiment of the present application provides a computer-readable storage medium, characterized in that a computer program is stored thereon, and the computer program is executed by a processor to implement the target credibility determination method provided by the technical solution of the first aspect of the present application and/or the steps of the target identification method provided by the technical solution of the second aspect of the present application.

In the embodiment of the present application, by detecting the target, obtaining the detection information of the target and the information of the Doppler unit around the target, and identifying the target based on the obtained information, the target can be effectively identified under all-day and all-weather conditions, thereby improving the stability and safety of autonomous driving/assisted driving.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

FIG1 is a schematic diagram of an application scenario provided by an embodiment of the present application;

FIG2 is a schematic diagram showing a flow chart of a method for determining target credibility provided by an embodiment of the present application;

FIG3 is a schematic diagram showing a flow chart of a method for determining target credibility provided by an embodiment of the present application;

FIG4 is a schematic diagram showing a flow chart of a method for determining target credibility provided by an embodiment of the present application;

FIG5 is a schematic diagram showing a flow chart of a target recognition method provided in an embodiment of the present application;

FIG6 is a schematic diagram showing a flow chart of a target recognition method provided by another embodiment of the present application;

FIG7 is a schematic diagram showing a flow chart of a target recognition method provided by yet another embodiment of the present application;

FIG8A shows a Doppler-range plane image provided by a specific embodiment of the present application, and FIG8B shows an algorithm implementation scheme of a specific embodiment of the present application;

FIG9 shows a schematic diagram of the structure of a target credibility determination system according to an embodiment of the present application;

FIG10 shows a schematic diagram of the structure of a target recognition system provided by an embodiment of the present application;

FIG11 is a schematic diagram showing the structure of a radar provided by an embodiment of the present application;

FIG12 is a schematic diagram showing the structure of a movable platform provided in an embodiment of the present application;

FIG. 13 shows a schematic structural diagram of a movable platform provided in an embodiment of the present application.

Detailed ways

In order to improve the safety of the automatic driving/assisted driving system, the embodiments of the present application propose a target credibility determination method, a target identification method, a system, a mobile platform, and a storage medium. At least one sensor carried on the movable platform: a visual system, a lidar, a millimeter-wave radar, and an ultrasonic radar, identifies the target by utilizing at least one of the above sensors required for automatic driving/assisted driving. For example, the target is identified by at least one of the above sensors carried on the movable platform. The target can be a person, an animal, a tree, a vehicle, a road sign, a fence, a drone, etc. The target identification method can be used to determine the type of target, determine the target's track, plan the track of the movable platform, and operate the movable platform in other scenarios.

Among them, the credibility is an evaluation index to measure the credibility of the type of the detection target. By detecting the detection target, the information of the detection target returned in the echo signal is obtained, and the credibility of the type of the detection target is generated based on the acquired information of the detection target. The higher the credibility, the higher the credibility of the type of the detection target; the lower the credibility, the lower the credibility of the type of the detection target. The type of the detection target is finally determined by making multiple judgments on the credibility determined by multiple detections.

In some embodiments, the same detection target is detected multiple times, and based on the current detection result of the detection target and the previous detection result of the detection target, the detection target is determined to be a specific target type, such as a pedestrian target, a drone target, etc.

In some embodiments, after the target is identified by the target identification method, the target's track can also be recorded and predicted, thereby tracking the target.

In some embodiments, after the target is identified by the target identification method, the movement trajectory of the movable platform can be planned according to the current track of the target, for example, deceleration and avoidance, emergency stop, obstacle detour, lane change, automatic stop at a station, etc.

The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

FIG1 provides an example of an application scenario provided by an embodiment of the present application. Referring to FIG1 , the movable platform is an unmanned vehicle 10 , and the movable platform includes a vehicle body 101 and a radar 102 . The radar 102 is installed on the vehicle body 101 .

The radar can be installed on a movable platform, such as a robot, an unmanned aerial vehicle, an unmanned vehicle, an ordinary vehicle, VR glasses, AR glasses, etc. Taking the radar installed on an unmanned vehicle as an example, the radar can be integrated in one or more locations of the vehicle, or a device installed on the vehicle, such as a vehicle-mounted device, etc., without limitation. Among them, the radar can be a millimeter wave radar or other types of radar sensors, without limitation. The radar includes at least an antenna, which is used to receive the echo signal.

In this embodiment, the radar 102 moves with the movement of the unmanned vehicle 10 to detect the target to be detected to obtain data for target credibility determination and target identification - obtaining detection information of the detected target and information of the Doppler unit around the detected target, and determining the credibility of the type of the detected target based on the detection information of the detected target and the information of the Doppler unit around the detected target; determining the current credibility of the detected target based on the current detection result of the detected target and the previous credibility of the detected target; and determining that the detected target is a specific target type based on the current credibility.

In this embodiment, the radar 102 used for target credibility determination and target identification may be a millimeter microwave radar.

FIG2 is a flow chart of a method for determining target credibility provided by an embodiment of the present application. As shown in FIG2 , the method may include:

S201: Acquire detection information of a detection target and information of Doppler units around the detection target.

The execution subject may be a radar or a processor installed on a mobile platform. The following takes the radar as an example to introduce the target credibility determination method in detail.

In some embodiments, the detection information of the detection target includes at least one of the following: distance, scattering intensity, speed information, angle information, and observation energy. Among them, the distance information includes the radial distance of the detection target relative to the radar; the scattering intensity information includes the echo intensity of the scattered echo generated by the detection target under the irradiation of the radar wave; the speed information includes the radial speed data of the detection target relative to the radar determined by the Doppler frequency shift; the angle information is the angle of the target object compared to the radar; and the observation energy is the energy of the echo signal.

Specifically, the radar acquires detection information of the detected target by transmitting electromagnetic waves and receiving feedback echo signals. Optionally, the echo signal is a frequency modulated continuous wave (FMCW), such as a fast scanning waveform, a triangle wave or a sawtooth wave.

In some embodiments, the information of the Doppler cells around the detection target includes at least one of the following: the Doppler cells around the detection target on the Doppler-range plane image acquired when the radar detects the detection target, the Doppler energy of each Doppler cell around the detection target, and the number of Doppler cells whose Doppler energy is greater than a preset Doppler energy threshold. The number of Doppler cells whose Doppler energy is greater than the preset Doppler energy threshold is determined in this way.

Specifically, obtaining the information of the Doppler units around the detection target may include but is not limited to: obtaining a Doppler-range plane image through a radar, the Doppler-range plane image including multiple Doppler units around the target; comparing the energy value of the Doppler unit with a preset Doppler energy threshold, and recording the number of Doppler units whose Doppler energy is greater than the preset Doppler energy threshold. Optionally, the Doppler unit whose Doppler energy is greater than the preset Doppler energy threshold is added to the Doppler unit set; otherwise, the Doppler unit is discarded.

The preset Doppler energy threshold can be a pre-set fixed value or an energy value of a reference Doppler unit. The Doppler energy threshold can be determined by the noise signal strength of the radar and the Doppler energy corresponding to different categories of targets. By counting the average energy of the noise, the average energy of the noise is selected and added to the constant Pn as the Doppler energy threshold. The constant Pn is the energy information of the radar acquisition target. Pn is obtained by multiple acquisitions and training of different categories of targets.

In this embodiment, the detection information of the detection target includes at least one of the following: distance, scattering intensity, and speed information; and the information of the Doppler units around the detection target includes at least one of the following: the Doppler energy of each Doppler unit around the detection target, and the number of Doppler units whose Doppler energy is greater than a preset Doppler energy threshold value.

The step of acquiring detection information of a detection target and information of Doppler units around the detection target specifically includes:

While acquiring the detection information of the detection target, the information of the Doppler units around the detection target is acquired, that is, while or after detecting the detection target, the detection information of the detection target and the information of the Doppler units around the detection target are acquired.

Alternatively, the detection information of the detection target is first obtained, and if the detection information of the detection target meets the first preset condition, the information of the Doppler unit around the detection target is obtained; and/or, if the detection information of the detection target does not meet the first preset condition, the information of the Doppler unit around the detection target is no longer obtained. A judgment is made for the detection information first, and the information of the Doppler unit around the detection target is obtained only when the first preset condition is met. This reduces the number of times the information of the Doppler unit around the detection target is obtained, reduces the amount of calculation, and improves the calculation speed of the system.

Specifically, determining whether the detection information satisfies the first preset condition specifically includes but is not limited to the following method: determining whether a specific parameter included in the detection information is within its corresponding threshold range. For example, determining whether the scattering intensity is within a preset scattering intensity threshold range, whether the speed information is within a preset speed threshold range, etc. The following three scenarios are exemplified for explanation:

For example, the detection information includes scattering intensity information. If the scattering intensity is within a preset scattering intensity threshold range, the detection information of the detection target satisfies a first preset condition, and the information of the Doppler units around the detection target is obtained. In some embodiments, if the scattering intensity is not within a preset scattering intensity threshold range, the detection information of the detection target does not satisfy the first preset condition, and the information of the Doppler units around the detection target is not obtained.

For another example, the detection information includes speed information. If the speed information is within a preset speed threshold range, the detection information of the detection target satisfies the first preset condition, and the information of the Doppler unit around the detection target is obtained. In some embodiments, if the speed information is not within the preset speed threshold range, the detection information of the detection target does not satisfy the first preset condition, and the information of the Doppler unit around the detection target is not obtained.

For another example, the detection information includes scattering intensity information and speed information. If the scattering intensity is within a preset scattering intensity threshold range, and the speed information is within a preset speed threshold range, the detection information of the detection target satisfies the first preset condition, and the information of the Doppler units around the detection target is obtained. That is, only when both conditions are met at the same time, the detection information of the detection target satisfies the first preset condition, and the information of the Doppler units around the detection target is obtained. In some embodiments, if the scattering intensity is not within the preset scattering intensity threshold range, and the speed information is not within the preset speed threshold range, the detection information of the detection target does not meet the first preset condition, and the information of the Doppler units around the detection target is not obtained.

Based on the above embodiment, the scattering intensity threshold range is determined, including but not limited to the following methods:

(1) Obtain the scattering intensity of the external target at different distances.

For targets of the same category, the distances between them and the radar are different, and the detection information contained in the echo signal obtained by the radar is also different. For example, when the distances between them and the radar are different, the radar detects the same target multiple times to obtain the scattering intensity of the target at different distances. In some embodiments, the scattering intensity of the targets at different distances is averaged in advance to improve the accuracy of the process of determining the target credibility. In some embodiments, for targets of multiple different categories, the radar detects the targets therein multiple times to obtain the scattering intensity of the targets at different distances.

In this embodiment, the scattering intensity of pedestrian targets at different distances is obtained as an example. In the field test, the radar detects pedestrian targets and obtains the scattering intensity of pedestrian targets at different distances. After that, the distance information and the scattering intensity information corresponding to the distance information are recorded at the same time. The obtained scattering intensities of pedestrian targets at different distances are averaged to form a scattering intensity average value and distance information change curve, or a scattering intensity average value and distance information lookup table of pedestrian targets.

(2) Determine the scattering intensity threshold range according to the scattering intensity of the external target at the different distances.

In some embodiments, the scattering intensity threshold is determined according to the scattering intensity average value and the distance information change curve. Optionally, considering that different types of targets have different scattering intensities, respective scattering intensity threshold ranges are determined for different types of targets. In some embodiments, considering that the radar has noise, the scattering intensity threshold is also determined by the noise signal strength of the radar. By statistically calculating the average intensity of the noise, the average intensity of the noise is selected and added to the scattering intensity of the target at different distances obtained as the scattering intensity threshold.

In this embodiment, when the movable platform is moving or stationary, the radar installed on the mobile platform detects an external target, performs multiple detections on the same target to obtain detection information of targets located at different distances, and processes the detection information to determine the scattering intensity threshold range to improve the accuracy of the target credibility determination process.

S202: Determine the credibility of the type of the detection target according to the detection information of the detection target and information of Doppler units around the detection target.

On the one hand, different types of targets have different movement speeds and/or scattering intensities. For example, the speed of a pedestrian target will not exceed a predetermined value, and the scattering intensity of a pedestrian target is weaker than that of a vehicle. In some embodiments, the credibility of the type of the detected target is determined based on the acquired detection information of the detected target. For example, the credibility of the type of the detected target is determined by acquiring information such as the speed, scattering intensity, and distance of the detected target.

Specifically, a pedestrian target is used as an example for explanation. For example, the speed information of the detection target obtained can be used to determine the credibility of the type of the detection target in combination with the speed range corresponding to different types of targets. When the speed information of the detection target obtained meets the speed range corresponding to the pedestrian target, the credibility of the detection target being a pedestrian is increased, for example, by increasing the first preset value. And/or, when the speed information of the detection target obtained does not meet the speed range corresponding to the pedestrian target, the credibility of the detection target being a pedestrian is reduced, for example, by subtracting the second preset value.

For another example, the scattering intensity of the detected target obtained can be compared with a pre-generated scattering intensity average value and distance information change curve, or a pedestrian target scattering intensity average value and distance information lookup table. When the scattering intensity of the detected target obtained meets the preset scattering intensity range corresponding to the pedestrian target, the credibility of the detected target being a pedestrian is increased, for example, by increasing the first preset value. And/or, when the scattering intensity of the detected target obtained does not meet the preset scattering intensity range corresponding to the pedestrian target, the credibility of the detected target being a pedestrian is reduced, for example, by subtracting the second preset value.

For another example, when the speed information of the detected target obtained satisfies the speed range corresponding to the pedestrian target, and when the scattering intensity of the detected target obtained satisfies the preset scattering intensity range corresponding to the pedestrian target, the credibility of the detected target being a pedestrian is increased; otherwise, the credibility of the detected target being a pedestrian is deducted.

On the other hand, the movement of the target is more complicated. It not only has overall movement, but also has micro-movements such as acceleration, vibration, rotation, and tumbling. The micro-movement of the target has corresponding micro-Doppler features, which contain iconic information about the target type such as movement and behavior, reflecting the fine characteristics of the target. The micro-movement of different types of targets has different micro-Doppler features, making the identification of the target unique. For example, when a person moves, the swing of his limbs has obvious micro-Doppler features, which contain iconic information about human movement and behavior. The iconic information, such as Doppler energy, is extracted from the micro-Doppler features to effectively identify pedestrian targets.

In some embodiments, the information of the Doppler units around the detection target is obtained and analyzed to obtain the corresponding micro-Doppler features, and the iconic information, such as Doppler energy, is extracted therefrom, and the Doppler units whose Doppler energy is greater than a preset Doppler energy threshold are obtained, so that the credibility is determined according to the number of the Doppler units whose Doppler energy is greater than the preset Doppler energy threshold. By obtaining and analyzing the information of the Doppler units around the detection target, the credibility of determining the target type is more accurate.

Specifically, the credibility of determining that the type of the detection target is a pedestrian is described as an example. When the number of the Doppler units whose Doppler energy is greater than the preset Doppler energy threshold is greater than or equal to the Doppler unit number threshold, the credibility of the detection target being a pedestrian is increased; and/or, when the number of the Doppler units whose Doppler energy is greater than the preset Doppler energy threshold is less than the Doppler unit number threshold, the credibility of the detection target being a pedestrian is reduced.

In this embodiment, the method for determining the credibility of the type of the detection target according to the detection information of the detection target and the information of the Doppler unit around the detection target is specifically as follows:

The detection information includes scattering intensity information. When the scattering intensity is within a preset scattering intensity threshold range and the information of the Doppler unit around the detection target meets the preset Doppler unit condition, the credibility is increased by a first preset value; otherwise, the credibility is reduced by a second preset value.

Alternatively, the detection information includes speed information. When the speed information is within a preset speed threshold range and the information of the Doppler unit around the detection target meets a preset Doppler unit condition, the credibility is increased by a first preset value; otherwise, the credibility is reduced by a second preset value.

Alternatively, the detection information includes scattering intensity information and speed information. When the speed information is within a preset speed threshold range, the scattering intensity is within a preset scattering intensity threshold range, and the information of the Doppler unit around the detection target meets a preset Doppler unit condition, the credibility is increased by a first preset value; otherwise, the credibility is reduced by a second preset value.

In some embodiments, the method further includes determining the type of the target based on the credibility of the determined type of the detected target. Optionally, at least one credibility range of different types of targets is pre-set. When the credibility of the determined type of the detected target is within a certain credibility range, the target is determined to be the target type corresponding to the credibility range.

The target credibility determination method provided in the embodiment of the present application obtains the detection information of the detection target and the information of the Doppler unit around the detection target, and determines the credibility of the type of the detection target based on the detection information of the detection target and the information of the Doppler unit around the detection target. Thus, the credibility of the target type is determined based on the information obtained by the radar. The speed of system operation is improved, which is conducive to the accuracy of determining the type of the detection target, and is conducive to improving the safety and stability during the automatic driving/assisted driving process.

Based on FIG2 , FIG3 is a flow chart of a method for determining target credibility provided in an embodiment of the present application. Referring to FIG3 , it specifically includes:

Step S301: Acquire the number of the Doppler units whose scattering intensity is within a preset scattering intensity threshold range.

In this embodiment, it specifically includes:

(1) Obtaining the Doppler energy of each Doppler unit around the detection target.

The radar can obtain the energy value, distance value and speed value of a large number of scattering points (Doppler units) of the detection target. Optionally, the relationship between the energy value and the distance value of each Doppler unit can constitute a Doppler-range plane, which includes multiple Doppler units.

In some embodiments, before obtaining the Doppler energy of each Doppler unit around the detection target, the echo signal obtained by the radar is preprocessed to obtain the Doppler energy of each Doppler unit around the detection target. For example, the radar uses FFT (Fast Fourier Transform) technology to perform coherent accumulation on the echo signal obtained by the radar to obtain the Doppler energy of each Doppler unit around the detection target. Of course, in practical applications, other technologies can also be used to obtain, and there is no limitation on this.

(2) Determining the number of the Doppler bins whose scattering intensity is within a preset scattering intensity threshold range according to the Doppler energy of each Doppler bin.

Energy screening is performed for each Doppler unit around the detection target, for example, by filtering through RCS (Radar Cross Section) or CFAR (Constant False-Alarm Rate) algorithms. A preset Doppler energy threshold can be obtained through a related method. After the Doppler energy of each Doppler unit around the detection target is obtained through the radar, the Doppler units around the detection target can be filtered using the preset Doppler energy threshold, thereby filtering some invalid Doppler units, avoiding these invalid Doppler units from affecting subsequent judgments, and reducing the amount of calculation. In some embodiments, the above-mentioned filtered Doppler units can also be filtered twice, for example, using the one-ring rule to output higher quality Doppler units, to determine to further reduce the amount of calculation and improve processing efficiency.

The specific method for determining the preset Doppler energy threshold may refer to but is not limited to the following method:

First, for different types of targets, the radar can collect energy information and distance information of the target at different times in advance. For example, during the movement of the movable platform, the radar installed on the movable platform can continuously collect Doppler energy information and distance information of the target. Then, the energy and distance change curve of the radar is obtained according to the Doppler energy information and the distance information. Finally, the preset Doppler energy threshold curve is determined according to the change curve.

In some embodiments, in some embodiments, considering that the radar has noise, the preset Doppler energy threshold can also be corrected according to the noise data of the radar. For example, the noise floor of the radar can be added to the preset Doppler energy threshold to obtain the corrected preset Doppler energy threshold. Of course, in practical applications, other methods can also be used to correct the preset Doppler energy threshold, which is not limited.

Step S302: Determine whether the number of Doppler units is within a preset range of the number of Doppler units according to the number of Doppler units, and determine the credibility.

In this embodiment, a pedestrian target is taken as an example for explanation. Specifically, if the number of Doppler units whose Doppler energy of the detected target is greater than the preset Doppler energy threshold is within the preset Doppler unit number range corresponding to the pedestrian target, the credibility is increased by a third preset value; and/or, if the number of Doppler units is not within the preset Doppler unit number range corresponding to the pedestrian target, the credibility is reduced by a fourth preset value.

The specific method for determining the preset range of the number of Doppler units can be found in the following method:

Take the example of obtaining the number of Doppler units whose Doppler energy is greater than the preset Doppler energy threshold at different distances from a pedestrian target as an example. The radar detects the pedestrian target and obtains the number of Doppler units whose Doppler energy is greater than the preset Doppler energy threshold at different distances from the pedestrian target. Afterwards, the distance information and the number of Doppler units of the pedestrian target corresponding to the distance information whose Doppler energy is greater than the preset Doppler energy threshold are recorded at the same time. The number of Doppler units whose Doppler energy of the pedestrian target at different distances is greater than the preset Doppler energy threshold is averaged to form a Doppler unit number threshold average value and distance information change curve, or a Doppler unit number threshold average value and distance information lookup table for pedestrian targets.

The target credibility determination method provided in the embodiment of the present application is beneficial to the accuracy of determining the type of the detected target and to improving the safety and stability during the autonomous driving/assisted driving process by obtaining the number of detection units whose Doppler energy is greater than a preset Doppler energy threshold among the Doppler units around the detected target and determining the credibility of the target type.

Based on the embodiment shown in FIG. 2 , FIG. 4 is a flow chart of a method for determining target credibility provided in an embodiment of the present application, which specifically includes:

Step S401, obtaining the distance information;

Specifically, the radial distance of the detection target relative to the radar or the movable platform on which the radar is installed is obtained.

Step S402: judging whether the distance information is less than a preset distance according to the distance information;

Specifically, the radar mounted on a car is used as an example for explanation. Based on the radial distance of the detected target relative to the radar or the car on which the radar is installed, it is determined whether the distance information is less than the preset distance. Optionally, the preset distance is predetermined in multiple field tests. For example, a fixed value of the preset distance is predetermined, or the preset distance at different speeds is determined based on the speed of the car on which the radar is installed. It is understandable that the determination of the preset distance is also related to at least one of the following factors: weather conditions, light intensity, driver's eyesight, braking equipment, and road conditions. The method for determining the preset distance based on any of the above factors is not limited here.

The preset distance is greater than or equal to the safe vehicle distance, that is, the preset distance is greater than or equal to the necessary distance between the car equipped with the radar and the detection target during driving, so that sufficient braking space (including braking time, braking distance, etc.) is left in case of emergency, which is conducive to the safe driving of the car.

Step S403: If the distance information is less than a preset distance, the movable platform is controlled to perform an obstacle avoidance operation, or the alarm device is controlled to perform an alarm process.

Specifically, when the distance information is less than the preset distance, the radar or the movable platform on which the radar is installed is relatively close to the detection target. In order to ensure the safety during the automatic driving/assisted driving process, the movable platform can be controlled to perform obstacle avoidance operations, and/or the alarm device can be controlled to perform alarm processing. In some embodiments, controlling the alarm device to perform alarm processing includes: the movable platform on which the radar is installed controls the alarm device to display an alarm through an LED light, or to display an alarm through a digital display, or to broadcast an alarm through voice, or to vibrate an alarm based on the distance information. The alarm device can be the movable platform, or other control platforms, etc., or it can be an APP of the corresponding device. Thereby ensuring the safety during the automatic driving/assisted driving process.

The target credibility determination method provided in the embodiment of the present application obtains the distance information of the detected target and determines whether the distance information is less than the preset distance. Once the distance information is less than the preset distance, the movable platform is controlled to perform obstacle avoidance operation, or the alarm device is controlled to perform alarm processing. Thus, passengers or drivers can be informed of abnormal situations during driving in a timely manner, ensuring the safety of the automatic driving/assisted driving process.

FIG5 is a flow chart of a target recognition method provided by another embodiment of the present application, including:

Step S501: Detect the same detection target multiple times.

When detecting a detection target, interference may occur during the detection process, resulting in a large difference in the detection results of the detections. This results in a large difference in the credibility of the detection results determined at the time of the detections, which in turn causes problems in determining that the target is a certain target type. For example, when detecting a detection target by radar, multipath interference may occur, which in turn affects the detection results. The following is an example of detecting a detection target by radar.

In some embodiments, the radar detects the same detection target once and obtains the detection result of the same detection target once. Optionally, the radar can detect multiple detection targets simultaneously or asynchronously and obtain the detection result of each detection target respectively. Optionally, the detection result includes but is not limited to the detection information of the detection target and the information of the Doppler unit around the detection target.

In some embodiments, the radar obtains the current detection result of the detection target according to the echo signal. Optionally, the current detection result of the detection target is obtained through the linear frequency modulation continuous wave radar echo signal.

Step S502: Determine the current credibility of the detection target according to the current detection result of the detection target and the previous credibility of the detection target.

Each time the radar detects the same detection target, it can determine the credibility based on the detection information obtained each time. When the radar detects the same detection target at the current moment, the determination of the current credibility depends on the detection information obtained at the current moment and the previous credibility. Therefore, as the number of detections of the radar for the same detection target increases, the current credibility of the detection target is constantly updated.

In some embodiments, for the current detection result, the current credibility of the detection target is determined by the following method: if the current detection result meets the second preset condition, the current credibility is the previous credibility plus the first preset value; otherwise, the current credibility is the previous credibility minus the second preset value.

The current detection result includes but is not limited to: the detection information of the detection target at the current moment and the information of the Doppler unit around the detection target. Optionally, the second preset condition: the detection information of the detection target at the current moment meets the preset detection information condition and the information of the Doppler unit around the detection target meets the preset Doppler condition.

Specifically, if the detection information of the detection target at the current moment meets the preset detection information condition and the information of the Doppler unit around the detection target meets the preset Doppler condition, the current credibility is the previous credibility plus the first preset value; otherwise, the current credibility is the previous credibility minus the second preset value.

It should be noted that the target credibility determination method involved in the embodiment of the present application can also be used in the embodiment of the above-mentioned target recognition method. Optionally, the "preset detection information condition" described in the above-mentioned embodiment corresponds to the "first preset condition" involved in an embodiment of the present application shown in Figure 2. Optionally, the "preset Doppler condition" described in the above-mentioned embodiment corresponds to the "preset Doppler unit number range" and "preset Doppler energy threshold" involved in an embodiment of the present application shown in Figure 2.

In some embodiments, multiple detection targets may be detected separately and detection results may be obtained separately. The multiple detection results of the multiple detection targets may be processed simultaneously or asynchronously. This enables the determination of target types for multiple detection targets and improves the safety and reliability of the operation of the autonomous driving/assisted driving system.

Step S503: Determine, based on the current credibility, that the detected target is a specific target type.

The current credibility of the detected target represents the credibility of the detected target being a specific target type at the current moment. As the number of detections of the same detected target by the radar increases, the current credibility of the detected target is constantly updated. Therefore, when the same target is detected multiple times to determine and update the current credibility of the detected target, the current credibility of the detected target can accurately determine whether the detected target is a specific target type.

Optionally, the type of the detection target is determined based on the number of times the same detection target is detected and the current credibility. Specifically, take determining whether the detection target is a pedestrian target as an example for explanation. The radar detects the detection target for the first time, obtains the first detection result, and determines the first credibility that the detection target is a pedestrian target based on the detection result; then, the radar detects the detection target for the second time, obtains the second detection result, and based on the detection result, adds or subtracts points on the basis of the first credibility to determine the second credibility that the detection target is a pedestrian target. And so on to the Nth time. Finally, determine whether the detection target is a pedestrian target based on the Nth credibility.

The target recognition method provided in the embodiment of the present application detects the same detection target multiple times, determines the current credibility of the detection target according to the current detection result of the detection target and the previous credibility of the detection target; and determines that the detection target is a specific target type according to the current credibility. Thus, it is determined whether the target is a specific target type based on the information obtained by the radar. It effectively avoids the problem of determining the target type caused by abnormal detection results, improves the accuracy of target recognition, and is conducive to improving the safety and stability during autonomous driving/assisted driving.

Based on the embodiment shown in FIG. 5 , FIG. 6 shows a flow chart of a target recognition method provided by another embodiment of the present application, including:

Step S601: When the number of detections performed on the same detection target is less than a first preset detection number, the current credibility of the detection target determined by each detection of the same detection target is compared with the first preset credibility.

Specifically, the method of determining that the detection target is a pedestrian target is described as an example. A detection number threshold value for detecting the same detection target is preset as a stop condition for multiple detections of the same detection target. For example, a first preset detection number is set as the detection number threshold value. A credibility threshold is set as a judgment condition for determining whether the detection target is a pedestrian target. For example, a first preset credibility is set as the credibility threshold. As the number of detections of the detection target by the radar increases, the current credibility of the detection target is updated on the basis of the previous credibility. When the number of detections of the detection target by the radar is less than the first preset detection number, the current credibility of the detection target determined by each detection of the same detection target is compared with the first preset credibility. Once the number of detections of the detection target is greater than or equal to the first preset detection number, the detection target is no longer detected, so there is no need to compare the current credibility of the detection target determined by the detection of the same detection target with the first preset credibility. Thereby, the operation speed is improved, and the efficiency of determining that the detection target is a specific target type is improved.

Step S602: If the current credibility of the detection target determined by detecting the same detection target each time is less than the first preset credibility, it is determined that the detection target is not the specific target type; and/or, if the current credibility is greater than the first preset credibility, it is determined that the detection target is the specific target type.

Specifically, the example of determining that the detection target is a pedestrian target is used for explanation. Optionally, a first preset detection number is used as a detection number threshold for detecting the same detection target, that is, as a stop condition for multiple detections of the same detection target. When the detection number of multiple detections of the same detection target reaches the first preset detection number, the detection of the same detection target is stopped. Thus, within a limited number of times, the determination of whether the detection target is the specific target type is completed.

For example, if the credibility of each detection target determined by detecting the same detection target is less than the first preset credibility until the detection number of the same detection target reaches the first preset detection number, it is determined that the detection target is not a pedestrian target. This reduces the amount of calculation of the system and improves the efficiency of identifying the detection target.

For another example, when the number of detections of the same detection target does not reach the first preset detection number, after each detection of the detection target, the current credibility of the detection target is compared with the first preset credibility. If the current credibility of the detection target is greater than the first preset credibility, the detection target is determined to be a pedestrian target. The same detection target is no longer detected, and it is no longer determined whether the detection target is a pedestrian target. This reduces the amount of calculation of the system and achieves rapid identification of the detection target.

The target recognition method provided in the embodiment of the present application determines the category of the detection target according to the current credibility of the detection target when the number of detections of the same detection target does not reach the first preset detection number. After determining that the target is of a specific category, a fixed value judgment is made; if the target is not determined to be of a specific category at the first preset number of times, the target is determined not to be a specific target type. Through this method, the efficiency of target recognition is effectively improved, and the safety during the automatic driving/assisted driving process is also improved.

Based on the embodiment shown in FIG. 5 , FIG. 7 is a flow chart of a target recognition method provided by another embodiment of the present application, including:

Step S701: When the number of detections for the same detection target is less than the first preset detection number, and the current credibility is greater than the first preset credibility, the first preset credibility is reduced by a fifth preset value.

When the radar detects a target, due to the multipath interference phenomenon, the signal returned from the target reaches the radar antenna through different paths, making the radar unstable and causing errors in the radar's detection results. By detecting the same detection target multiple times, the detection error can be effectively eliminated, which helps to improve the radar's ability to identify the target category.

Specifically, it is described by taking determining that the detected target is a pedestrian target as an example.

In some embodiments, the target is determined to be a pedestrian target based on the detection result obtained at the previous detection moment; and the target is determined not to be a pedestrian target based on the detection results obtained at the current and subsequent detection moments. If the number of detections of the same detection target is less than the first preset number of detections, the detection target is no longer detected after the target is determined to be a pedestrian target based on the detection result obtained at the previous detection moment, and the detection result obtained at the previous detection moment is incorrect, an erroneous judgment may occur in determining whether the detection target is a pedestrian target.

To avoid the above situation, in some embodiments, the target detection exit hysteresis judgment is set. For example, when the number of detections of the same detection target is less than the first preset detection number, after each detection of the same detection target, the current credibility is compared with the first preset credibility. If the current credibility is greater than the first preset credibility, the first preset credibility is updated, for example, by reducing the fifth preset value. Therefore, after the next detection of the same detection target, what needs to be compared is the next credibility and the updated first preset credibility.

In some embodiments, if the credibility of each detection target determined by detecting the same detection target is less than the first preset credibility until the number of detections of the same detection target reaches the first preset detection number, it is determined that the detection target is not a pedestrian target. Optionally, at this time, the determination of whether the detection target is a pedestrian target is exited, and the first preset credibility does not need to be updated.

Step S702: When the number of detections for the same detection target is less than the first preset detection number and the current credibility is greater than the first preset credibility, continue to detect the detection target, wherein the target type of the detection target is determined before continuing to detect for a second preset detection number.

Specifically, when the number of detections for the same detection target is less than the first preset detection number, after each detection of the same detection target, the current credibility is compared with the first preset credibility. If the current credibility is greater than the first preset credibility, the detection target continues to be detected. This helps to avoid misjudgment of the type of the detection target at the current moment due to an incorrect detection result obtained at the previous detection moment. Optionally, before continuing to detect the detection target, a second detection number is set as a termination condition for determining the target type of the detection target. In the process of continuing to detect the detection target, before the number of continued detections reaches the second detection number, the target type of the detection target needs to be determined. In this way, the type of the detection target is accurately determined in a limited number of detections, the processing time is reduced, and the safety of automatic driving/assisted driving is improved.

Step S703: If the current credibility of the detection target determined by detecting the same detection target each time is greater than or equal to the first preset credibility, then the detection target is determined to be the specific target type; and/or, if the current credibility of the detection target determined by detecting the same detection target each time is less than the first preset credibility, then it is determined that the detection target is not the specific target type.

Specifically, when the number of detections for the same detection target is less than the first preset detection number, before continuing to detect the detection target, a threshold value is preset, and the threshold value is used to determine whether to determine that the detection target is a specific target type.

For example, when continuing to detect the detection target, once the number of continued detections reaches the threshold value, the detection target is determined to be a specific target type. Optionally, the detection target can be continued to be detected. Optionally, the threshold value can also be used as a stop condition for continuing to detect the same detection target. Once the number of continued detections reaches the threshold value, the continued detection of the same detection target is stopped. This avoids the problem of large system computation and slow computation speed caused by continuously acquiring and analyzing streaming data information.

In this embodiment, a second preset number of detections is set as the threshold value. The number of continued detections of the detection target is less than the second preset number of detections. In this process, if the current credibility of the detection target determined by each detection of the same detection target is greater than or equal to the first preset credibility, the detection target is determined to be a specific target type. And/or, if the current credibility of the detection target determined by each detection of the same detection target is less than the first preset credibility, the detection target is determined not to be a specific target type. Through this method, the misjudgment of the determination of the target type due to the jitter of the detection result is effectively avoided.

In some embodiments, when the detected target is determined to be a specific target type, the alarm device is controlled to perform alarm processing. Specifically, the alarm device can be the movable platform, or other control platforms, etc., so as to ensure the safety of the automatic driving/assisted driving process.

In some embodiments, after determining that the detected target is a specific target type, the target type of the detected target is output through LED light display, voice broadcast, or vibration. Specifically, the movable platform on which the radar is installed controls the alarm device to display an alarm through an LED light, display an alarm through a digital display, broadcast an alarm through a voice, or vibrate an alarm according to the specific target type of the detected target.

In some embodiments, the radar is a millimeter wave radar.

The target recognition method provided in the embodiment of the present application sets the target detection exit hysteresis judgment, which effectively solves the abnormal results caused by interference in detection, effectively improves the accuracy of target recognition, and is beneficial to improving the safety and stability during autonomous driving/assisted driving.

In a specific embodiment, the detection target is determined to be a pedestrian target as an example for description.

FIG8A shows a Doppler-range plane information provided by a specific embodiment of the present application, see FIG8A . Among them, each acquisition of a frame of data corresponds to the acquisition of a frame of Doppler-range unit plane image, the darker the color, the higher the Doppler energy representing the Doppler unit; the lighter the color, the lower the Doppler energy representing the Doppler unit. Pedestrian targets have an extended characteristic in Doppler due to the swinging of arms and legs when walking, so there are multiple Doppler units around the target. The Doppler energy of the multiple Doppler units around the pedestrian target is relatively low. Based on the above characteristics, it can be determined whether the detected target is a pedestrian target.

FIG8B shows an algorithm implementation scheme of a specific embodiment of the present application. As shown in FIG8B , the specific algorithm execution steps are as follows:

(1) Train the scattering intensity threshold range for pedestrian targets.

Through multiple field tests, the scattering intensity of pedestrian targets at different distances is obtained, and the scattering intensity is averaged to obtain a scattering intensity threshold lookup table. The energy fluctuation range is obtained based on multiple measurements, such as ±P_a, where P_a is a constant. The scattering intensity threshold is selected according to the distance of the detection target. If the scattering intensity of the detection target is within the set threshold ±P_a, the scattering intensity condition of the pedestrian target is met.

(2) Set a speed threshold range for pedestrian targets.

The speed of the pedestrian target is set to no more than 10m/s, and the speed range is adjustable. If the speed of the detected target exceeds the speed range, it is considered that the target is not a pedestrian target.

(3) Doppler energy threshold range training for pedestrian targets

The most appropriate Doppler energy threshold is selected through multiple trainings, and the Doppler energy threshold range is determined according to the noise signal strength of the radar system. Specifically, the average Doppler energy of non-targets is counted, for example, the result is P_n, and the Doppler energy threshold + P_n is selected as the Doppler energy threshold range, where P_n is a constant.

(4) Perform Doppler unit number threshold training for pedestrian targets.

When the Doppler unit corresponding intensity around the detected target meets the Doppler energy threshold range set in (3), the count is increased by 1. When the count exceeds the Doppler unit number threshold, the Doppler characteristics of the pedestrian target are met, that is, the Doppler decision condition is met. The Doppler unit number threshold is obtained by taking the average of multiple pedestrian targets.

(5) Calculate the pedestrian probability of the detected target.

The radar detects the target once, obtains detection data once, and determines the probability that the target is a pedestrian. That is, each time it detects, it obtains a frame of detection data and determines the credibility of the target being a pedestrian.

If for a single frame of data, the detection target simultaneously meets the pedestrian scattering intensity threshold range, pedestrian speed threshold range and Doppler judgment conditions, the pedestrian probability Prob_i of the detection target is increased by the probability Probl; if the target does not meet the intensity judgment, the pedestrian probability Prob_i is subtracted from the probability Prob2; if the target does not meet the speed judgment, the pedestrian probability Prob_i is subtracted from the probability Prob3, where Prob1, Prob2, and Prob3 are constants obtained through training of multiple pedestrian targets.

(6) Setting the pedestrian detection probability threshold

a) Determine whether the detection target is a pedestrian target through single-frame data. Since the detection process may be disturbed, a large number of misjudgments will occur. Therefore, here we use multi-frame accumulation and joint judgment, that is, by detecting the same detection target multiple times, the current credibility of the detection target is determined according to the current detection result of the detection target and the previous credibility of the detection target; and based on the current credibility, determine whether the detection target is a pedestrian target. Within the set frame number range, when the current credibility of the detection target is greater than the first preset credibility threshold, the target is judged as a pedestrian target. If the number of frames reaches the set number of frames, when the current credibility of the detection target still does not reach the first preset credibility threshold, the target is judged as a non-pedestrian target.

b) In order to avoid jitter in pedestrian detection results, that is, the current frame judges that the detection target is a pedestrian target, the next frame judges it as a non-pedestrian target, and then it is detected as a pedestrian target again. The present invention sets the pedestrian detection to exit the hysteresis judgment. After the current frame judges that the detection target is a pedestrian target, the first preset credibility is updated to a smaller value, and the next frame continues to be judged. In the subsequent process of detecting the detection target, obtaining detection data, and determining the current credibility, within a limited number of detection times, such as the second preset number of detection times, once it is determined that the current credibility of the detection target is less than the updated first preset credibility, the detection target is determined to be a non-pedestrian target; if within the second preset number of detections, each time the credibility of the detection target is determined to be greater than or equal to the updated first preset credibility, the detection target is determined to be a pedestrian target.

When the current credibility of the detection target determined in the next frame is lower than the set credibility threshold, the pedestrian detection state is changed to the non-pedestrian detection state. The threshold setting value is smaller than the threshold in a), that is, the first preset credibility is updated to a smaller value.

This specific embodiment shows how to determine whether a detected target is a pedestrian target. It should be understood that for detected targets with micro-Doppler characteristics, it is applicable to determine the target type of the detected target by the technical solution described in this embodiment. For example, based on the micro-Doppler characteristics of the propeller of a drone when it moves, it can be determined whether the detected target is a drone.

Based on the embodiments shown in Figures 2 to 5, the embodiment of the present application provides a target credibility determination system, and Figure 9 is a schematic diagram of the structure of a target credibility determination system provided by the embodiment of the present application. As shown in Figure 9, the target credibility determination system 90 includes: a processor 901. Optionally, the processor 901 is one or more, working together or individually, and the processor 901 is used to execute the technical solution of the embodiment of the above-mentioned target credibility determination method.

Optionally, the target credibility determination system 90 further includes: a memory 902 and a radar 903. The memory is used to store program codes;

The processor 901 calls the program code, and when the program code is executed, is used to perform the following operations:

Acquire detection information of a detection target and information of Doppler units around the detection target;

The reliability of the type of the detection target is determined according to the detection information of the detection target and information of Doppler units around the detection target.

Optionally, the radar 903 is separately provided from the processor 901. Optionally, the radar 903 includes the processor 901.

The target credibility determination system provided in this embodiment can execute the technical solution of the embodiment of the above-mentioned target credibility determination method, and the execution method and beneficial effects are similar, which will not be repeated here.

On the basis of the embodiments shown in FIG6 and FIG7, the embodiment of the present application provides a target recognition system, and FIG10 is a schematic diagram of the structure of a target recognition system provided by the embodiment of the present application. As shown in FIG10, the target recognition system 100 includes: The target recognition system 100 includes: a processor 1001. Optionally, the processor 1001 is one or more, working together or individually, and the processor is used to execute the technical solution of the embodiment of the above-mentioned target recognition method.

Optionally, the target recognition system 100 further includes: a memory 1002 and a radar 1003. The memory 1002 is used to store program codes;

The processor 1001 calls the program code, and when the program code is executed, is used to perform the following operations:

Detect the same detection target multiple times;

Determining the current credibility of the detection target according to the current detection result of the detection target and the last credibility of the detection target;

According to the current credibility, the detection target is determined to be a specific target type.

Optionally, the radar 1003 is separately configured from the processor 1001. Optionally, the radar 1003 includes the processor 1001.

The target recognition system provided in this embodiment can execute the technical solution of the above-mentioned target recognition system method embodiment, and the execution method and beneficial effects are similar, which will not be repeated here.

On the basis of the above embodiments, the embodiment of the present application provides a radar. FIG11 is a schematic diagram of the structure of a radar provided in the embodiment of the present application. As shown in FIG11 , the radar 110 includes: an antenna 1101 and a processor 1102 .

Antenna 1101, the antenna is used to obtain an echo signal;

The processor 1102 is communicatively connected to the antenna, and is used to execute the technical solution of the above-mentioned target credibility determination method embodiment, and/or to execute the technical solution of the target recognition method embodiment.

Based on the embodiment shown in Figure 9, the embodiment of the present application provides a movable platform. Figure 12 is a movable platform 120 provided by the embodiment of the present application. As shown in Figure 12, the movable platform 120 includes: a body 1201, a power system 1202 and the target credibility determination system 90 of the above-mentioned technical solution.

The movable platform 120 may be any one of the following: a robot, an unmanned aerial vehicle, an unmanned vehicle, an ordinary vehicle, VR glasses, and AR glasses.

The movable platform of the embodiment shown in FIG. 12 can be used to execute the technical solution of the above-mentioned target credibility determination method embodiment, and its implementation principle and technical effect are similar and will not be repeated here.

Based on the embodiment shown in Figure 10, the embodiment of the present application provides a movable platform. Figure 13 is a movable platform 130 provided by the embodiment of the present application. As shown in Figure 13, the movable platform 130 includes: a fuselage 1301, a power system 1302 and the target recognition system 100 of the above-mentioned technical solution.

The movable platform 130 can be any of the following: a robot, an unmanned aerial vehicle, an unmanned vehicle, an ordinary vehicle, VR glasses, and AR glasses.

The movable platform of the embodiment shown in FIG. 13 can be used to execute the technical solution of the above-mentioned target recognition method embodiment, and its implementation principle and technical effect are similar and will not be repeated here.

In addition, this embodiment further provides a computer-readable storage medium on which a computer program is stored. The computer program is executed by a processor to implement the target credibility determination method and/or target recognition method described in the above embodiments.

In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform some steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example for illustration. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims (46)

1. A target credibility determination method, applied to a radar, characterized by comprising:

Acquiring detection information of a detection target and information of Doppler units around the detection target, wherein the information of the Doppler units around the detection target comprises at least one of the following: the Doppler energy of each Doppler unit around the detection target and the number of Doppler units with the Doppler energy greater than a preset Doppler energy threshold value;

and determining the credibility of the type of the detection target according to the detection information of the detection target and the information of Doppler units around the detection target.

2. The method of claim 1, wherein the detection information of the detection target comprises at least one of: distance, scattering intensity, velocity information.

3. The method according to claim 1, wherein the reliability is increased by a first preset value when the detection information of the detection target satisfies a preset condition and information of doppler cells around the detection target satisfies a preset doppler cell condition; otherwise, subtracting a second preset value from the reliability.

4. The method of claim 3, wherein the detection information of the detection target includes scattering intensity and velocity information,

And when the speed information is within a preset speed threshold range, determining that the detection information of the detection target meets a preset condition when the scattering intensity is within the preset scattering intensity threshold range.

5. The method of claim 3, wherein the detection information of the detection target includes a scattering intensity,

And when the scattering intensity is within a preset scattering intensity threshold range, determining that the detection information of the detection target meets a preset condition.

6. The method according to claim 3, wherein the detection information of the detection target includes speed information,

And when the speed information is within a preset speed threshold range, determining that the detection information of the detection target meets a preset condition.

7. The method according to claim 4 or 5, wherein before the acquisition of the detection information of the detection target, further comprising:

acquiring the scattering intensities of the external target at different distances;

and determining the scattering intensity threshold range according to the scattering intensities of the acquired external targets at the different distances.

8. The method of claim 1, wherein the step of determining the position of the substrate comprises,

And when the detection information of the detection target meets a first preset condition, acquiring the information of Doppler units around the detection target.

9. The method according to claim 8, characterized in that it comprises in particular:

The detection information comprises a distance and scattering intensity, and/or comprises speed information if the scattering intensity is within a preset scattering intensity threshold range, and the detection information of the detection target meets a first preset condition if the speed information is within a preset speed threshold range; otherwise, the detection information of the detection target does not meet the first preset condition.

10. The method of claim 1, wherein the step of determining the position of the substrate comprises,

And acquiring the information of Doppler units around the detection target while acquiring the detection information of the detection target.

11. The method according to claim 1, characterized in that it comprises:

The information of Doppler units around the detection target comprises Doppler energy of each Doppler unit around the detection target and the number of Doppler units with scattering intensity within a preset scattering intensity threshold value range;

and determining the credibility according to the number of Doppler units of the scattering intensity within a preset scattering intensity threshold range.

12. The method according to claim 11, comprising:

Acquiring the number of Doppler units of the scattering intensity within a preset scattering intensity threshold range;

and determining whether the number of Doppler units is within a preset Doppler unit number range according to the number of Doppler units, and determining the credibility.

13. The method according to claim 12, comprising:

Acquiring Doppler energy of each Doppler unit around the detection target;

And determining the number of Doppler units with the scattering intensity within a preset scattering intensity threshold according to the Doppler energy of each Doppler unit.

14. The method according to claim 11, comprising:

if the number of Doppler units is within the range of the preset number of Doppler units, the reliability is increased by a third preset value; and/or the number of the groups of groups,

And subtracting a fourth preset value from the reliability if the number of Doppler units is not within the preset Doppler unit number range.

15. The method as recited in claim 1, further comprising:

Acquiring distance information;

Judging whether the distance information is smaller than a preset distance according to the distance information;

And if the distance information is smaller than the preset distance, controlling the movable platform to execute obstacle avoidance operation and/or controlling the alarm device to perform alarm processing.

16. The method according to claim 1, characterized in that

And acquiring detection information of the detection target through a radar.

17. The method of claim 16, wherein the radar is a millimeter wave radar.

18. The method according to claim 1, wherein the detection information of the detection target is acquired by acquiring an echo signal.

19. A method of target identification, comprising:

detecting the same detection target for multiple times;

Determining the current credibility of the detection target according to the current detection result of the detection target and the last credibility of the detection target, wherein the current detection result of the detection target comprises at least one of the following information: the Doppler energy of each Doppler unit around the detection target and the number of Doppler units with the Doppler energy greater than a preset Doppler energy threshold value;

And determining that the detection target is a specific target type according to the current credibility.

20. The method according to claim 19, wherein the detection result of the same detection target is obtained once every time the same detection target is detected.

21. The method of claim 19, wherein the step of determining the position of the probe comprises,

If the current detection result meets a second preset condition, the current reliability is increased by a first preset value for the last reliability; otherwise, the current credibility is obtained by subtracting a second preset value from the last credibility.

22. The method according to claim 21, wherein the detection result of the detection target includes detection information of the detection target, and information of doppler cells around the detection target;

the second preset condition includes: the detection information of the detection target at the current moment meets the preset detection information condition, and the information of Doppler units around the detection target meets the preset Doppler condition.

23. The method according to claim 19, comprising:

And determining the type of the detection target according to the detection times of the same detection target and the current credibility.

24. The method according to claim 23, wherein when the number of times the same detection target is detected is smaller than a first preset number of times of detection, comparing the current reliability of the detection target determined by detecting the same detection target each time with a first preset reliability;

If the current credibility of the detection target which is detected and determined for the same detection target each time is smaller than the first preset credibility, determining that the detection target is not the specific target type; and/or the number of the groups of groups,

And if the current credibility is larger than or equal to the first preset credibility, determining that the detection target is the specific target type.

25. The method of claim 23, wherein the first preset confidence level is updated to a fifth preset value when the number of times the same detection target is detected is less than a first preset number of detections, the current confidence level being greater than a first preset confidence level.

26. The method of claim 25, wherein when the number of times the same detection target is detected is less than the first preset number of detections, continuing to detect the detection target after the current confidence level is greater than the first preset confidence level, wherein determining a target type of the detection target is performed before continuing to detect a second preset number of detections;

If the current credibility of the detection target, which is detected and determined for the same detection target each time, is greater than or equal to a first preset credibility, determining that the detection target is of the specific target type; and/or the number of the groups of groups,

And if the current credibility of the detection targets detected and determined by detecting the same detection target is smaller than the first preset credibility, determining that the detection target is not the specific target type.

27. The method of claim 19, wherein upon determining that the detected target is a particular target type, controlling an alarm device to perform an alarm process.

28. The method as recited in claim 19, further comprising:

After the detection target is determined to be of a specific target type, the target type of the detection target is output in a mode of LED lamp display, voice broadcasting and vibration.

29. The method of claim 19, wherein the same detection target is detected multiple times by the radar.

30. The method of claim 19, wherein the method is applied to a radar, the radar being a millimeter wave radar.

31. The method of claim 19, wherein the current detection result of the detection target is obtained from an echo signal.

32. A target credibility determination system, comprising: one or more processors, working together or separately, for performing the method of any of claims 1 to 15.

33. The system according to claim 32, wherein the detection information of the detection target is acquired by radar.

34. The system of claim 32, wherein the radar is a millimeter wave radar.

35. The system of claim 32, wherein the detection information of the detection target is obtained by obtaining echo signals.

36. An object recognition system, comprising: one or more processors, working together or separately, for performing the method of any of claims 19 to 27.

37. The system of claim 36, wherein the same detection target is detected multiple times by the radar.

38. The system of claim 36, wherein the system comprises a radar, the radar being a millimeter wave radar.

39. The system of claim 36, wherein the detection information of the detection target is obtained by obtaining echo signals.

40. A radar, comprising:

The antenna is used for acquiring echo signals;

A processor in communication with the antenna for performing the method of any one of claims 1 to 15 and/or for performing the method of any one of claims 19 to 28.

41. The radar of claim 40, wherein the radar is a millimeter wave radar.

42. The radar of claim 40, wherein the detection information of the detection target is obtained by obtaining the echo signal.

43. A movable platform, comprising:

A body;

the power system is arranged on the machine body and is used for providing power;

and the radar of any one of claims 40 to 42.

44. The mobile platform of claim 43, wherein the mobile platform comprises at least one of: automobiles and unmanned aerial vehicles.

45. A computer readable storage medium, having stored thereon a computer program, the computer program being executable by a processor to implement the method of any one of claims 1-18.

46. A computer readable storage medium having stored thereon a computer program, the computer program being executed by a processor to implement the method of any of claims 19-31.