CN111190169A

CN111190169A - Radar data filtering method and device, electronic device and storage medium

Info

Publication number: CN111190169A
Application number: CN201911416525.2A
Authority: CN
Inventors: 高旭
Original assignee: Zhicheauto Technology Beijing Co ltd
Current assignee: Zhicheauto Technology Beijing Co ltd
Priority date: 2019-12-31
Filing date: 2019-12-31
Publication date: 2020-05-22
Anticipated expiration: 2039-12-31
Also published as: CN111190169B

Abstract

Embodiments of the present invention disclose a radar data filtering method and device, an electronic device and a storage medium, wherein the radar data filtering method includes: acquiring a radar data sequence arranged in time sequence, and correlating radar data in the radar data sequence where the radar data in the radar data sequence indicates the distance between the radar transceiver and the target object, and the target object is located within the radar detection envelope of the radar transceiver; if the radar data sequence belongs to the preset radar data interval The quantity of radar data is less than the preset quantity threshold, and the target radar data does not belong to the preset radar data interval, then based on the obtained moving distance, the radar data sequence is filtered to obtain a filtered data sequence, wherein the target radar data sequence is The data is the radar data whose generation time is closest to the current time in the radar data sequence. The embodiments of the present invention can improve the accuracy of filtering processing.

Description

Radar data filtering method and device, electronic device and storage medium

Technical Field

The invention relates to the technical field of computers, in particular to a radar data filtering method and device, an obstacle monitoring method and device, and a parking method and device.

Background

Due to the characteristics of slow energy consumption, long propagation distance in a medium, strong penetrability and the like of the ultrasonic waves, the ultrasonic distance measuring sensor has great advantages in short-distance measurement and is widely applied to the fields of automatic parking, obstacle identification and the like.

For example, in automatic parking, the parking space searching part is the key for the success of automatic parking. And the parking space searching adopts an ultrasonic radar to identify the target vehicle and judges whether the parking space exists. However, in the process of identifying the target vehicle and the obstacle, due to the problems of the characteristics of the ultrasonic radar, the irregular shape of the target vehicle and the like, the situations that the target (namely the target vehicle and the obstacle) is not identified accurately, the target is divided and the like often occur, and the parking space search fails.

In the existing parking space search, data obtained by threshold filtering and outputting of radar original data generally used for target vehicle detection is not processed aiming at a parking space search scene; the general improvement mode is to carry out filtering smoothing processing on radar data by filtering modes such as moving average filtering, Kalman filtering and the like.

Disclosure of Invention

The embodiment of the invention aims to solve the technical problem that: in the prior art, the accuracy of filtering radar data is low, so that the target (such as a vehicle, an obstacle and the like) is not accurately identified, the target is segmented, and the parking space search fails.

According to a first aspect of the embodiments of the present invention, there is provided a radar data filtering method, including: acquiring a radar data sequence arranged according to a time sequence and a moving distance associated with radar data in the radar data sequence, wherein the radar data in the radar data sequence indicates a distance between a radar transceiving end and a target object, the target object is located within a radar detection envelope range of the radar transceiving end, and the moving distance associated with the radar data in the radar data sequence indicates a moving distance of the radar transceiving end; and if the quantity of the radar data belonging to the preset radar data interval in the radar data sequence is smaller than a preset quantity threshold value, and the target radar data do not belong to the preset radar data interval, filtering the radar data sequence based on the acquired moving distance to obtain a filtered data sequence, wherein the target radar data are the radar data with the time closest to the current time generated in the radar data sequence.

Optionally, in the method according to any embodiment of the present invention, the filtering the radar data sequence based on the obtained moving distance to obtain a filtered data sequence includes: determining whether a target movement distance is less than or equal to a distance indicated by a radar detection envelope range, wherein the target movement distance is a movement distance associated with target valid radar data that precedes the target radar data and is the radar data that is closest to the target radar data among radar data belonging to a preset radar data interval in a radar data sequence; and if the moving distance of the target is less than or equal to the distance indicated by the radar detection envelope range of the radar transceiving end, updating the target radar data into target effective radar data to obtain an updated radar data sequence, and taking the updated radar data sequence as a filtered data sequence.

Optionally, in the method according to any embodiment of the present invention, the filtering processing is performed on the radar data sequence based on the obtained moving distance to obtain a filtered data sequence, and the method further includes: and if the target moving distance is greater than the distance indicated by the radar detection envelope range of the radar transceiving end, taking the radar data sequence as a filtered data sequence.

Optionally, in the method according to any embodiment of the present invention, the method further includes: if the radar data sequence meets a preset first condition, filtering the radar data sequence by adopting a predetermined filtering algorithm to obtain a filtered data sequence, wherein the preset first condition comprises the following steps: the number of radar data belonging to a preset radar data interval in the radar data sequence is greater than or equal to a preset number threshold, and the target radar data belongs to the preset radar data interval.

Optionally, in the method according to any embodiment of the present invention, the method further includes: if the radar data sequence meets a preset second condition, generating substitute data of the target radar data based on the previous radar data of the target radar data, wherein the preset second condition comprises: the number of radar data belonging to a preset radar data interval in the radar data sequence is greater than or equal to a preset number threshold, and the target radar data do not belong to the preset radar data interval; calculating a correction value of the substitute data to obtain first corrected data; and updating the target radar data into corrected data to obtain a filtered data sequence.

Optionally, in the method of any embodiment of the present invention, generating substitute data for the target radar data based on previous radar data of the target radar data includes: and generating substitute data of the target radar data based on the previous frame of radar data of the target radar data and the previous frame of radar data of the previous frame of radar data.

Optionally, in the method according to any embodiment of the present invention, the method further includes: if the radar data sequence meets a preset third condition, calculating a correction value of the target radar data to obtain second correction data, wherein the preset third condition comprises the following steps: the method comprises the steps that the number of radar data belonging to a preset radar data interval in a radar data sequence is smaller than a preset number threshold, target radar data belong to the preset radar data interval, and the target radar data are not acquired first frame radar data; and updating the target radar data into second correction data to obtain a filtered data sequence.

Optionally, in the method according to any embodiment of the present invention, the method further includes: if the radar data sequence meets the preset fourth condition, deleting target radar data from the radar data sequence, and taking the deleted radar data sequence as a filtered data sequence, wherein the preset fourth condition comprises: the number of the radar data belonging to the preset radar data interval in the radar data sequence is smaller than a preset number threshold, the target radar data belongs to the preset radar data interval, and the target radar data is the acquired first frame radar data.

Optionally, in the method of any embodiment of the present invention, an upper limit value of the number of radar data stored in the radar data sequence is predetermined; and, the radar data sequence is determined by: applying for a storage space for storing radar data sequences, wherein the storage space is used for storing radar data with the quantity being an upper limit value of the quantity; in response to receiving the radar data, performing the queue generating step of: if the quantity of the stored radar data in the radar data sequence is smaller than the upper limit value of the quantity, adding the acquired radar data into the radar data sequence; and if the quantity of the stored radar data in the radar data sequence is greater than or equal to the quantity upper limit value, performing dequeue operation on the radar data which is stored firstly in the radar data sequence, and adding the acquired radar data to the radar data sequence.

Optionally, in the method of any embodiment of the present invention, if radar data stored in the radar data sequence changes, a filtered data sequence corresponding to the changed radar data sequence is generated.

Optionally, in the method according to any embodiment of the present invention, the radar transceiver end is provided with a wheel, and the radar transceiver end moves through the wheel; and the distance of movement associated with the radar data in the sequence of radar data is the distance the wheel is rolling.

Optionally, in the method according to any embodiment of the present invention, acquiring a radar data sequence arranged in time sequence and a moving distance associated with radar data in the radar data sequence includes: determining a data sequence to be filtered based on echoes of transmitting waves transmitted by a radar transmitting and receiving end according to preset frequency, wherein the data to be filtered in the data sequence to be filtered comprises radar data and a moving distance associated with the radar data; and based on the obtained moving distance, filtering the radar data sequence to obtain a filtered data sequence, including: and based on the acquired moving distance, filtering the data sequence to be filtered to obtain a filtered data sequence.

According to a second aspect of the embodiments of the present invention, there is provided an obstacle detection method, including: and determining whether an object exists in the radar detection envelope range of the target radar transceiver end based on the filtered data sequence obtained by adopting the target filtering method, wherein the target filtering method is any one of the radar data filtering methods in the first aspect.

Optionally, in the method according to any embodiment of the present invention, the method further includes: if an object is present within the radar detection envelope, the class of the object is determined.

According to a third aspect of the embodiment of the present invention, there is provided a parking method characterized by comprising: determining whether a parking space exists in a radar detection envelope range of a target vehicle provided with a radar transceiving end based on a filtered data sequence obtained by adopting a target filtering method, wherein the target filtering method is any one of the radar data filtering methods in the first aspect; and if the parking space exists in the radar detection envelope range, controlling the target vehicle to drive into the parking space to park.

According to a fourth aspect of the embodiments of the present invention, there is provided a radar data filtering apparatus, including: an acquisition unit configured to acquire a radar data sequence arranged in time order and a moving distance associated with radar data in the radar data sequence, wherein the radar data in the radar data sequence indicates a distance between a radar transceiver terminal and a target object, the target object is located within a radar detection envelope of the radar transceiver terminal, and the moving distance associated with the radar data in the radar data sequence indicates a distance moved by the radar transceiver terminal; the first filtering unit is configured to filter the radar data sequence to obtain a filtered data sequence based on the acquired moving distance if the number of radar data in the radar data sequence, which belong to a preset radar data interval, is less than a preset number threshold value and target radar data does not belong to the preset radar data interval, wherein the target radar data is radar data in the radar data sequence, and the generated time of the target radar data is the closest to the current time.

Optionally, in the method of any embodiment of the present invention, the first filtering unit includes: a determination module configured to determine whether a target movement distance is less than or equal to a distance indicated by a radar detection envelope, wherein the target movement distance is a movement distance associated with target valid radar data that precedes the target radar data and is a radar data that is closest to the target radar data among radar data belonging to a preset radar data interval in a radar data sequence; and the updating module is configured to update the target radar data into target effective radar data if the target moving distance is less than or equal to the distance indicated by the radar detection envelope range of the radar transceiving end, obtain an updated radar data sequence, and take the updated radar data sequence as a filtered data sequence.

Optionally, in the method according to any of the embodiments of the present invention, the first filtering unit further includes: and the processing module is configured to take the radar data sequence as a filtered data sequence if the target moving distance is greater than the distance indicated by the radar detection envelope range of the radar transceiving end.

Optionally, in the method according to any embodiment of the present invention, the method further includes: the second filtering unit is configured to perform filtering processing on the radar data sequence by adopting a predetermined filtering algorithm if the radar data sequence meets a preset first condition, so as to obtain a filtered data sequence, wherein the preset first condition comprises: the number of radar data belonging to a preset radar data interval in the radar data sequence is greater than or equal to a preset number threshold, and the target radar data belongs to the preset radar data interval.

Optionally, in the method according to any embodiment of the present invention, the method further includes: a generating unit configured to generate substitute data for the target radar data based on previous radar data of the target radar data if the radar data sequence satisfies a preset second condition, wherein the preset second condition includes: the number of radar data belonging to a preset radar data interval in the radar data sequence is greater than or equal to a preset number threshold, and the target radar data do not belong to the preset radar data interval; a first calculation unit configured to calculate a correction value of the substitute data, resulting in first corrected data; and the first updating unit is configured to update the target radar data into modified data to obtain a filtered data sequence.

Optionally, in the method according to any embodiment of the present invention, the generating unit includes: a generation module configured to generate substitute data for the target radar data based on a previous frame of radar data of the target radar data and a previous frame of radar data of the previous frame of radar data.

Optionally, in the method according to any embodiment of the present invention, the method further includes: a second calculation unit configured to calculate a correction value of the target radar data if the radar data sequence satisfies a preset third condition, resulting in second correction data, wherein the preset third condition includes: the method comprises the steps that the number of radar data belonging to a preset radar data interval in a radar data sequence is smaller than a preset number threshold, target radar data belong to the preset radar data interval, and the target radar data are not acquired first frame radar data; and the second updating unit is configured to update the target radar data into second correction data to obtain a filtered data sequence.

Optionally, in the method according to any embodiment of the present invention, the method further includes: a deleting unit configured to delete the target radar data from the radar data sequence if the radar data sequence satisfies a preset fourth condition, taking the deleted radar data sequence as a filtered data sequence, wherein the preset fourth condition includes: the number of the radar data belonging to the preset radar data interval in the radar data sequence is smaller than a preset number threshold, the target radar data belongs to the preset radar data interval, and the target radar data is the acquired first frame radar data.

Optionally, in the method according to any embodiment of the present invention, the obtaining unit includes: the device comprises a determining module, a filtering module and a filtering module, wherein the determining module is configured to determine a data sequence to be filtered based on an echo of a transmitting wave transmitted by a radar transceiving end according to a preset frequency, and the data to be filtered in the data sequence to be filtered comprises radar data and a moving distance associated with the radar data; and, the first filtering unit includes: and the filtering module is configured to perform filtering processing on the data sequence to be filtered based on the acquired moving distance to obtain a filtered data sequence.

According to a fifth aspect of the embodiments of the present invention, there is provided an obstacle detection device, including: a first determining unit configured to determine whether an object exists within a radar detection envelope of a target radar transceiver based on the filtered data sequence obtained by using a target filtering method, wherein the target filtering method is any one of the radar data filtering methods described in the first aspect.

Optionally, in the method according to any embodiment of the present invention, the method further includes: a second determination unit configured to determine a category of the object if the object is present within the radar detection envelope.

According to a sixth aspect of the embodiment of the present invention, there is provided a parking apparatus comprising: a third determining unit, configured to determine whether a parking space exists within a radar detection envelope range of a target vehicle provided with a radar transceiver end based on a filtered data sequence obtained by using a target filtering method, where the target filtering method is any one of the radar data filtering methods in the first aspect; and the control unit is configured to control the target vehicle to drive into the parking space for parking if the parking space exists in the radar detection envelope range.

According to a seventh aspect of the embodiments of the present invention, there is provided an electronic apparatus, including: a memory for storing a computer program; a processor for executing a computer program stored in the memory, and when executed, implementing a method as in any one of the embodiments of the radar data filtering method of the first aspect described above, or implementing a method as in any one of the embodiments of the obstacle detection method of the second aspect described above, or implementing a method as in any one of the embodiments of the parking method of the third aspect described above.

According to an eighth aspect of embodiments of the present invention, there is provided a computer readable medium, which when executed by a processor implements the method according to any one of the embodiments of the radar data filtering method according to the first aspect described above, or implements the method according to any one of the embodiments of the obstacle detecting method according to the second aspect described above, or implements the method according to any one of the embodiments of the parking method according to the third aspect described above.

Based on the radar data filtering method and apparatus provided by the above embodiments of the present invention, a radar data sequence arranged according to a time sequence and a moving distance associated with radar data in the radar data sequence are obtained, wherein the radar data in the radar data sequence indicates a distance between a radar transceiver and a target object, the target object is located within a radar detection envelope of the radar transceiver, and the moving distance associated with the radar data in the radar data sequence indicates a distance moved by the radar transceiver, and then, if a number of radar data belonging to a preset radar data interval in the radar data sequence is smaller than a preset number threshold and the target radar data does not belong to the preset radar data interval, the radar data sequence is filtered based on the obtained moving distance to obtain a filtered data sequence, wherein, the target radar data is the radar data with the time closest to the current time generated in the radar data sequence, so that the accuracy of filtering the radar data is improved, and the filtering result (namely the filtered data sequence) obtained by adopting the radar data filtering method and the device provided by the embodiment of the invention is beneficial to improving the accuracy of target (such as vehicles, obstacles and the like) identification, and the probability of the conditions that the target is segmented, the parking space search fails and the like can be avoided to a certain extent.

Based on the obstacle detection method and apparatus provided in the above embodiments of the present invention, whether an object exists within a radar detection envelope range of a target radar transceiver is determined based on a filtered data sequence obtained by using a target filtering method, where the target filtering method is any one of the radar data filtering methods in the above first aspect, thereby improving the accuracy of obstacle detection.

Based on the parking method and the parking device provided by the embodiment of the invention, whether a parking space exists in the radar detection envelope range of the target vehicle provided with the radar transceiving end is determined based on the filtered data sequence obtained by adopting the target filtering method, wherein the target filtering method is any one of the radar data filtering methods in the first aspect, and if the parking space exists in the radar detection envelope range, the target vehicle is controlled to drive into the parking space for parking, so that the accuracy of parking space detection is improved, and the accuracy of automatic parking is improved.

The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description, serve to explain the principles of the invention.

The invention will be more clearly understood from the following detailed description, taken with reference to the accompanying drawings, in which:

FIG. 1 is a flow diagram of one embodiment of a radar data filtering method of the present invention;

FIGS. 2A and 2B are schematic diagrams for one application scenario of FIG. 1;

FIG. 3 is a flow chart of yet another embodiment of a radar data filtering method of the present invention;

FIG. 4A is an example for FIG. 3;

FIG. 4B is an image contrast diagram of a filtered data sequence obtained by separately filtering a radar data sequence using the example of FIG. 4A and prior art techniques;

FIG. 5 is a flow chart of one embodiment of an obstacle detection method of the present invention;

FIG. 6 is a flow chart of one embodiment of a parking method of the present invention;

FIG. 7 is a schematic structural diagram of one embodiment of a radar data filtering apparatus of the present invention;

fig. 8 is a schematic structural view of one embodiment of the obstacle detecting device of the present invention;

fig. 9 is a schematic structural view of an embodiment of the parking apparatus of the present invention.

Detailed Description

Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, the numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.

Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.

The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.

Embodiments of the invention are operational with numerous other general purpose or special purpose computing system environments or configurations. Examples of well known computing systems, environments, and/or configurations that may be suitable for use with electronic devices, such as computer systems/servers, include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, hand-held or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, networked personal computers, minicomputer systems, mainframe computer systems, distributed cloud computing environments that include any of the above, and the like.

The electronic device, such as a computer system/server, may be described in the general context of computer system-executable instructions, such as program modules, being executed by a computer system. Generally, program modules may include routines, programs, objects, components, logic, data structures, etc. that perform particular tasks or implement particular abstract data types. The computer system/server may be practiced in distributed cloud computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed cloud computing environment, program modules may be located in both local and remote computer system storage media including memory storage devices.

Referring to fig. 1, a flow 100 of one embodiment of a radar data filtering method according to the present disclosure is shown. The radar data filtering method comprises the following steps:

step 101, a radar data sequence arranged according to a time sequence and a moving distance associated with radar data in the radar data sequence are obtained.

In the present embodiment, an executing subject (e.g., a server, a vehicle, a mobile phone terminal, etc.) of the radar data filtering method may acquire a radar data sequence arranged in time series, and a moving distance associated with radar data in the radar data sequence. Wherein the radar data in the radar data sequence indicates a distance between the radar transceiver end and the target object. The target object is positioned in the radar detection envelope range of the radar transmitting and receiving end. The movement distance associated with radar data in the radar data sequence indicates the distance the radar transceiving end has moved.

Here, the radar transceiving terminal may be a device for transmitting and receiving radar data, such as an ultrasonic ranging sensor, a vehicle provided with an ultrasonic ranging sensor. The target object may be various objects such as a vehicle, a parking space, a pedestrian, a curb, and the like. The moving distance may be determined based on a GPS (Global Positioning System), and in addition, in a case where the radar transmitting and receiving terminal is provided with a wheel and the radar transmitting and receiving terminal moves by the wheel, the moving distance may be a distance in which the wheel rolls, and the distance may be obtained by a count sensor, as an example.

It will be appreciated that a more accurate distance of movement can be obtained by determining the distance of movement as the distance the wheel rolls, relative to other ways of calculating the distance of movement. The modulated sound waves are sent out by the radar transceiving end, and after the modulated sound waves are reflected by an object (namely a target object) in a radar detection envelope range of the radar transceiving end, the radar transceiving end can calculate more accurate moving distance according to the speed of the sound waves and the time spent on transmitting and receiving the sound waves, and can improve the speed of calculating the moving distance.

And 102, if the quantity of the radar data belonging to the preset radar data interval in the radar data sequence is smaller than a preset quantity threshold value and the target radar data does not belong to the preset radar data interval, filtering the radar data sequence based on the acquired moving distance to obtain a filtered data sequence.

In this embodiment, if the number of radar data belonging to a preset radar data interval in the radar data sequence is smaller than a preset number threshold, and the target radar data does not belong to the preset radar data interval, the execution main body may perform filtering processing on the radar data sequence based on the acquired moving distance, so as to obtain a filtered data sequence. And the target radar data is the radar data with the time closest to the current time generated in the radar data sequence. The current time may be the time the execution agent performed the step 102.

Here, the preset radar data section may be various preset radar data sections. As an example, the preset radar data interval may be determined according to the ranging accuracy of the radar transceiver. For example, if the range accuracy of the radar transceiver end is 0.5 m to 1 m (it is characterized that the accuracy of the obtained range is high when the radar transceiver end is in a range from an obstacle to the obstacle, and is less than or equal to 0.5 m and less than or equal to 1 m, and the accuracy of the obtained range is low when the radar transceiver end is in a range from the obstacle to the obstacle, and is less than 0.5 m and more than 1 m), the preset radar data interval may be greater than or equal to 0.5 m and less than or equal to 1 m.

In some optional implementations of this embodiment, the executing main body may execute the step 102 by:

step one, whether the moving distance of the target is smaller than or equal to the distance indicated by the radar detection envelope range is determined. Wherein the target movement distance is a movement distance associated with the target valid radar data. The target valid radar data is ahead of the target radar data, and is the radar data which is closest to the target radar data in generation time in the radar data belonging to the preset radar data interval in the radar data sequence.

And step two, if the moving distance of the target is less than or equal to the distance indicated by the radar detection envelope range of the radar transceiving end, updating the target radar data into target effective radar data to obtain an updated radar data sequence, and taking the updated radar data sequence as a filtered data sequence.

It can be understood that, in the case that the target moving distance is less than or equal to the distance indicated by the radar detection envelope range of the radar transceiving end (that is, the distance moved by the radar transceiving end is small), the optional implementation mode performs filtering by updating the target radar data to the target effective radar data, thereby avoiding the sudden change of the radar data to a certain extent and further improving the accuracy of filtering processing.

In some optional implementations of this embodiment, after determining whether the target moving distance is less than or equal to the distance indicated by the radar detection envelope, if the target moving distance is greater than the distance indicated by the radar detection envelope of the radar transceiving end, the executing entity may directly use the radar data sequence as the filtered data sequence.

It can be understood that, in the case that the target moving distance is greater than the distance indicated by the radar detection envelope range of the radar transceiving end (that is, the distance moved by the radar transceiving end is large), and the accuracy of the radar data (that is, the target effective radar data) associated with the target moving distance is high (belonging to the preset radar data interval), the optional implementation manner directly takes the radar data sequence as the filtered data sequence, which can improve the speed of obtaining the filtered data sequence and ensure the accuracy of filtering.

Optionally, the executing main body may further execute the step 202 by using the following steps:

if the obtained moving distance is larger than or equal to a preset value, filtering the radar data sequence by adopting a first filtering algorithm (such as a moving average filtering algorithm) to obtain a filtered data sequence; if the obtained moving distance is smaller than the preset value, filtering the radar data sequence by adopting a second filtering algorithm (such as a Kalman filtering algorithm) to obtain a filtered data sequence

With continuing reference to fig. 2A and 2B, fig. 2A and 2B are schematic diagrams for one application scenario of fig. 1. In fig. 2A, a vehicle 201 enters a parking lot and performs automatic parking. Therein, the radar detection envelope 202 is formed via an ultrasonic radar transmitted by a radar transmitting and receiving end provided to the vehicle 201. As shown in fig. 2B, the vehicle 201 first acquires a radar data sequence 203 arranged in time series, and a moving distance 204 associated with radar data in the radar data sequence. Wherein the radar data in the radar data sequence 203 indicates a distance between the radar transceiving end and the target object. The target object is located within a radar detection envelope of the radar transceiving end (e.g., radar detection envelope 202 shown in fig. 2A). The movement distance 204 associated with the radar data in the radar data sequence 203 indicates the distance the radar transceiving end has moved. If the number of radar data belonging to the preset radar data interval in the radar data sequence 203 is smaller than the preset number threshold value, and the target radar data does not belong to the preset radar data interval, then the vehicle 201 may perform filtering processing on the radar data sequence 203 based on the acquired moving distance 204, to obtain a filtered data sequence 205. The target radar data is the radar data generated in the radar data sequence 203 and having the time closest to the current time.

The radar data filtering method provided by the above embodiment of the present invention obtains a filtered data sequence by obtaining a radar data sequence arranged according to a time sequence, and a moving distance associated with radar data in the radar data sequence, wherein the radar data in the radar data sequence indicates a distance between a radar transceiver and a target object, the target object is located within a radar detection envelope of the radar transceiver, and the moving distance associated with the radar data in the radar data sequence indicates a distance that the radar transceiver moves, and then, if a number of radar data belonging to a preset radar data interval in the radar data sequence is smaller than a preset number threshold and the target radar data does not belong to the preset radar data interval, filtering the radar data sequence based on the obtained moving distance to obtain the filtered data sequence, wherein the target radar data is radar data that has a closest time to a current time generated in the radar data sequence, the accuracy of the radar data filtering processing is improved, and the filtering result (namely the filtered data sequence) obtained by the radar data filtering method and the device provided by the embodiment of the invention is beneficial to improving the accuracy of target (such as vehicles, obstacles and the like) identification, and the probability of the conditions that the target is segmented, the parking space search fails and the like can be avoided to a certain extent.

In some optional implementations of this embodiment, if the radar data sequence satisfies the preset first condition, the executing body may further perform the following steps:

and filtering the radar data sequence by adopting a predetermined filtering algorithm to obtain a filtered data sequence. Wherein, presetting a first condition comprises: the number of radar data belonging to a preset radar data interval in the radar data sequence is greater than or equal to a preset number threshold, and the target radar data belongs to the preset radar data interval.

The predetermined filtering algorithm may be various filtering algorithms. As an example, the predetermined filtering algorithm may be a sliding window filtering algorithm.

It can be understood that, when the first condition is satisfied, the radar data with higher accuracy (belonging to the preset radar data interval) in the radar data sequence is more (the number is greater than or equal to the preset number threshold), and the target radar data belongs to the preset radar data interval, and the radar data sequence may be filtered by using a predetermined filtering algorithm. Practice proves that the accuracy of filtering can be further improved under the condition that the predetermined filtering algorithm is a sliding window filtering algorithm.

In some optional implementations of this embodiment, if the radar data sequence satisfies the preset second condition, the executing body may further perform the following steps:

in a first step, substitute data for the target radar data is generated based on previous radar data for the target radar data. Wherein, presetting the second condition comprises: the number of radar data belonging to a preset radar data interval in the radar data sequence is greater than or equal to a preset number threshold, and the target radar data does not belong to the preset radar data interval.

Here, the substitute data for the target radar data may be generated by:

and generating substitute data of the target radar data based on the previous frame of radar data of the target radar data and the previous frame of radar data of the previous frame of radar data.

For example, the substitute data for the target radar data may be: the square of the previous frame of radar data of the target radar data divided by the previous frame of radar data of the previous frame of radar data.

As another example, the substitute data for the target radar data may be: an arithmetic square root of a previous frame of radar data of the target radar data and a previous frame of radar data of the previous frame of radar data.

It can be understood that, here, the substitute data of the target radar data can be generated based on the previous frame radar data of the target radar data and the previous frame radar data of the previous frame radar data, so that the target radar data can be predicted with reference to the variation trend of the radar data, the substitute data of the target radar data is obtained, and then the accuracy of subsequent filtering processing can be improved.

Optionally, the substitute data of the target radar data may also be generated by the following steps:

and generating substitute data of the target radar data based on the radar data of which the previous frame belongs to the preset radar data interval and the radar data of which the next previous frame belongs to the preset radar data interval.

Here, the above-mentioned example may be referred to calculate the square sum quotient, or the above-mentioned manner of calculating the arithmetic square root to generate the substitute data of the target radar data, and details thereof are not repeated.

And secondly, calculating a correction value of the substitute data to obtain first corrected data. Here, the correction value of the above-described substitute data obtained by a filter algorithm (e.g., a sliding window filter algorithm) may be used.

And thirdly, updating the target radar data into corrected data to obtain a filtered data sequence.

It can be understood that, in the alternative implementation manner, the target radar data can be adjusted by calculating the substitute data of the target radar data and the correction value of the substitute data, so that the filtered data sequence can be more accurate.

In some optional implementations of this embodiment, if the radar data sequence satisfies the preset third condition, the executing body may further perform the following steps:

firstly, calculating a correction value of target radar data to obtain second correction data. Wherein, presetting a third condition comprises: the number of the radar data belonging to the preset radar data interval in the radar data sequence is smaller than a preset number threshold, the target radar data belongs to the preset radar data interval, and the target radar data is not the acquired first frame radar data.

Here, the correction value of the above target radar data obtained by a filter algorithm (e.g., a sliding window filter algorithm) may be used.

And secondly, updating the target radar data into second correction data to obtain a filtered data sequence.

It can be understood that, in the case that the third condition is satisfied, the radar data with higher accuracy (belonging to the preset radar data interval) in the radar data sequence is less (the number is smaller than the preset number threshold), the target radar data belongs to the preset radar data interval, and the target radar data is not acquired from the first frame of radar data, so that the target radar data can be corrected, and the filtered data sequence can be more accurate.

In some optional implementations of the present embodiment, if the radar data sequence satisfies a preset fourth condition, the executing main body may further perform the following steps:

and deleting the target radar data from the radar data sequence, and taking the deleted radar data sequence as a filtered data sequence. Wherein, predetermine the fourth condition and include: the number of the radar data belonging to the preset radar data interval in the radar data sequence is smaller than a preset number threshold, the target radar data belongs to the preset radar data interval, and the target radar data is the acquired first frame radar data.

It can be understood that, under the condition that the optional implementation manner satisfies the fourth condition, the target radar data can be directly deleted from the radar data sequence, so that burrs appearing in the filtered data sequence can be effectively removed, and the accuracy of feature extraction is not required, so that the filtered data sequence is more accurate.

In some optional implementations of the embodiment, the upper limit value of the amount of radar data stored in the radar data sequence is predetermined. And, the radar data sequence is determined by:

in a first step, a memory space for storing a radar data sequence is applied. The storage space is used for storing the radar data with the quantity being the upper limit value of the quantity.

A second step of, in the case of receiving radar data, performing the following queue generating step (including the first and second substeps):

a first substep of adding the acquired radar data to the radar data sequence if the amount of radar data already stored in the radar data sequence is less than an upper limit value of the amount.

And a second sub-step of performing dequeue operation on the radar data stored first in the radar data sequence if the number of radar data already stored in the radar data sequence is greater than or equal to the number upper limit value, and adding the acquired radar data to the radar data sequence.

It can be understood that, in this optional implementation manner, filtering of the acquired radar data of each frame may be implemented based on filtering of the radar data sequence, and accuracy of filtering may be improved compared to directly filtering the acquired radar data of each frame in the prior art.

In some optional implementations of this embodiment, if the radar data stored in the radar data sequence changes, a filtered data sequence corresponding to the changed radar data sequence is generated.

It can be understood that, in the alternative implementation manner, filtering processing may be performed once under the condition that radar data is received each time, so that the real-time performance of the filtering processing is improved.

In some optional implementations of this embodiment, the executing main body may execute the step 101 by:

and determining a data sequence to be filtered based on the echo of the transmitted wave transmitted by the radar transmitting and receiving end according to the preset frequency. The data to be filtered in the data sequence to be filtered comprises radar data and a moving distance associated with the radar data.

Here, the radar transmitting and receiving terminal may transmit a transmission wave (e.g., ultrasonic wave) at a predetermined frequency (e.g., 25 hz), and after the transmission wave encounters an obstacle, the obstacle reflects the transmission wave to generate a reflected wave, and then the radar transmitting and receiving terminal may receive the reflected wave. Since the radar transmitting/receiving ends transmit the transmission waves in order, there is also an order of the received reflection waves, and thus respective radar data arranged in time series can be obtained. Further, the above-described executing body may also transmit a transmission wave at the radar transceiving end, or determine a moving distance when the radar transceiving end receives a reflection wave, and take the determined moving distance as the moving distance associated with the radar data. A time-sequentially arranged data sequence to be filtered can thereby be obtained.

Based on this, the execution main body may execute the step 102 by:

and based on the acquired moving distance, filtering the data sequence to be filtered to obtain a filtered data sequence.

Here, the specific execution step of the filtering process in this optional implementation may refer to the above description (for example, the radar data sequence to be filtered described above is replaced with the data sequence to be filtered in this optional implementation, that is, the specific execution step of the filtering process may be obtained), and is not described herein again.

It can be understood that, in the optional implementation manner, the data sequence to be filtered may be filtered through the radar data included in the data sequence to be filtered and the moving distance associated with the radar data, so that filtering may be implemented by integrating two aspects of the radar data and the moving distance, and thus, the accuracy of filtering is further improved.

With further reference to fig. 3, fig. 3 is a flow chart of yet another embodiment of the radar data filtering method of the present invention. The process 300 of the radar data filtering method includes the following steps:

step 301, a radar data sequence arranged in time sequence and a moving distance associated with radar data in the radar data sequence are obtained.

In this embodiment, step 301 is substantially the same as step 101 in the embodiment corresponding to fig. 1, and is not described here again.

Step 302, if the number of radar data belonging to a preset radar data interval in the radar data sequence is smaller than a preset number threshold, and the target radar data does not belong to the preset radar data interval, determining whether the target moving distance is smaller than or equal to the distance indicated by the radar detection envelope range.

In this embodiment, if the number of radar data belonging to a preset radar data interval in the radar data sequence is less than a preset number threshold, and the target radar data does not belong to the preset radar data interval, then the executing entity of the radar data filtering method (e.g., a server, a vehicle, a mobile phone terminal, etc.) may determine whether the target moving distance is less than or equal to the distance indicated by the radar detection envelope range. And the target radar data is the radar data with the time closest to the current time generated in the radar data sequence. The target movement distance is a movement distance associated with target valid radar data. The target effective radar data is ahead of the target radar data, and is the radar data which is closest to the target radar data in the radar data which belong to the preset radar data interval in the radar data sequence.

Step 303, if the target moving distance is less than or equal to the distance indicated by the radar detection envelope range of the radar transceiving end, updating the target radar data into target valid radar data to obtain an updated radar data sequence, and using the updated radar data sequence as a filtered data sequence.

In this embodiment, if the target moving distance is less than or equal to the distance indicated by the radar detection envelope range of the radar transceiver, the executing entity may update the target radar data to the target valid radar data, obtain an updated radar data sequence, and use the updated radar data sequence as the filtered data sequence.

And step 304, if the target moving distance is greater than the distance indicated by the radar detection envelope range of the radar transceiving end, taking the radar data sequence as a filtered data sequence.

In this embodiment, if the target moving distance is greater than the distance indicated by the radar detection envelope range of the radar transceiving end, the execution body may treat the radar data sequence as a filtered data sequence.

By way of example, referring to fig. 4A, fig. 4A is one example for fig. 3. As shown in fig. 4A, one example of the radar data filtering method may include the steps of:

step 401, a storage space for storing a radar data sequence is applied. Thereafter, step 402 is performed.

In the present embodiment, an executing body (e.g., a server, a vehicle, a mobile phone terminal, etc.) of the radar data filtering method may apply for a storage space for storing a radar data sequence. The storage space is used for storing the radar data with the quantity being the upper limit value of the quantity. An upper limit value of the amount of radar data stored in the radar data sequence is predetermined.

Step 402, determining whether the quantity of stored radar data in the radar data sequence is less than a quantity upper limit value. If yes, go to step 403; if not, go to step 404.

In this embodiment, the execution subject may determine whether the number of radar data stored in the radar data sequence is smaller than a number upper limit value.

Step 403, adding the acquired radar data to the radar data sequence. Thereafter, step 405 is performed.

In this embodiment, in the case where the number of radar data already stored in the radar data sequence is smaller than the number upper limit value, the execution subject described above may add the acquired radar data to the radar data sequence.

In step 404, a dequeue operation is performed on the radar data that was first stored in the radar data sequence, and the acquired radar data is added to the radar data sequence. Thereafter, step 405 is performed.

In this embodiment, in the case where the number of pieces of radar data that have been stored in the radar data sequence is greater than or equal to the number upper limit value, the execution subject described above may perform dequeue operation on the radar data that is stored first in the radar data sequence, and add the acquired radar data to the radar data sequence.

Step 405, determining whether the number of radar data belonging to a preset radar data interval in the radar data sequence is greater than or equal to a preset number threshold. If yes, go to step 406; if not, go to step 407.

In this embodiment, the execution subject may determine whether the number of radar data belonging to a preset radar data interval in the radar data sequence is greater than or equal to a preset number threshold.

Step 406, determining whether the target radar data belongs to a preset radar data interval. If yes, go to step 408; if not, go to step 409.

In this embodiment, in a case that the number of radar data belonging to the preset radar data interval in the radar data sequence is greater than or equal to the preset number threshold, the execution main body may determine whether the target radar data belongs to the preset radar data interval.

Step 407, determining whether the target radar data belongs to a preset radar data interval. Then, if yes, go to step 412; if not, go to step 414.

In this embodiment, in a case where it is determined that the number of radar data belonging to the preset radar data interval in the radar data sequence is smaller than the preset number threshold, the execution main body may determine whether the target radar data belongs to the preset radar data interval.

And step 408, filtering the radar data sequence by adopting a predetermined filtering algorithm. Thereafter, step 410 is performed.

In this embodiment, in a case that the target radar data belongs to a preset radar data interval, the executing body may perform filtering processing on the radar data sequence by using a predetermined filtering algorithm.

Step 409, generating substitute data for the target radar data based on the previous radar data for the target radar data. Thereafter, step 410 is performed.

In this embodiment, in a case where the target radar data does not belong to the preset radar data interval, the execution subject may generate substitute data for the target radar data.

And step 410, calculating a correction value to obtain first corrected data. Thereafter, step 411 is performed.

In this embodiment, the execution body may calculate the correction value to obtain the first corrected data.

And step 411, updating the target radar data into corrected data to obtain a filtered data sequence.

In this embodiment, the executing entity may update the target radar data into modified data, so as to obtain a filtered data sequence.

At step 412, it is determined whether the target radar data is the first frame of radar data acquired. If yes, go to step 413; if not, go to step 410.

In this embodiment, in a case where the target radar data belongs to a preset radar data interval, the execution main body may determine whether the target radar data is the acquired first frame radar data.

And 413, deleting the target radar data from the radar data sequence, and taking the deleted radar data sequence as a filtered data sequence.

In this embodiment, in the case where the target radar data is the acquired first frame radar data, the execution subject may delete the target radar data from the radar data sequence, and use the deleted radar data sequence as the filtered data sequence.

At step 414, it is determined whether the target movement distance is less than or equal to the distance indicated by the radar probe packet range. If yes, go to step 415; if not, go to step 416.

In this embodiment, in the case where the target radar data does not belong to the preset radar data interval, the execution main body may determine whether the target moving distance is less than or equal to the distance indicated by the radar detection packet range.

Step 415, updating the target radar data into target effective radar data to obtain an updated radar data sequence, and using the updated radar data sequence as a filtered data sequence.

In this embodiment, when the target moving distance is less than or equal to the distance indicated by the radar detection packet range, the execution main body may update the target radar data to the target valid radar data, obtain an updated radar data sequence, and use the updated radar data sequence as the filtered data sequence.

Step 416, the radar data sequence is used as a filtered data sequence.

In this embodiment, in the case where the target moving distance is greater than the distance indicated by the radar detection packet range, the execution subject may regard the radar data sequence as the filtered data sequence.

Referring now to fig. 4B, fig. 4B is a graph of image contrast of a filtered data sequence obtained by filtering a radar data sequence using the example of fig. 4A and the prior art. The comparison map can be obtained by the vehicle in the automatic vehicle-waving process by adopting the technical scheme described in the above fig. 4A to search the parking space.

In fig. 4B, three images of upper, middle, and lower are included. The image positioned in the middle is an image of the radar data sequence which is not subjected to filtering processing; the top image is an image of the filtered data sequence obtained by filtering the radar data sequence using the example of fig. 4A; the lower image is an image of the filtered data sequence obtained by filtering the radar data sequence in the prior art. The abscissa of the image is time, and the ordinate is distance (representing the distance between the radar transceiver and the target object). As can be seen from fig. 4B, due to the existence of the structures such as the air intake grid of the vehicle, a large amount of burrs exist in the image of the radar data sequence that is not subjected to the filtering processing and the image of the filtered data sequence that is obtained by performing the filtering processing according to the prior art, and the whole obstacle is divided into a plurality of small obstacles, whereas the burr can be effectively removed in the example of fig. 4A, so that the situation that one obstacle is divided into a plurality of small obstacles is avoided to some extent.

In some use cases, in order to further increase the speed of the filtering process, in the case where each data to be filtered in the data sequence to be filtered includes radar data and a moving distance associated with the radar data, the data sequence to be filtered may be divided into 2 parts. One part (for example, two thirds of the number of the data to be filtered included in the data sequence to be filtered) is used for judging whether the number of the radar data included in the data sequence to be filtered, which belong to a preset radar data interval, is less than a preset number threshold value, and whether the target radar data belongs to the preset radar data interval; the other part (for example, one third of the amount of the data to be filtered included in the data sequence to be filtered) is used for judging whether the moving distance included in the data sequence to be filtered is less than or equal to the distance indicated by the radar detection envelope range.

It should be noted that, besides the above-mentioned contents, the embodiment of the present application may further include the same or similar features and effects as the embodiment corresponding to fig. 1, and details are not repeated herein.

As can be seen from fig. 3, in the process 300 of the radar data filtering method in this embodiment, the radar data sequence is filtered by determining the size relationship between the target moving distance and the distance indicated by the radar detection envelope range of the radar transceiver, so as to obtain a filtered data sequence, thereby further improving the accuracy of filtering.

Referring to fig. 5, fig. 5 is a flowchart illustrating an obstacle detection method according to an embodiment of the invention. The obstacle detection method comprises the following steps:

step 501, determining whether an object exists in a radar detection envelope range of a target radar transceiver based on a filtered data sequence obtained by a target filtering method.

In this embodiment, an executing entity (e.g., a server, a vehicle, a mobile phone terminal, etc.) of the obstacle detection method may determine whether an object exists within a radar detection envelope of a target radar transceiver based on the filtered data sequence obtained by the target filtering method. Wherein the target filtering method is any one of the radar data filtering methods as described in the first aspect above.

Here, the execution body may render the filtered data sequence in time order. For example, an image with time as the abscissa and a moving distance as the ordinate can be obtained. So as to determine whether an object exists in the radar detection envelope range of the target radar transceiving end according to the shape of the image.

In the obstacle detection method provided in the above embodiment of the present invention, based on the filtered data sequence obtained by using the target filtering method, it is determined whether an object exists within a radar detection envelope range of a target radar transceiver, where the target filtering method is any one of the radar data filtering methods in the above first aspect, so that accuracy of obstacle detection is improved.

In some alternative implementations in this implementation, if an object is present within the radar detection envelope, the performing agent may determine the class of the object.

Here, the execution body may render the filtered data sequence in time order. For example, an image with time as the abscissa and a moving distance as the ordinate can be obtained. Thereby determining the class of the object based on the shape of the image.

It will be appreciated that the present alternative implementation may more accurately determine the class of objects.

Continuing now with reference to fig. 6, fig. 6 is a flow chart of one embodiment of a parking method of the present invention. The parking method comprises the following steps:

step 601, determining whether a parking space exists in a radar detection envelope range of a target vehicle provided with a radar transceiving end based on a filtered data sequence obtained by adopting a target filtering method.

In this embodiment, an executing entity (e.g., a server, a vehicle, a mobile phone terminal, etc.) of the parking method may determine whether a parking space exists within a radar detection envelope of a target vehicle provided with a radar transceiver based on a filtered data sequence obtained by using a target filtering method. Wherein the target filtering method is any one of the radar data filtering methods as described in the first aspect above.

Here, the execution body may render the filtered data sequence in time order. For example, an image with time as the abscissa and a moving distance as the ordinate can be obtained. Therefore, whether a parking space exists in the radar detection envelope range of the target vehicle provided with the radar transceiving end is determined according to the shape of the image.

Step 602, if a parking space exists in the radar detection envelope range, controlling the target vehicle to drive into the parking space for parking.

In this embodiment, if there is a parking space within the radar detection envelope, the execution subject may control the target vehicle to enter the parking space for parking.

In the obstacle detection method provided by the above embodiment of the present invention, based on the filtered data sequence obtained by using the target filtering method, it is determined whether there is a parking space within a radar detection envelope of a target vehicle provided with a radar transceiver, where the target filtering method is any one of the radar data filtering methods in the above first aspect, and if there is a parking space within the radar detection envelope, the target vehicle is controlled to drive into the parking space for parking, so that accuracy of parking space detection is improved, and accuracy of automatic parking is improved.

With further reference to fig. 7, as an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a radar data filtering apparatus, which corresponds to the embodiment of the method shown in fig. 1, and which may include the same or corresponding features as the embodiment of the method shown in fig. 1, and produce the same or corresponding effects as the embodiment of the method shown in fig. 1, in addition to the features described below. The device can be applied to various electronic equipment.

As shown in fig. 7, the radar data filtering apparatus 700 of the present embodiment includes: an acquisition unit 701 and a first filtering unit 702. The obtaining unit 701 is configured to obtain a radar data sequence arranged in time order and a moving distance associated with radar data in the radar data sequence, wherein the radar data in the radar data sequence indicates a distance between a radar transceiver and a target object, the target object is located within a radar detection envelope of the radar transceiver, and the moving distance associated with the radar data in the radar data sequence indicates a distance moved by the radar transceiver; the first filtering unit 702 is configured to, if the number of radar data in the radar data sequence that belong to a preset radar data interval is smaller than a preset number threshold, and the target radar data do not belong to the preset radar data interval, perform filtering processing on the radar data sequence based on the acquired moving distance, to obtain a filtered data sequence, where the target radar data are radar data whose generation time is closest to the current time in the radar data sequence.

In this embodiment, the acquisition unit 701 of the radar data filtering apparatus 700 may acquire a radar data sequence arranged in time series and a moving distance associated with radar data in the radar data sequence. Wherein the radar data in the radar data sequence indicates a distance between the radar transceiver end and the target object. The target object is positioned in the radar detection envelope range of the radar transmitting and receiving end. The movement distance associated with radar data in the radar data sequence indicates the distance the radar transceiving end has moved.

In this embodiment, if the number of radar data belonging to a preset radar data interval in the radar data sequence is smaller than a preset number threshold, and the target radar data does not belong to the preset radar data interval, the first filtering unit 702 may perform filtering processing on the radar data sequence based on the obtained moving distance, so as to obtain a filtered data sequence. And the target radar data is the radar data with the time closest to the current time generated in the radar data sequence.

In some optional implementations of the present embodiment, the first filtering unit 702 includes: a determining module (not shown in the figures) is configured to determine whether a target movement distance is less than or equal to a distance indicated by the radar detection envelope, wherein the target movement distance is a movement distance associated with target valid radar data that precedes the target radar data and is a radar data that is closest to the target radar data among radar data belonging to a preset radar data interval in the radar data sequence; an update module (not shown) is configured to update the target radar data to target valid radar data if the target movement distance is less than or equal to a distance indicated by a radar detection envelope of the radar transceiving end, resulting in an updated radar data sequence, and to take the updated radar data sequence as the filtered data sequence.

In some optional implementations of this embodiment, the first filtering unit 702 further includes: the processing module (not shown in the figure) is configured to treat the radar data sequence as a filtered data sequence if the target moving distance is greater than the distance indicated by the radar detection envelope range of the radar transceiving end.

In some optional implementations of this embodiment, the apparatus 700 further includes: the second filtering unit (not shown in the figure) is configured to, if the radar data sequence satisfies a preset first condition, perform filtering processing on the radar data sequence by using a predetermined filtering algorithm to obtain a filtered data sequence, where the preset first condition includes: the number of radar data belonging to a preset radar data interval in the radar data sequence is greater than or equal to a preset number threshold, and the target radar data belongs to the preset radar data interval.

In some optional implementations of this embodiment, the apparatus 700 further includes: the generation unit (not shown in the figures) is configured to generate substitute data for the target radar data based on preceding radar data of the target radar data if the radar data sequence fulfils a preset second condition, wherein the preset second condition comprises: the number of radar data belonging to a preset radar data interval in the radar data sequence is greater than or equal to a preset number threshold, and the target radar data do not belong to the preset radar data interval; a first calculation unit configured to calculate a correction value of the substitute data, resulting in first corrected data; and the first updating unit is configured to update the target radar data into modified data to obtain a filtered data sequence.

In some optional implementation manners of this embodiment, the generating unit includes: a generation module (not shown) is configured to generate substitute data for the target radar data based on a previous frame of radar data of the target radar data and a previous frame of radar data of the previous frame of radar data.

In some optional implementations of this embodiment, the apparatus 700 further includes: the second calculation unit (not shown in the figures) is configured to calculate a correction value of the target radar data, resulting in second correction data, if the radar data sequence satisfies a preset third condition, wherein the preset third condition includes: the method comprises the steps that the number of radar data belonging to a preset radar data interval in a radar data sequence is smaller than a preset number threshold, target radar data belong to the preset radar data interval, and the target radar data are not acquired first frame radar data; and the second updating unit is configured to update the target radar data into second correction data to obtain a filtered data sequence.

In some optional implementations of this embodiment, the apparatus 700 further includes: the deleting unit (not shown in the figure) is configured to delete the target radar data from the radar data sequence if the radar data sequence satisfies a preset fourth condition, and take the deleted radar data sequence as a filtered data sequence, wherein the preset fourth condition includes: the number of the radar data belonging to the preset radar data interval in the radar data sequence is smaller than a preset number threshold, the target radar data belongs to the preset radar data interval, and the target radar data is the acquired first frame radar data.

In some optional implementations of this embodiment, an upper limit value of the number of radar data stored in the radar data sequence is predetermined; and, the radar data sequence is determined by: applying for a storage space for storing radar data sequences, wherein the storage space is used for storing radar data with the quantity being an upper limit value of the quantity; in response to receiving the radar data, performing the queue generating step of: if the quantity of the stored radar data in the radar data sequence is smaller than the upper limit value of the quantity, adding the acquired radar data into the radar data sequence; and if the quantity of the stored radar data in the radar data sequence is greater than or equal to the quantity upper limit value, performing dequeue operation on the radar data which is stored firstly in the radar data sequence, and adding the acquired radar data to the radar data sequence.

In some optional implementation manners of this embodiment, the radar transceiving end is provided with a wheel, and the radar transceiving end moves through the wheel; and the distance of movement associated with the radar data in the sequence of radar data is the distance the wheel is rolling.

In some optional implementations of this embodiment, the obtaining unit 701 includes: the determining module (not shown in the figure) is configured to determine a data sequence to be filtered based on an echo of a transmitted wave transmitted by a radar transceiving end according to a preset frequency, wherein the data to be filtered in the data sequence to be filtered comprises radar data and a moving distance associated with the radar data; and, the first filtering unit 702 includes: the filtering module (not shown in the figure) is configured to perform filtering processing on the data sequence to be filtered based on the obtained moving distance, so as to obtain a filtered data sequence.

The apparatus provided in the above-mentioned embodiment of the present disclosure acquires, by the acquisition unit 701, a radar data sequence arranged in time sequence, and a moving distance associated with radar data in the radar data sequence, where the radar data in the radar data sequence indicates a distance between a radar transceiver and a target object, the target object is located within a radar detection envelope of the radar transceiver, and the moving distance associated with the radar data in the radar data sequence indicates a distance that the radar transceiver moves, then, if the number of radar data in the radar data sequence that belong to a preset radar data interval is less than a preset number threshold, and the target radar data does not belong to the preset radar data interval, the first filtering unit 702 performs filtering processing on the radar data sequence based on the acquired moving distance to obtain a filtered data sequence, where, the target radar data is the radar data with the time closest to the current time generated in the radar data sequence, so that the accuracy of filtering the radar data is improved, and the filtering result (namely the filtered data sequence) obtained by adopting the radar data filtering method and the device provided by the embodiment of the invention is beneficial to improving the accuracy of target (such as vehicles, obstacles and the like) identification, and the probability of the conditions that the target is segmented, the parking space search fails and the like can be avoided to a certain extent.

Referring now to fig. 8, as an implementation of the method shown in the above figures, the present disclosure provides an embodiment of an obstacle detection apparatus, which corresponds to the embodiment of the method shown in fig. 5, and which may include the same or corresponding features as the embodiment of the method shown in fig. 5 and produce the same or corresponding effects as the embodiment of the method shown in fig. 5, in addition to the features described below. The device can be applied to various electronic equipment.

As shown in fig. 8, the obstacle detection device 800 of the present embodiment includes: the first determination unit 801 is configured to determine whether an object exists within a radar detection envelope of a target radar transceiver based on a filtered data sequence obtained by using a target filtering method, wherein the target filtering method is any one of the radar data filtering methods described in the first aspect.

In this embodiment, the first determination unit 801 of the obstacle detection apparatus 800 may determine whether or not an object exists within the radar detection envelope of the target radar transceiver based on the filtered data sequence obtained by the target filtering method. Wherein the target filtering method is any one of the radar data filtering methods as described in the first aspect above.

In some optional implementations of this embodiment, the apparatus 800 further includes: the second determination unit (not shown in the figure) is configured to determine the class of the object if the object is present within the radar detection envelope.

The apparatus provided in the foregoing embodiment of the present disclosure determines whether an object exists within a radar detection envelope range of a target radar transceiver based on a filtered data sequence obtained by the first determining unit 801 by using a target filtering method, where the target filtering method is any one of the radar data filtering methods in the foregoing first aspect, thereby improving accuracy of obstacle detection.

With continuing reference to fig. 9, as an implementation of the method shown in the above figures, the present disclosure provides an embodiment of a parking apparatus, which corresponds to the embodiment of the method shown in fig. 6, and which may include the same or corresponding features as the embodiment of the method shown in fig. 6 and produce the same or corresponding effects as the embodiment of the method shown in fig. 6, in addition to the features described below. The device can be applied to various electronic equipment.

As shown in fig. 9, a parking device 9900 of the present embodiment includes: a third determination unit 901 and a control unit 902. The third determining unit 901 is configured to determine whether a parking space exists within a radar detection envelope range of a target vehicle provided with a radar transceiver end based on a filtered data sequence obtained by using a target filtering method, where the target filtering method is any one of the radar data filtering methods in the first aspect; the control unit 902 is configured to control the target vehicle to enter a parking space for parking if the parking space exists within the radar detection envelope.

In this embodiment, the third determining unit 901 of the parking apparatus 900 may determine whether there is a parking space within the radar detection envelope of the target vehicle provided with the radar transceiver based on the filtered data sequence obtained by using the target filtering method. Wherein the target filtering method is any one of the radar data filtering methods as described in the first aspect above.

In this embodiment, if there is a parking space within the radar detection envelope, the control unit 902 may control the target vehicle to enter the parking space for parking.

In the parking device provided in the above embodiment of the present disclosure, based on the filtered data sequence obtained by the third determining unit 901 by using the target filtering method, it is determined whether there is a parking space within the radar detection envelope range of the target vehicle provided with the radar transceiver, where the target filtering method is any one of the radar data filtering methods in the above first aspect, and if there is a parking space within the radar detection envelope range, the control unit 902 may control the target vehicle to drive into the parking space for parking, so as to improve the accuracy of parking space detection and improve the accuracy of automatic parking.

Those of ordinary skill in the art will understand that: all or part of the steps for implementing the method embodiments may be implemented by hardware related to program instructions, and the program may be stored in a computer readable storage medium, and when executed, the program performs the steps including the method embodiments; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.

In the present specification, the embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts in the embodiments are referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The method and apparatus of the present invention may be implemented in a number of ways. For example, the methods and apparatus of the present invention may be implemented in software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order for the steps of the method is for illustrative purposes only, and the steps of the method of the present invention are not limited to the order specifically described above unless specifically indicated otherwise. Furthermore, in some embodiments, the present invention may also be embodied as a program recorded in a recording medium, the program including machine-readable instructions for implementing a method according to the present invention. Thus, the present invention also covers a recording medium storing a program for executing the method according to the present invention.

The description of the present invention has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the invention in the form disclosed. Many modifications and variations will be apparent to practitioners skilled in this art. The embodiment was chosen and described in order to best explain the principles of the invention and the practical application, and to enable others of ordinary skill in the art to understand the invention for various embodiments with various modifications as are suited to the particular use contemplated.

Claims

1. A method of radar data filtering, comprising:

acquiring a radar data sequence arranged according to a time sequence and a moving distance associated with radar data in the radar data sequence, wherein the radar data in the radar data sequence indicates a distance between a radar transceiving end and a target object, the target object is located within a radar detection envelope of the radar transceiving end, and the moving distance associated with the radar data in the radar data sequence indicates a moving distance of the radar transceiving end;

and if the quantity of the radar data belonging to a preset radar data interval in the radar data sequence is smaller than a preset quantity threshold value, and target radar data do not belong to the preset radar data interval, filtering the radar data sequence based on the acquired moving distance to obtain a filtered data sequence, wherein the target radar data are the radar data with the time closest to the current time generated in the radar data sequence.

2. The method of claim 1, wherein the filtering the radar data sequence based on the obtained moving distance to obtain a filtered data sequence comprises:

determining whether a target movement distance is less than or equal to a distance indicated by the radar detection envelope, wherein the target movement distance is a movement distance associated with target valid radar data that precedes the target radar data and is a radar data that is closest to the target radar data among radar data belonging to the preset radar data interval in the radar data sequence;

and if the target moving distance is less than or equal to the distance indicated by the radar detection envelope range of the radar transceiving end, updating the target radar data into the target effective radar data to obtain an updated radar data sequence, and taking the updated radar data sequence as a filtered data sequence.

3. An obstacle detection method, comprising:

determining whether an object exists in a radar detection envelope range of a target radar transceiver based on a filtered data sequence obtained by using a target filtering method, wherein the target filtering method is the radar data filtering method according to any one of claims 1-2.

4. A method of parking a vehicle, comprising:

determining whether a parking space exists in a radar detection envelope range of a target vehicle provided with a radar transceiving end based on a filtered data sequence obtained by adopting a target filtering method, wherein the target filtering method is the radar data filtering method according to one of claims 1-2;

and if the parking space exists in the radar detection envelope range, controlling the target vehicle to drive into the parking space to park.

5. A radar data filtering apparatus, comprising:

an acquisition unit configured to acquire a radar data sequence arranged in time order and a moving distance associated with radar data in the radar data sequence, wherein the radar data in the radar data sequence indicates a distance between a radar transceiving end and a target object, the target object is located within a radar detection envelope of the radar transceiving end, and the moving distance associated with the radar data in the radar data sequence indicates a distance moved by the radar transceiving end;

the first filtering unit is configured to filter the radar data sequence based on the acquired moving distance to obtain a filtered data sequence if the number of radar data in the radar data sequence, which belong to a preset radar data interval, is smaller than a preset number threshold and target radar data does not belong to the preset radar data interval, wherein the target radar data is the radar data in the radar data sequence, which is generated in the time closest to the current time.

6. The apparatus of claim 5, wherein the first filtering unit comprises:

a determining module configured to determine whether a target movement distance is less than or equal to a distance indicated by the radar detection envelope range, wherein the target movement distance is a movement distance associated with target valid radar data that precedes the target radar data and is a radar data that is closest to the target radar data among radar data belonging to the preset radar data interval in the radar data sequence;

an update module configured to update the target radar data to the target valid radar data if the target movement distance is less than or equal to a distance indicated by a radar detection envelope range of the radar transceiving end, resulting in an updated radar data sequence, and to take the updated radar data sequence as a filtered data sequence.

7. An obstacle detection device, comprising:

a first determining unit configured to determine whether an object exists within a radar detection envelope of a target radar transceiver based on a filtered data sequence obtained by using a target filtering method, wherein the target filtering method is the radar data filtering method according to any one of claims 1 to 2.

8. A parking apparatus, comprising:

a third determining unit configured to determine whether there is a parking space within a radar detection envelope of a target vehicle provided with radar transceiving ends based on a filtered data sequence obtained by using a target filtering method, wherein the target filtering method is the radar data filtering method according to any one of claims 1 to 2;

a control unit configured to control the target vehicle to drive into a parking space for parking if the parking space exists within the radar detection envelope.

9. An electronic device, comprising:

a memory for storing a computer program;

a processor for executing a computer program stored in the memory, and when executed, implementing the method of any of the preceding claims 1-4.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method of any one of the preceding claims 1 to 4.