CN115063980B

CN115063980B - Self-adaptive vehicle abnormal running detection method and device and terminal equipment

Info

Publication number: CN115063980B
Application number: CN202210492957.7A
Authority: CN
Inventors: 请求不公布姓名
Original assignee: Shenzhen Huichen Software Co ltd
Current assignee: Shenzhen Huichen Software Co ltd
Priority date: 2022-05-07
Filing date: 2022-05-07
Publication date: 2024-07-26
Anticipated expiration: 2042-05-07
Also published as: CN115063980A

Abstract

The application is applicable to the technical field of vehicle monitoring, and provides a self-adaptive vehicle abnormal running detection method, a device and terminal equipment, wherein the method comprises the following steps: collecting vehicle fusion information of each vehicle, determining an abnormal running speed threshold corresponding to a lane and a vehicle type of each vehicle according to the vehicle fusion information, calculating to obtain vehicle abnormal running comprehensive probability according to the vehicle fusion information and the abnormal running speed threshold, determining a vehicle abnormal running state detection result according to the vehicle abnormal running comprehensive probability, generating alarm information when the vehicle is detected to be in an abnormal running state, and sending the alarm information to a target terminal. According to the application, the corresponding abnormal running speed threshold value is adaptively adjusted based on the vehicle type and the lane through the laser integrated antenna, the abnormal detection result of the vehicle is comprehensively determined, the abnormal situation of the detection result caused by internal factors such as vehicle faults or external factors such as bad weather and traffic accidents is reduced, and the accuracy and the stability of the abnormal detection result of the vehicle are improved.

Description

Self-adaptive vehicle abnormal running detection method and device and terminal equipment

Technical Field

The application belongs to the technical field of vehicle monitoring, and particularly relates to a self-adaptive vehicle abnormal running detection method, device and terminal equipment.

Background

With the rapid development of society, the number of vehicles in cities is increased, and the potential safety hazard of urban traffic is increased.

Among them, the occupation of safety problems due to abnormal driving of the vehicle by the driver is relatively large. Therefore, the running state of the vehicle needs to be monitored in real time, so that potential safety hazards are reduced.

Related abnormal driving monitoring methods of vehicles generally detect whether the driving speed of a vehicle exceeds (or falls below) a preset speed threshold value through sensing data collected by various sensors, and detect whether the vehicle is in an abnormal driving state.

However, the detection result of the method is easily affected by external environmental factors (such as bad weather or traffic accidents) such as vehicle internal factors (such as vehicle faults, etc.), so that the accuracy and stability of the detection result are not high.

Disclosure of Invention

The embodiment of the application provides a self-adaptive vehicle abnormal running detection method, a device, terminal equipment and a readable storage medium, which can solve the problems of low accuracy and poor stability of detection results of a related vehicle abnormal running monitoring method.

In a first aspect, an embodiment of the present application provides a method for detecting abnormal driving of a self-adaptive vehicle, which is applied to a laser integrated antenna, and is connected in communication between every two adjacent laser integrated antennas in a driving direction;

the self-adaptive vehicle abnormal running detection method comprises the following steps:

Collecting vehicle fusion information of each vehicle; the vehicle fusion information comprises an ID of a vehicle, a vehicle running speed, vehicle position information, a relative distance between the vehicle and the laser integrated antenna, a signal-to-noise ratio of the vehicle, vehicle type information, license plate information and a running direction;

determining an abnormal running speed threshold corresponding to the lane and the vehicle type of each vehicle according to the vehicle fusion information; the abnormal driving speed threshold value comprises an overspeed threshold value and a slow speed threshold value;

calculating to obtain the vehicle abnormal running comprehensive probability according to the vehicle fusion information and the abnormal running speed threshold;

Determining whether the vehicle is in a detection result of an abnormal running state according to the comprehensive abnormal running probability of the vehicle;

and when the detection result is that the vehicle is in an abnormal running state, generating alarm information and sending the alarm information to a target terminal.

In a second aspect, an embodiment of the present application provides an adaptive vehicle abnormal driving detection device, which is applied to a laser integrated antenna, and is in communication connection between every two adjacent laser integrated antennas in a driving direction;

the adaptive vehicle abnormal running detection device includes:

The information acquisition module is used for acquiring vehicle fusion information of each vehicle; the vehicle fusion information comprises an ID of a vehicle, a vehicle running speed, vehicle position information, a relative distance between the vehicle and the laser integrated antenna, a signal-to-noise ratio of the vehicle, vehicle type information, license plate information and a running direction;

The threshold value determining module is used for determining an abnormal running speed threshold value corresponding to the lane and the vehicle type of each vehicle according to the vehicle fusion information; the abnormal driving speed threshold value comprises an overspeed threshold value and a slow speed threshold value;

The probability determining module is used for calculating the abnormal running comprehensive probability of the vehicle according to the vehicle fusion information and the abnormal running speed threshold value;

the abnormal detection module is used for determining whether the vehicle is in a detection result of an abnormal running state according to the comprehensive abnormal running probability of the vehicle;

And the alarm module is used for generating alarm information and sending the alarm information to a target terminal when the detection result is that the vehicle is in an abnormal running state.

In a third aspect, an embodiment of the present application provides a terminal device, including a radio frequency module, a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the method for detecting abnormal driving of an adaptive vehicle according to any one of the first aspect when the processor executes the computer program.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the adaptive vehicle abnormal running detection method according to any one of the first aspects described above.

In a fifth aspect, an embodiment of the present application provides a computer program product, which when run on a terminal device, causes the terminal device to perform the adaptive vehicle abnormal running detection method according to any one of the first aspects above.

Compared with the prior art, the embodiment of the application has the beneficial effects that: the laser integrated antenna is used for collecting vehicle fusion information, adaptively determining an abnormal running speed threshold corresponding to the type and the lane of the vehicle based on the vehicle fusion information, calculating the comprehensive abnormal running probability of the vehicle, determining whether the vehicle is in the abnormal running detection result, adaptively adjusting the corresponding abnormal running speed threshold based on different types, different lanes and different environments, reducing the influence of internal factors and external factors of the vehicle on the abnormal running detection result of the vehicle, and improving the accuracy and stability of the abnormal running detection result of the vehicle.

It will be appreciated that the advantages of the second to fifth aspects may be found in the relevant description of the first aspect, and are not described here again.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments or the description of the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a schematic diagram of an adaptive vehicle abnormal running detection system provided in an embodiment of the present application;

fig. 2 is a flow chart of an adaptive vehicle abnormal running detection method according to an embodiment of the present application;

FIG. 3 is a schematic diagram of an on-road laser integrated antenna according to an embodiment of the present application;

Fig. 4 is a schematic structural diagram of an adaptive vehicle abnormal running detection device according to an embodiment of the present application;

Fig. 5 is a schematic structural diagram of a terminal device according to an embodiment of the present application.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

It should be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

It should also be understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.

As used in the present description and the appended claims, the term "if" may be interpreted as "when..once" or "in response to a determination" or "in response to detection" depending on the context. Similarly, the phrase "if a determination" or "if a [ described condition or event ] is detected" may be interpreted in the context of meaning "upon determination" or "in response to determination" or "upon detection of a [ described condition or event ]" or "in response to detection of a [ described condition or event ]".

Furthermore, the terms "first," "second," "third," and the like in the description of the present specification and in the appended claims, are used for distinguishing between descriptions and not necessarily for indicating or implying a relative importance.

Reference in the specification to "one embodiment" or "some embodiments" or the like means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the application. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," and the like in the specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments" unless expressly specified otherwise. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless expressly specified otherwise.

The self-adaptive vehicle abnormal running detection method provided by the embodiment of the application can be applied to terminal equipment such as laser integrated antennas, and the like, and every two adjacent laser integrated antennas are in communication connection in the running direction. The embodiment of the application does not limit the specific type of the terminal equipment.

In recent years, there are more and more potential safety hazards in urban traffic, wherein the occupation of safety problems caused by abnormal driving of vehicles by drivers is relatively large. The related vehicle abnormal running monitoring method has the problems of low accuracy and poor stability of the detection result. In order to solve the problem, the application provides a self-adaptive vehicle abnormal running detection method, a self-adaptive vehicle abnormal running detection device, a terminal device and a computer readable storage medium, which can collect vehicle fusion information through a laser integrated antenna in the vehicle running process, and self-adaptively determine abnormal running speed thresholds corresponding to lanes and vehicle types based on the vehicle fusion information, so as to detect whether the vehicle is in an abnormal running state, and realize self-adaptive and dynamic adjustment of the corresponding abnormal running speed thresholds based on different vehicle types and different lanes, thereby improving the accuracy and stability of a vehicle abnormal detection result.

In order to realize the technical scheme provided by the application, a self-adaptive vehicle abnormal running detection system can be constructed. Referring to fig. 1, the adaptive vehicle abnormal driving detection system is composed of more than one laser integrated antenna (only 4 are shown in fig. 1) and at least one vehicle (only 2 are shown in fig. 1, each vehicle is provided with an OBU), every two adjacent laser integrated antennas are in communication connection (the laser integrated antenna 1 is in communication connection with the laser integrated antenna 2 in fig. 1, the laser integrated antenna 3 is in communication connection with the laser integrated antenna 4) in the driving direction, and the laser integrated antennas are in communication with the OBU of the vehicle in the driving direction through the built-in RSUs thereof based on a special short range communication technology (DEDICATED SHORT RANGE COMMUNICATIONS, DSRC).

The laser integrated antenna is detection equipment capable of acquiring vehicle fusion information through radio frequency signals and providing a vehicle abnormal running detection function based on the vehicle fusion information, and the RSU built in the laser integrated antenna is identification equipment for determining vehicle identity information through communication with an OBU on a vehicle. In the running process of the vehicle, the laser integrated antenna carries out fusion processing on the radio frequency signals and the vehicle identity information determined by the built-in RSU to obtain vehicle fusion information, an abnormal running threshold (comprising an overspeed threshold and a slow speed threshold) corresponding to the vehicle type and the lane of each vehicle is adaptively and dynamically determined based on the vehicle fusion information, the probability of overspeed running or slow running of the vehicle is calculated and determined based on the vehicle fusion information and the abnormal running threshold, and accordingly whether the vehicle is in a detection result of overspeed running or slow running state is determined, and corresponding alarm information is generated based on the detection result.

In order to illustrate the technical scheme provided by the application, the following description is made by specific embodiments.

Fig. 2 shows a schematic flow chart of the adaptive vehicle abnormal driving detection method provided by the application, which can be applied to a laser integrated antenna by way of example and not limitation.

S101, collecting vehicle fusion information of each vehicle; the vehicle fusion information comprises the ID of the vehicle, the running speed of the vehicle, the position information of the vehicle, the relative distance between the vehicle and the laser integrated antenna, the signal-to-noise ratio of the vehicle, the vehicle type information, the license plate information and the running direction.

Specifically, a side rod or a portal is deployed at preset distances (which can be specifically set according to actual requirements, such as 100m or 200 m) on public transportation roads (including but not limited to highways), each laser integrated antenna is mounted on a side rod/portal, and every two adjacent laser integrated antennas in the same driving direction are in communication connection. Meanwhile, each laser integrated antenna is initialized, parameters of the laser integrated antennas (including but not limited to ID, IP address, longitude and latitude position of the communication port laser integrated antenna, positive beam pointing absolute coordinate vector of the laser integrated antenna, ID of a covered road section, driving direction of the covered road section, radio frequency point, bandwidth, radio frequency emission power, binding area position and system parameters) are configured to realize full coverage of the whole road section, and simultaneously, space-time synchronization operation is performed on all the laser integrated antennas on the current road section and in the current vehicle flow direction, so that the data acquisition coordinate system of each laser integrated antenna is unified or can be unified (namely, the data acquisition coordinate system of each laser integrated antenna is directly configured to be unified or a coordinate system conversion matrix is configured), the timers of all the laser integrated antennas are synchronized, and the low-delay communication and time synchronization functions are realized among all the laser integrated antennas.

Specifically, the communication class and the corresponding communication object of each laser integrated antenna are determined based on the traveling direction and the position information of each laser integrated antenna. The laser integrated antenna with low communication level sends the detection result and the corresponding alarm information to the adjacent laser integrated antenna with high communication level. Mainly expressed as: the communication level of the laser integrated antenna at the road entrance corresponding to the driving direction is the lowest, the communication level of the laser integrated antenna at the road exit corresponding to the driving direction is the highest, and the communication level of the laser integrated antenna from the road entrance to the exit is increased one by one. And the full coverage of the whole road section on the road is sequentially realized, and whether the vehicle in the current road section is in an overspeed or slow driving state is monitored and determined in real time.

FIG. 3 schematically illustrates a schematic diagram of an on-road laser integrated antenna;

In fig. 3, the road driving direction is from left to right, and the corresponding communication levels from the laser integrated antenna 4 at the left entrance, the middle laser integrated antenna 5, and the laser integrated antenna 6 at the right exit are increased one by one, that is, the communication level of the laser integrated antenna 4 < the communication level of the laser integrated antenna 5 < the communication level of the laser integrated antenna 6; the corresponding laser integrated antenna 4 transmits the detection result and the corresponding alarm information to the laser integrated antenna 5, and the laser integrated antenna 5 transmits the detection result and the corresponding alarm information to the laser integrated antenna 6.

Specifically, vehicle fusion information of each vehicle meeting a preset range on a current road and in a current driving direction is acquired and determined in advance through a laser fusion technology, wherein the vehicle fusion information comprises, but is not limited to, an ID of the vehicle, a driving speed of the vehicle, vehicle position information, a relative distance between the vehicle and a current laser integrated antenna, a signal-to-noise ratio of the vehicle, a driving direction, vehicle type information and license plate information. The preset range can be determined according to the traveling direction and the distance between the current laser integrated antenna and the adjacent laser integrated antenna. The predetermined range is specifically from the position of the current laser integrated antenna to the region between one laser integrated antenna (i.e., two adjacent laser integrated antennas) closest to the current laser integrated antenna in the current traveling direction.

For example, in fig. 3, the road traveling direction is from left to right, the laser integrated antenna 4 is located at the road entrance, the laser integrated antenna 4 needs to collect vehicle fusion information of each vehicle in the region from the road entrance (i.e., the position of the laser integrated antenna 14) to the laser integrated antenna 5, and the laser integrated antenna 5 needs to collect vehicle fusion information of each vehicle in the region from the position of the laser integrated antenna 5 to the laser integrated antenna 6.

S102, determining an abnormal running speed threshold corresponding to the lane and the vehicle type of each vehicle according to the vehicle fusion information; the abnormal travel speed threshold includes an overspeed threshold and a slow speed threshold.

Specifically, according to the road traffic safety regulations, different types of vehicles, different lanes each have different vehicle limiting speeds (a highest limiting speed and a lowest limiting speed, hereinafter simply referred to as an overspeed threshold value and a slowness threshold value). Therefore, first, the lane and the vehicle type of each vehicle are determined from the vehicle fusion information, and the abnormal running speed threshold corresponding to each vehicle is adaptively determined based on the lane and the vehicle type of the vehicle. The abnormal travel speed threshold includes an overspeed threshold and a slow speed threshold.

And S103, calculating the vehicle abnormal running comprehensive probability according to the vehicle fusion information and the abnormal running speed threshold value.

Specifically, the vehicle abnormal running probability and the motion smoothing probability are calculated and determined according to the vehicle fusion information and the abnormal running speed threshold value, and the vehicle abnormal running comprehensive probability is calculated and determined according to the vehicle abnormal running probability and the motion smoothing probability. The transverse abnormal driving probability refers to the abnormal driving probability which is calculated and determined based on the deviation degree between the vehicle and the total vehicle flow speed on the current road section; the motion smoothing probability refers to an abnormal running probability determined by calculation based on the degree of speed smoothing of the vehicle itself.

S104, determining whether the vehicle is in a detection result of the abnormal running state according to the comprehensive abnormal running probability of the vehicle.

Specifically, a first detection result of whether the vehicle is in an overrun state or a second detection result of whether the vehicle is in a slow-speed state is determined according to the vehicle abnormal-running integrated probability and a preset vehicle abnormal-running integrated probability threshold.

And S105, when the detection result is that the vehicle is in an abnormal running state, generating alarm information and sending the alarm information to a target terminal.

Specifically, when the detection result of the vehicle is that the vehicle is in an overspeed running state, overspeed warning information is generated and sent to the target terminal. And when the detection result of the vehicle is that the vehicle is in a slow running state, generating slow warning information and sending the slow warning information to the target terminal. The target terminal is a preset terminal device for receiving alarm information, and includes, but is not limited to, other laser integrated antennas with communication levels higher than those of the current laser integrated antennas, the vehicle-mounted devices of the vehicles and the mobile terminals of the vehicle owners in the abnormal driving states, and the vehicle-mounted devices of other vehicles and the mobile terminals of the vehicle owners on the current road section. The warning information includes, but is not limited to, a vehicle ID, license plate information, lane information, a vehicle traveling speed, vehicle position information, and voice and/or text information that the vehicle is in an abnormal traveling state.

Based on the vehicle fusion information, the overspeed threshold and the slow threshold corresponding to the vehicle are dynamically adjusted according to different lanes and vehicle types, so that the detection result of overspeed or slow running of the vehicle can be prevented from being wrongly judged under the influence of external factors such as bad weather, traffic accidents and the like or under the influence of internal factors such as vehicle faults and the like. The abnormal running probability of different vehicles on different lanes under different environments is accurately detected, and the accuracy and stability of the abnormal vehicle detection result are improved.

In one embodiment, the determining the abnormal driving speed threshold corresponding to the lane and the vehicle type of each vehicle according to the vehicle fusion information includes:

Acquiring system parameters; the system parameters comprise a transverse coefficient, a longitudinal frame number, a speed precision, a standard distance, a maximum signal-to-noise ratio, a longitudinal model standard deviation, a vehicle type initial overspeed threshold value corresponding to each vehicle type, a lane initial overspeed threshold value corresponding to each lane, a vehicle type initial slow speed threshold value corresponding to each vehicle type, a lane initial slow speed threshold value corresponding to each lane, a threshold value update coefficient, a transverse model standard deviation, a preset vehicle abnormal running comprehensive probability threshold value, a preset overspeed running confidence coefficient threshold value and a preset slow speed running confidence coefficient threshold value;

Determining a target lane and a target vehicle type of each vehicle according to the vehicle fusion information;

Determining an initial overspeed threshold value and an initial slow threshold value of a target lane corresponding to each target lane, and an initial overspeed threshold value and an initial slow threshold value of a target vehicle corresponding to each target vehicle type;

calculating and determining an average overspeed coefficient of the vehicle according to the vehicle running speed of each vehicle, the initial overspeed threshold value of the target lane and the initial overspeed threshold value of the target vehicle type;

calculating and determining an average slow coefficient of the vehicle according to the vehicle running speed of each vehicle, the initial slow threshold of the target lane and the initial slow threshold of the target vehicle type;

Calculating to obtain a lane overspeed threshold according to the average overspeed coefficient of the vehicle and the target lane overspeed threshold;

According to the average overspeed coefficient of the vehicle and the overspeed threshold value of the target vehicle type, calculating to obtain the overspeed threshold value of the vehicle type;

calculating a lane slow threshold according to the average slow coefficient of the vehicle and the target lane slow threshold;

according to the average slow coefficient of the vehicle and the target vehicle type slow threshold, calculating to obtain a vehicle type slow threshold;

and selecting an overspeed threshold and a slow threshold which meet preset conditions from the lane overspeed threshold, the vehicle type overspeed threshold, the lane slow threshold and the vehicle type slow threshold.

Specifically, system parameters of the initialized laser integrated antenna are determined. The system parameters include, but are not limited to, lateral coefficients, longitudinal frame numbers, speed accuracy, standard distance, maximum signal to noise ratio, longitudinal model standard deviation, vehicle type initial overspeed threshold value corresponding to each vehicle type, lane initial overspeed threshold value corresponding to each lane, vehicle type initial slowness threshold value corresponding to each vehicle type, lane initial slowness threshold value corresponding to each lane, threshold value update coefficients, lateral model standard deviation, preset vehicle abnormal driving comprehensive probability threshold value, preset overspeed driving confidence threshold value, and preset slowness confidence threshold value.

The transverse coefficient alpha is the weight for calculating the transverse abnormal running probability, the longitudinal coefficient beta is the weight for calculating the motion smoothing probability, and the motion smoothing probability can be determined through the fitting of the historical vehicle running speed on the current road section (namely, the parameter with the highest detection accuracy is selected to be fitted), or the motion smoothing probability is determined through a machine learning algorithm; the value range is as follows: alpha epsilon (0, 1) and beta epsilon (0, 1). The longitudinal frame number N and the speed precision Deltav are used for calculating the speed expansion aromatic entropy. The greater the number of longitudinal frames, the longer the period of time the historical vehicle travel speed is required to calculate the motion smoothing probability. Since detecting an abnormal running state of the vehicle mainly requires determining the degree of smoothness of the speed change of the vehicle several seconds before overspeed/low speed, N is not required to be set to an excessive value, and N e 50, 100 is generally set. The speed precision Deltav is used for dividing the running speed of the historical vehicle into sections, determining the probability of the running speed of the historical vehicle in each section, and setting Deltav epsilon [0.2,5] km/h generally because of uneven probability distribution caused by excessive or insufficient probability. The standard distance is the distance between the vehicle and the laser integrated antenna at the time when the maximum signal-to-noise ratio SNRmax is detected, and SNRmax epsilon [10m,100m ] is generally set. The most accurate value of motion smoothing probability detection can be selected through the fitting of the historical vehicle running speed on the current road section and used as the standard deviation of a longitudinal model; the standard deviation of the transverse model can determine the sensitivity of the abnormal running detection result of the vehicle, the smaller the standard deviation of the transverse model is, the higher the sensitivity of the abnormal running detection result of the vehicle is when the overspeed and the low speed are detected, and the standard deviation epsilon (2 km/h,5 km/h) of the transverse model is set. Normal average speed coefficient= (historical vehicle average running speed of the vehicle type corresponding to the current road section)/Hs of each vehicle type, and normal average speed coefficient= (historical vehicle average running speed of the vehicle type corresponding to the current road section)/Hs of each lane. And determining an initial overspeed threshold value of the vehicle type corresponding to each vehicle type, an initial overspeed threshold value of the lane corresponding to each lane, an initial slow threshold value of the vehicle type corresponding to each vehicle type and an initial slow threshold value of the lane corresponding to each lane according to the road traffic specification. The lower the threshold update coefficient, the higher the sensitivity of the abnormal travel speed threshold iteration, and thus the threshold update coefficient e (0,0.2) is set, the lower the preset vehicle abnormal travel comprehensive probability threshold Ps is, the higher the sensitivity of abnormal travel state detection is, the lower the detection accuracy is, and thus the preset vehicle abnormal travel comprehensive probability threshold Ps e [0.7,0.9] is set, and the greater the preset overdrive confidence threshold ks1 (or preset slow travel confidence threshold ks 2) is, the lower the sensitivity of abnormal travel state detection is, and thus the preset overdrive confidence threshold ks1 (or preset slow travel confidence threshold ks 2) e [10, 50] is set.

Specifically, the target lane and the target vehicle type of each currently detected vehicle are determined according to the content of the vehicle type information, the vehicle position information, the vehicle ID and the like in the vehicle fusion information. And determining a target lane initial overspeed threshold value and a target lane initial slowness threshold value corresponding to the target lane of each vehicle and a target vehicle type initial overspeed threshold value and a target vehicle type initial slowness threshold value corresponding to the target vehicle type of each vehicle according to the system parameters. And calculating and determining an average overspeed coefficient of the vehicle according to the vehicle running speed of each vehicle, the initial overspeed threshold value of the target lane and the initial overspeed threshold value of the target vehicle type. And calculating and determining an average slow coefficient of the vehicle according to the vehicle running speed of each vehicle, the initial slow threshold of the target vehicle type and the initial slow threshold of the target lane.

Specifically, the calculation method of the vehicle average overspeed coefficient ζ _{_Ls} and the vehicle average slowness coefficient ζ _{_Hs} is as follows:

Where v _i denotes a vehicle running speed, ls _i denotes a lane/vehicle type initial slow threshold, hs _i denotes a lane/vehicle type initial slow threshold, and n denotes a vehicle number.

Specifically, a lane overspeed threshold is calculated according to the average overspeed coefficient of the vehicle and the target lane overspeed threshold. And calculating the overspeed threshold value of the vehicle type according to the average overspeed coefficient of the vehicle and the overspeed threshold value of the target vehicle type. And calculating the lane slow threshold according to the average slow coefficient of the vehicle and the target lane slow threshold. And calculating the vehicle model slow threshold according to the vehicle average slow coefficient and the target vehicle model slow threshold. And selecting the overspeed threshold value and the slow threshold value which meet the preset conditions from the lane overspeed threshold value, the vehicle type overspeed threshold value, the lane slow threshold value and the vehicle type slow threshold value.

Specifically, the calculation methods of the lane overspeed threshold value, the vehicle type overspeed threshold value, the lane slow speed threshold value and the vehicle type slow speed threshold value are as follows:

Hs=Hs [1+bln (1+ζ _{_Hs}-ζ₀) ] (equation 2)

Wherein Ls ^* represents a lane/vehicle type slow threshold; hs ^* represents the lane/vehicle type overspeed threshold; a represents a transverse coefficient, b represents a longitudinal coefficient, ζ ₀ represents a normal average speed coefficient of a lane/vehicle type.

In this embodiment, when it is detected that the vehicle average overspeed coefficient ζ _{_Ls} is greater than 1, or the vehicle average slowness coefficient ζ _{_Hs} is smaller than the normal coefficient ζ ₀, the initial overspeed/slowness threshold is kept unchanged (i.e., the corresponding overspeed or slowness threshold is not required to be determined through the calculation of the above formula 2).

Through the vehicle type of each vehicle and the overall vehicle speed on each lane, the overspeed threshold value and the slow threshold value of the lane where each vehicle is located are dynamically adjusted, and abnormal running events and normal running events of the vehicle under different traffic conditions (including congestion or normal) under different weather conditions are accurately distinguished, so that the detection precision and stability of abnormal running of the vehicle are improved.

For example, in normal weather, all vehicles on a public traffic road run at a normal speed, and an abnormal running speed threshold is correspondingly adjusted based on the normal speed, and when detecting that the running speed of a certain vehicle is lower than the normal running speed, the vehicle is determined to run slowly; or when all vehicles on the public traffic road run at a slow speed due to factors such as vehicle blockage, bad weather such as rain, snow and fog and the like, correspondingly and dynamically adjusting the abnormal running speed threshold value based on the overall slow speed of the traffic flow, and judging that the vehicle is in an overspeed or slow running state when the running speed of a certain vehicle is detected to be higher than the adjusted overspeed threshold value or lower than the adjusted slow speed threshold value. And 3, accurately detecting overspeed or slow running states of the vehicle under different environments. Or after dynamically adjusting the abnormal running speed based on the overall traffic running speed on the public traffic road, when a certain vehicle detects that the running speed of the vehicle is higher than the adjusted overspeed threshold value or lower than the adjusted slow speed threshold value due to internal faults, the vehicle is judged to be in an overspeed or slow speed running state.

In one embodiment, selecting the overspeed threshold value and the slow threshold value that meet the preset condition from the lane overspeed threshold value, the vehicle type overspeed threshold value, the lane slow threshold value and the vehicle type slow threshold value includes:

When the lane overspeed threshold value is detected to be smaller than or equal to the vehicle type overspeed threshold value, selecting the lane overspeed threshold value as an overspeed threshold value meeting a preset condition;

Or when the overspeed threshold value of the vehicle type is detected to be smaller than or equal to the overspeed threshold value of the lane, selecting the overspeed threshold value of the lane as the overspeed threshold value meeting a preset condition;

When the lane slow speed threshold is detected to be greater than or equal to the vehicle type slow speed threshold, selecting the lane slow speed threshold as a slow speed threshold meeting a preset condition;

or when the vehicle type slow speed threshold value is detected to be larger than or equal to the lane slow speed threshold value, selecting the vehicle type slow speed threshold value as a slow speed threshold value meeting a preset condition.

Specifically, based on overspeed thresholds or slow thresholds with different values of different lanes and different vehicle types, preset conditions are preset to select the slow threshold with the largest value and the overspeed threshold with the smallest value in order to improve the accuracy of detection results of abnormal driving states. Correspondingly, when the lane overspeed threshold value is detected to be smaller than or equal to the vehicle type overspeed threshold value, selecting the lane overspeed threshold value as an overspeed threshold value meeting a preset condition; or when the overspeed threshold value of the vehicle type is detected to be smaller than or equal to the overspeed threshold value of the lane, selecting the overspeed threshold value of the vehicle type as the overspeed threshold value meeting the preset condition. When the lane slow threshold is detected to be greater than or equal to the vehicle type slow threshold, selecting the lane slow threshold as a slow threshold meeting a preset condition; or when the vehicle type slow speed threshold value is detected to be larger than or equal to the lane slow speed threshold value, selecting the vehicle type slow speed threshold value as the slow speed threshold value meeting the preset condition.

For example, the lane overspeed threshold value is 120km/h, the vehicle type overspeed threshold value is 130km/h, and 120km/h is selected as the overspeed threshold value. The lane slow speed threshold is 60km/h, the vehicle type slow speed threshold is 40km/h, and 60km/h is selected as the slow speed threshold.

In one embodiment, the calculating the vehicle abnormal driving comprehensive probability according to the vehicle fusion information and the abnormal driving speed threshold value includes:

Determining a lateral abnormal driving probability of the vehicle according to the driving speed of the vehicle and the abnormal driving speed threshold;

determining a motion smoothing probability of the vehicle according to the relative distance between the vehicle and the laser integrated antenna and the signal-to-noise ratio;

And calculating to obtain the comprehensive probability of abnormal running of the vehicle according to the transverse abnormal running probability and the motion smoothing probability.

Specifically, according to the comparison result of the running speed of the vehicle and the abnormal running speed threshold value, it is determined whether the current vehicle is likely to be in the overspeed running state or the slow running state, and according to the comparison result, the running speed of the vehicle and the abnormal running speed threshold value are input into the corresponding lateral normal distribution model, and the lateral overspeed running probability of the vehicle or the lateral slow running probability of the vehicle (i.e., the lateral abnormal running probability P ₁ of the vehicle) is determined. When the vehicle is determined to be in an abnormal driving state based on the comparison result, the relative distance between the vehicle and the laser integrated antenna and the signal to noise ratio are input into a longitudinal normal distribution model to obtain a motion smoothing probability P ₂. And calculating the transverse abnormal running probability and the motion smooth probability to obtain the vehicle abnormal running comprehensive probability. And determining whether the vehicle is in the overspeed driving state or the slow driving state according to the comprehensive abnormal driving probability of the vehicle.

In one embodiment, when it is detected that the running speed of the vehicle is greater than or equal to the slow speed threshold value and less than or equal to the overspeed threshold value, it is determined that the vehicle is in a normal running state.

Specifically, the vehicle abnormal running comprehensive probability calculation method may be expressed as:

P=α·p ₁+β·P₂ (formula 3)

In one embodiment, if the vehicle speed does not exceed the overspeed threshold value or is not below the creep threshold value, it is determined that the overspeed/creep state of the vehicle does not occur, and the overspeed confidence kH and the creep confidence kL of the vehicle are respectively decremented by 1 (the minimum value of the overspeed confidence and the creep confidence is 0).

In one embodiment, the determining the probability of lateral abnormal driving of the vehicle according to the driving speed of the vehicle and the abnormal driving speed threshold value includes:

When the vehicle running speed of the vehicle is detected to be greater than the overspeed threshold value, inputting the vehicle running speed into a first transverse normal distribution model to obtain transverse overspeed running probability; the standard deviation of the first transverse normal distribution model is the standard deviation of the transverse model, and the mean value is the overspeed threshold value;

When the vehicle running speed of the vehicle is detected to be smaller than the slow threshold value, inputting the vehicle running speed into a second transverse normal distribution model to obtain transverse slow running probability; and the standard deviation of the second transverse normal distribution model is the standard deviation of the transverse model, and the average value is the slow threshold value.

Specifically, the lateral abnormal running probability of the vehicle includes a lateral overrun running probability or a lateral slow running probability. When the vehicle running speed of the vehicle is detected to be greater than the overspeed threshold value, the vehicle is judged to be in an overspeed running state possibly, the vehicle running speed is input into a first transverse normal distribution model with standard deviation being the standard deviation of the transverse model and average value being the overspeed threshold value, and the transverse overspeed running probability is obtained. Or when the vehicle running speed of the vehicle is detected to be smaller than the slow threshold value, judging that the vehicle is possibly in a slow running state, and inputting the vehicle running speed into a second transverse normal distribution model with the standard deviation being the standard deviation of the transverse model and the mean value being the slow threshold value, so as to obtain the transverse slow running probability.

In one embodiment, the determining the motion smoothing probability of the vehicle according to the relative distance between the vehicle and the laser integrated antenna and the signal-to-noise ratio comprises:

acquiring the historical vehicle running speed of the longitudinal frame number;

partitioning the historical vehicle running speed based on the speed precision to obtain a plurality of speed intervals;

calculating to obtain a speed expansion aromatic entropy according to the relative distance between the vehicle and the laser integrated antenna, the standard distance, a signal-to-noise ratio average value of the vehicle running speed of each vehicle in each speed interval and the maximum signal-to-noise ratio;

Inputting the speed expansion aromatic entropy into a longitudinal normal distribution model to obtain motion smoothing probability; the mean value of the longitudinal normal distribution model is zero, and the standard deviation is the standard deviation of the longitudinal model.

Specifically, a history of vehicle travel speeds for a number of longitudinal frames on the current road segment (the history of vehicle travel speeds is a vehicle travel speed acquired before the current frame) is acquired. And dividing the historical vehicle running speed based on the speed precision and the longitudinal frame number to obtain a plurality of speed intervals, and determining the probability p _vi that the vehicle running speed of each vehicle is positioned in each speed area, so as to determine the signal-to-noise ratio average value of the vehicle running speed of each vehicle in each speed interval. Calculating to obtain a speed expansion aromatic entropy according to the relative distance between the vehicle and the laser integrated antenna, the standard distance, the average value of the signal to noise ratio and the maximum signal to noise ratio of the vehicle running speed of each vehicle in each speed interval, inputting the speed expansion aromatic entropy into a longitudinal normal distribution model with the average value of zero and the standard deviation of the longitudinal model standard deviation, and obtaining the motion smoothing probability.

Firstly, determining the signal-to-noise ratio of each vehicle based on the distance Ri between the vehicle and the laser integrated antenna, the standard distance Rb and the average value of the signal-to-noise ratio in each speed interval;

Wherein, Representing the signal-to-noise ratio for each vehicle, SNR _i represents the average of the signal-to-noise ratios over each speed interval.

Then with the signal to noise ratio of each vehicleAnd the ratio of the maximum signal-to-noise ratio SNR _max For the weight, calculating the expanded aromatic entropy S of the speed based on the signal-to-noise ratio confidence level:

And the expanded aromatic entropy S is input into a longitudinal normal distribution model, so that the motion smoothing probability is obtained.

In one embodiment, the determining, according to the comprehensive probability of abnormal running of the vehicle, a result of detecting whether the vehicle is in an abnormal running state includes:

Determining overspeed running confidence and slow running confidence of the vehicle according to the vehicle abnormal running comprehensive probability and a preset vehicle abnormal running comprehensive probability threshold;

When the overspeed running confidence coefficient is detected to be larger than a preset overspeed running confidence coefficient threshold value, determining a first detection result that the vehicle is in an overspeed running state;

And when the slow running confidence coefficient is detected to be larger than a preset slow running confidence coefficient threshold value, determining a second detection result that the vehicle is in an overspeed running state.

Specifically, if the vehicle abnormal running comprehensive probability P is greater than a preset vehicle abnormal running comprehensive probability threshold value Ps, judging that the vehicle is running at overspeed/slow speed, and adding 1 to the overspeed confidence coefficient kH or the slow confidence coefficient kL; otherwise, the overspeed confidence kH or the slow confidence kL is decremented by 1.

Specifically, when the overspeed running confidence coefficient kH is detected to be larger than a preset overspeed running confidence coefficient threshold value ks1, judging that the vehicle is in overspeed running, and determining a first detection result that the vehicle is in an overspeed running state by carrying out overspeed warning on the vehicle; when the slow running confidence coefficient kL is detected to be larger than the preset slow running confidence coefficient threshold value ks2, judging that the vehicle is running slowly, and determining a second detection result that the vehicle is in an overspeed running state by slowly alarming the vehicle.

In one embodiment, when the detection result is that the vehicle is in an abnormal driving state, generating alarm information and sending the alarm information to a target terminal, where the alarm information includes:

When the detection result is detected to be a first detection result, overspeed alarm information is generated and sent to a target terminal;

And when the detection result is detected to be a second detection result, generating slow warning information and sending the slow warning information to the target terminal.

Specifically, when the detection result is detected as a first detection result, overspeed warning information including content such as a vehicle ID, vehicle position information, license plate information, vehicle type information, vehicle running speed, overspeed running of the vehicle and the like is generated and sent to the target terminal. Or when the detection result is detected to be the second detection result, generating slow warning information comprising the contents of the vehicle ID, the vehicle position information, the license plate information, the vehicle type information, the vehicle running speed, the vehicle running at a slow speed and the like, and sending the slow warning information to the target terminal. And broadcasting the overspeed or slow warning information to all vehicles on the current road section through the laser integrated antenna. Or each laser integrated antenna is set to be in communication connection with an external RSU, and the overspeed or slow warning information is sent to OBU equipment of all vehicles on the current road section based on the external RSU equipment.

In one embodiment, each of the laser integrated antennas comprises a built-in RSU;

the collecting vehicle fusion information of each vehicle comprises the following steps:

Determining vehicle track information of each vehicle through radar echo signals; the vehicle track information comprises an ID of a vehicle, a vehicle running speed, vehicle position information, a relative distance between the vehicle and the laser integrated antenna, a signal-to-noise ratio of the vehicle and license plate information;

Determining vehicle identity information of each vehicle through the built-in RSU; the vehicle identity information comprises the ID of the vehicle, the vehicle type information and license plate information;

and carrying out matching fusion processing on the vehicle track information and the vehicle identity information to obtain vehicle fusion information.

Specifically, a laser integrated antenna is set to send radar radio frequency signals according to a preset period, vehicle track information (including but not limited to an ID of a vehicle, a vehicle running speed, vehicle position information, a relative distance between the vehicle and the laser integrated antenna, a signal to noise ratio of the vehicle, a running direction and license plate information) of each vehicle is determined according to the detected radar echo signals, the vehicle identification information (including but not limited to the ID of the vehicle, the running direction, the vehicle type information and the license plate information) of each vehicle is acquired and obtained through communication between a built-in RSU and the vehicle OBU, and matching and fusing processing is carried out on the vehicle track information and the vehicle identification information based on the ID of the vehicle, the running direction, the license plate information and the like to obtain vehicle fusion information, so that one-to-one binding of the vehicle track and the vehicle identification information is realized.

According to the embodiment, the laser integrated antenna is used for collecting vehicle fusion information, the abnormal running speed threshold corresponding to the vehicle type and the lane of the vehicle is adaptively determined based on the vehicle fusion information, the comprehensive abnormal running probability of the vehicle is calculated, whether the vehicle is in the abnormal running detection result is determined, the corresponding abnormal running speed threshold is adaptively adjusted based on different vehicle types, different lanes and different environments, the influence of internal factors and external factors of the vehicle on the abnormal running detection result of the vehicle is reduced, and the accuracy and the stability of the abnormal running detection result of the vehicle are improved.

It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present application.

Corresponding to the method for detecting abnormal running of the adaptive vehicle described in the above embodiments, fig. 4 shows a block diagram of a device for detecting abnormal running of the adaptive vehicle according to an embodiment of the present application, where the device for detecting abnormal running of the adaptive vehicle is applied to laser integrated antennas, and communication connection is performed between every two adjacent laser integrated antennas in the running direction. For convenience of explanation, only portions relevant to the embodiments of the present application are shown.

Referring to fig. 4, the adaptive vehicle abnormal running detection apparatus 100 includes:

an information acquisition module 101 for acquiring vehicle fusion information of each vehicle; the vehicle fusion information comprises an ID of a vehicle, a vehicle running speed, vehicle position information, a relative distance between the vehicle and the laser integrated antenna, a signal-to-noise ratio of the vehicle, vehicle type information, license plate information and a running direction;

a threshold determining module 102, configured to determine an abnormal driving speed threshold corresponding to a lane and a vehicle type of each vehicle according to the vehicle fusion information; the abnormal driving speed threshold value comprises an overspeed threshold value and a slow speed threshold value;

the probability determining module 103 is used for calculating the abnormal running comprehensive probability of the vehicle according to the vehicle fusion information and the abnormal running speed threshold;

an anomaly detection module 104, configured to determine a detection result of whether the vehicle is in an abnormal driving state according to the comprehensive probability of abnormal driving of the vehicle;

And the alarm module 105 is used for generating alarm information and sending the alarm information to a target terminal when the detection result is that the vehicle is in an abnormal running state.

In one embodiment, the threshold determination module includes:

The parameter acquisition unit is used for acquiring system parameters; the system parameters comprise a transverse coefficient, a longitudinal frame number, a speed precision, a standard distance, a maximum signal-to-noise ratio, a longitudinal model standard deviation, a vehicle type initial overspeed threshold value corresponding to each vehicle type, a lane initial overspeed threshold value corresponding to each lane, a vehicle type initial slow speed threshold value corresponding to each vehicle type, a lane initial slow speed threshold value corresponding to each lane, a threshold value update coefficient, a transverse model standard deviation, a preset vehicle abnormal running comprehensive probability threshold value, a preset overspeed running confidence coefficient threshold value and a preset slow speed running confidence coefficient threshold value;

The information determining unit is used for determining a target lane and a target vehicle type of each vehicle according to the vehicle fusion information;

A threshold value determining unit, configured to determine a target lane initial overspeed threshold value and a target lane initial slowness threshold value corresponding to each target lane, and a target vehicle type initial overspeed threshold value and a target vehicle type initial slowness threshold value corresponding to each target vehicle type;

The overspeed coefficient calculating unit is used for calculating and determining an average overspeed coefficient of the vehicle according to the vehicle running speed of each vehicle, the initial overspeed threshold value of the target lane and the initial overspeed threshold value of the target vehicle type;

the slow coefficient calculation unit is used for calculating and determining an average slow coefficient of the vehicle according to the vehicle running speed of each vehicle, the initial slow threshold value of the target lane and the initial slow threshold value of the target vehicle type;

The first overspeed threshold value calculation unit is used for calculating a lane overspeed threshold value according to the average overspeed coefficient of the vehicle and the target lane overspeed threshold value;

The second super-threshold calculating unit is used for calculating the vehicle overspeed threshold according to the average overspeed coefficient of the vehicle and the target vehicle overspeed threshold;

the first slow threshold calculating unit is used for calculating a lane slow threshold according to the average slow coefficient of the vehicle and the target lane slow threshold;

the second slow threshold calculating unit is used for calculating a vehicle type slow threshold according to the average slow coefficient of the vehicle and the target vehicle type slow threshold;

the threshold value determining unit is used for selecting an overspeed threshold value and a slow threshold value which meet preset conditions from the lane overspeed threshold value, the vehicle type overspeed threshold value, the lane slow threshold value and the vehicle type slow threshold value.

In one embodiment, the threshold determining unit includes:

The first threshold value determining subunit is used for selecting the lane overspeed threshold value as the overspeed threshold value meeting a preset condition when the lane overspeed threshold value is detected to be smaller than or equal to the vehicle type overspeed threshold value;

The second threshold value determining subunit is used for selecting the lane overspeed threshold value as the overspeed threshold value meeting a preset condition when the overspeed threshold value of the vehicle type is detected to be smaller than or equal to the lane overspeed threshold value;

A third threshold determining subunit, configured to select, when the lane slow threshold is detected to be greater than or equal to the vehicle type slow threshold, the lane slow threshold as a slow threshold that meets a preset condition;

And the fourth threshold value determining subunit is used for selecting the vehicle type slow speed threshold value as the slow speed threshold value meeting the preset condition when the vehicle type slow speed threshold value is detected to be larger than or equal to the lane slow speed threshold value.

In one embodiment, the probability determination module includes:

a first probability calculation unit configured to determine a lateral abnormal running probability of the vehicle according to a running speed of the vehicle and the abnormal running speed threshold;

a second probability calculation unit for determining a motion smoothing probability of the vehicle according to a relative distance between the vehicle and the laser integrated antenna and the signal-to-noise ratio;

and the third probability calculation unit is used for calculating the vehicle abnormal running comprehensive probability according to the transverse abnormal running probability and the motion smoothing probability.

In one embodiment, the first probability calculation unit includes:

The first probability calculation subunit is used for inputting the vehicle running speed into a first transverse normal distribution model to obtain transverse overspeed running probability when detecting that the vehicle running speed of the vehicle is greater than the overspeed threshold value; the standard deviation of the first transverse normal distribution model is the standard deviation of the transverse model, and the mean value is the overspeed threshold value;

The second probability calculation subunit is used for inputting the vehicle running speed into a second transverse normal distribution model to obtain transverse slow running probability when the vehicle running speed of the vehicle is detected to be smaller than the slow threshold; and the standard deviation of the second transverse normal distribution model is the standard deviation of the transverse model, and the average value is the slow threshold value.

In one embodiment, the second probability calculation unit includes:

a data acquisition subunit, configured to acquire a historical vehicle running speed of the longitudinal frame number;

the partitioning subunit is used for partitioning the historical vehicle running speed based on the speed precision to obtain a plurality of speed intervals;

the aroma concentration entropy calculating subunit is used for calculating to obtain the speed expansion aroma concentration entropy according to the relative distance between the vehicle and the laser integrated antenna, the standard distance, the average value of the signal to noise ratio of the vehicle running speed of each vehicle in each speed interval and the maximum signal to noise ratio;

The third probability calculation subunit is used for inputting the speed expansion aromatic entropy into the longitudinal normal distribution model to obtain motion smoothing probability; the mean value of the longitudinal normal distribution model is zero, and the standard deviation is the standard deviation of the longitudinal model.

In one embodiment, the anomaly detection module includes:

The confidence coefficient determining unit is used for determining overspeed driving confidence coefficient and slow driving confidence coefficient of the vehicle according to the vehicle abnormal driving comprehensive probability and a preset vehicle abnormal driving comprehensive probability threshold value;

the first abnormality detection unit is used for determining a first detection result of the vehicle in an overspeed running state when the overspeed running confidence is detected to be larger than a preset overspeed running confidence threshold value;

and the second abnormality detection unit is used for determining a second detection result of the overspeed running state of the vehicle when the slow running confidence coefficient is detected to be larger than a preset slow running confidence coefficient threshold value.

In one embodiment, the alert module includes:

The first alarm unit is used for generating overspeed alarm information and sending the overspeed alarm information to the target terminal when the detection result is detected to be a first detection result;

and the second alarm unit is used for generating slow alarm information and sending the slow alarm information to the target terminal when the detection result is detected to be a second detection result.

The information acquisition module comprises:

The first information acquisition unit is used for determining vehicle track information of each vehicle through radar echo signals; the vehicle track information comprises an ID of a vehicle, a vehicle running speed, vehicle position information, a relative distance between the vehicle and the laser integrated antenna, a signal-to-noise ratio of the vehicle and license plate information;

The second information acquisition unit is used for determining the vehicle identity information of each vehicle through the built-in RSU; the vehicle identity information comprises the ID of the vehicle, the vehicle type information and license plate information;

and the information fusion processing unit is used for carrying out matching fusion processing on the vehicle track information and the vehicle identity information to obtain vehicle fusion information.

It should be noted that, because the content of information interaction and execution process between the above devices/units is based on the same concept as the method embodiment of the present application, specific functions and technical effects thereof may be referred to in the method embodiment section, and will not be described herein.

Fig. 5 is a schematic structural diagram of a terminal device according to this embodiment. As shown in fig. 5, the terminal device 5 of this embodiment includes: at least one processor 50 (only one is shown in fig. 5), a memory 51, a computer program 52 stored in the memory 51 and executable on the at least one processor 50, and a radio frequency module 53, the processor 50 implementing the steps in any of the various adaptive vehicle abnormal driving detection method embodiments described above when executing the computer program 52.

The terminal device 5 may be a computing device such as a desktop computer, a notebook computer, a palm computer, a cloud server, etc. The terminal device may include, but is not limited to, a processor 50, a memory 51. It will be appreciated by those skilled in the art that fig. 5 is merely an example of the terminal device 5 and is not meant to be limiting as the terminal device 5, and may include more or fewer components than shown, or may combine certain components, or different components, such as may also include input-output devices, network access devices, etc.

The radio frequency module 52 may in some embodiments be a transmitting and receiving module of radio frequency signals in the terminal device 5.

The Processor 50 may be a central processing unit (Central Processing Unit, CPU), the Processor 50 may also be other general purpose processors, digital signal processors (DIGITAL SIGNAL processors, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), off-the-shelf Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 51 may in some embodiments be an internal storage unit of the terminal device 5, such as a hard disk or a memory of the terminal device 5. The memory 51 may in other embodiments also be an external storage device of the terminal device 5, such as a plug-in hard disk provided on the terminal device 5, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD) or the like. Further, the memory 51 may also include both an internal storage unit and an external storage device of the terminal device 5. The memory 51 is used for storing an operating system, application programs, boot loader (BootLoader), data, other programs, etc., such as program codes of the computer program. The memory 51 may also be used to temporarily store data that has been output or is to be output.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, the specific names of the functional units and modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.

Embodiments of the present application also provide a computer readable storage medium storing a computer program which, when executed by a processor, implements steps for implementing the various method embodiments described above.

Embodiments of the present application provide a computer program product which, when run on a mobile terminal, causes the mobile terminal to perform steps that enable the implementation of the method embodiments described above.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present application may implement all or part of the flow of the method of the above embodiments, and may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include at least: any entity or device capable of carrying computer program code to a photographing device/terminal apparatus, recording medium, computer Memory, read-Only Memory (ROM), random access Memory (RAM, random Access Memory), electrical carrier signals, telecommunications signals, and software distribution media. Such as a U-disk, removable hard disk, magnetic or optical disk, etc. In some jurisdictions, computer readable media may not be electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.

In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus/network device and method may be implemented in other manners. For example, the apparatus/network device embodiments described above are merely illustrative, e.g., the division of the modules or units is merely a logical functional division, and there may be additional divisions in actual implementation, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via interfaces, devices or units, which may be in electrical, mechanical or other forms.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of 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.

The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.

Claims

1. The self-adaptive vehicle abnormal running detection method is characterized by being applied to laser integrated antennas, and being in communication connection between every two adjacent laser integrated antennas in the running direction;

When the detection result is that the vehicle is in an abnormal running state, generating alarm information and sending the alarm information to a target terminal;

the determining the abnormal running speed threshold corresponding to the lanes and the vehicle types of each vehicle according to the vehicle fusion information comprises the following steps:

Selecting an overspeed threshold and a slow threshold meeting preset conditions from the lane overspeed threshold, the vehicle type overspeed threshold, the lane slow threshold and the vehicle type slow threshold;

the calculating the vehicle abnormal running comprehensive probability according to the vehicle fusion information and the abnormal running speed threshold value comprises the following steps:

calculating to obtain the comprehensive probability of abnormal running of the vehicle according to the horizontal abnormal running probability and the motion smoothing probability;

the determining the transverse abnormal driving probability of the vehicle according to the driving speed of the vehicle and the abnormal driving speed threshold value comprises the following steps:

When the vehicle running speed of the vehicle is detected to be smaller than the slow threshold value, inputting the vehicle running speed into a second transverse normal distribution model to obtain transverse slow running probability; the standard deviation of the second transverse normal distribution model is the standard deviation of the transverse model, and the average value is the slow threshold value;

the determining the motion smoothing probability of the vehicle according to the relative distance between the vehicle and the laser integrated antenna and the signal-to-noise ratio comprises the following steps:

2. The method for detecting abnormal driving of an adaptive vehicle according to claim 1, wherein selecting an overspeed threshold value and a slowness threshold value satisfying a preset condition from among the lane overspeed threshold value, the vehicle type overspeed threshold value, the lane slowness threshold value, and the vehicle type slowness threshold value comprises:

Or when the overspeed threshold value of the vehicle type is detected to be smaller than or equal to the overspeed threshold value of the lane, selecting the overspeed threshold value of the vehicle type as the overspeed threshold value meeting the preset condition;

3. The adaptive vehicle abnormal-running detection method according to claim 1, wherein the determination of the detection result of whether the vehicle is in an abnormal-running state based on the vehicle abnormal-running integrated probability includes:

4. The adaptive vehicle abnormal driving detection method according to claim 1, wherein the generating and transmitting warning information to a target terminal when the detection result is that the vehicle is in an abnormal driving state, comprises:

5. The adaptive vehicle abnormal driving detection method according to any one of claims 1 to 4, wherein each of the laser integrated antennas includes a built-in RSU;

6. An adaptive vehicle abnormal running detection device is characterized by being applied to laser integrated antennas, and being in communication connection between every two adjacent laser integrated antennas in the running direction;

the adaptive vehicle abnormal running detection device includes:

The alarm module is used for generating alarm information and sending the alarm information to a target terminal when the detection result is that the vehicle is in an abnormal running state;

The threshold determination module includes:

The number acquisition unit is used for acquiring system parameters; the system parameters comprise a transverse coefficient, a longitudinal frame number, a speed precision, a standard distance, a maximum signal-to-noise ratio, a longitudinal model standard deviation, a vehicle type initial overspeed threshold value corresponding to each vehicle type, a lane initial overspeed threshold value corresponding to each lane, a vehicle type initial slow speed threshold value corresponding to each vehicle type, a lane initial slow speed threshold value corresponding to each lane, a threshold value update coefficient, a transverse model standard deviation, a preset vehicle abnormal running comprehensive probability threshold value, a preset overspeed running confidence coefficient threshold value and a preset slow speed running confidence coefficient threshold value;

the threshold value determining unit is used for selecting an overspeed threshold value and a slow threshold value which meet preset conditions from the lane overspeed threshold value, the vehicle type overspeed threshold value, the lane slow threshold value and the vehicle type slow threshold value;

a probability determination module comprising:

The third probability calculation unit is used for calculating the vehicle abnormal running comprehensive probability according to the transverse abnormal running probability and the motion smoothing probability;

the first probability calculation unit includes:

The second probability calculation subunit is used for inputting the vehicle running speed into a second transverse normal distribution model to obtain transverse slow running probability when the vehicle running speed of the vehicle is detected to be smaller than the slow threshold; the standard deviation of the second transverse normal distribution model is the standard deviation of the transverse model, and the average value is the slow threshold value;

The second probability calculation unit includes:

7. A terminal device comprising a radio frequency module, a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1 to 5 when executing the computer program.

8. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the method according to any one of claims 1 to 5.