Abnormal vehicle detection method, device and equipment and storage medium

Abstract

The embodiment of the invention relates to the technical field of intelligent driving, and discloses an abnormal vehicle detection method, device and equipment and a storage medium, and the method comprises the steps: obtaining vehicle driving video data, and obtaining the driving track of a vehicle according to the vehicle driving video data; calculating the speed and acceleration of the vehicle according to the driving track of the vehicle and the sampling frequency of the data frame; judging whether the vehicle is abnormally driven according to the driving track and the acceleration of the vehicle; and if it is judged that the vehicle runs abnormally, reminding the vehicle and surrounding vehicles. According to the method disclosed by the embodiment of the invention, the abnormal driving vehicle is judged according to the vehicle driving video data, and the driver and the surrounding vehicles are reminded in various modes, so that the coverage rate of dangerous driving behavior interference reminding and danger avoidance is greatly improved, traffic accidents, casualties and loss are reduced, and the traffic safety is improved.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of intelligent driving technology, and specifically to an abnormal vehicle detection method, device, equipment and storage medium. Background Art

[0002] In recent years, with the rapid development of the economy, more and more families choose cars as their means of transportation. During the driving process, especially on highways, the car is at a high speed, and the driving state of the car is often affected by various factors, causing the vehicle to be in an abnormal driving state. In the long run, it also causes a series of traffic problems, thus seriously threatening people's lives and safety. In particular, there are more and more vehicle accidents caused by vehicle failures or driver fatigue.

[0003] If we can detect and discover abnormal driving behaviors of vehicles on the road in time, eliminate abnormal behaviors through effective measures, and inform the following vehicles of relevant information of abnormal behaviors, we can effectively reduce and avoid the occurrence of traffic accidents. Therefore, timely and effective detection of abnormal vehicle behaviors is of great significance to reducing the incidence of traffic accidents, saving lives and property losses, and improving traffic safety.

[0004] In the prior art, the following technologies are usually used to detect abnormal vehicles:

[0005] 1. Use V2X technology to broadcast the vehicle's own driving speed, acceleration, driving direction, heading angle, location information, etc. After the V2X modules of surrounding vehicles receive the message, they can combine their own vehicle location and driving speed direction to detect and determine whether there is any danger with the vehicle in front.

[0006] 2. A camera is installed in front of the driver of the vehicle, and DMS technology is used to detect the driver's driving behavior and physiological state through visual tracking, target detection, motion recognition and other technologies. When the driver is in dangerous situations such as fatigue, distraction, making a phone call, smoking, etc., an alarm will be sounded within the system set time to avoid accidents.

[0007] However, in the above scheme, V2X technology is used to avoid dangerous driving behaviors, but the penetration rate of V2X installation in vehicles is not high. Many vehicles cannot send vehicle status information through V2X broadcast, and cannot detect abnormal driving of the vehicle and surrounding vehicles, so that the vehicle cannot stay away from danger in time; DMS technology is used to identify the driver's dangerous driving behavior. DMS technology can only detect driving behaviors in dangerous situations such as driver fatigue, distraction, making phone calls, smoking, etc., and cannot detect driving behaviors caused by vehicle failures, nor can it actively notify surrounding vehicles to avoid danger. Summary of the invention

[0008] In order to solve the problems in the prior art of using V2X technology to avoid dangerous driving behaviors, such as the low penetration rate of vehicle V2X installation, the inability to detect abnormal driving of the vehicle and surrounding vehicles, and the inability of the vehicle to stay away from danger in time, the embodiments of the present invention provide an abnormal vehicle detection method, device, equipment and storage medium.

[0009] According to an object of an embodiment of the present invention, a method for detecting an abnormal vehicle is provided, comprising the following steps:

[0010] Acquire vehicle driving video data, and acquire the vehicle's driving trajectory based on the vehicle driving video data;

[0011] Calculate the acceleration of the vehicle according to the vehicle's driving trajectory and the sampling frequency of the data frame;

[0012] Determine whether the vehicle is moving abnormally based on its driving trajectory and acceleration;

[0013] If the vehicle is judged to be in abnormal driving, the vehicle and surrounding vehicles will be reminded.

[0014] In some optional implementations, determining whether the vehicle is driving abnormally specifically includes:

[0015] Determine whether the vehicle is changing lanes abnormally based on the vehicle's driving trajectory;

[0016] If so, judging whether the vehicle is accelerating or decelerating abnormally according to the acceleration of the vehicle;

[0017] If so, it is determined that the vehicle is in abnormal driving.

[0018] In some optional implementations, judging whether the vehicle is changing lanes abnormally according to the driving trajectory of the vehicle specifically includes:

[0019] According to the driving trajectory of the vehicle, determine whether multiple vehicles identified at multiple times change lanes;

[0020] If a vehicle changes lanes continuously in different lanes and there are no other vehicles in between when changing lanes;

[0021] Detect whether the vehicle turns on the turn signal during the continuous lane change process;

[0022] If not, it is determined that the vehicle is changing lanes abnormally.

[0023] In some optional implementations, determining whether the vehicle is accelerating or decelerating abnormally specifically includes:

[0024] Determining whether the acceleration of the vehicle is greater than a preset threshold;

[0025] If so, determine whether the current distance difference is less than the safety distance;

[0026] If so, it is determined that the vehicle is in abnormal acceleration or deceleration.

[0027] In some optional implementations, the calculation of the vehicle's driving trajectory specifically includes:

[0028] Continuously extracting multiple frames of vehicle driving image data from vehicle driving video data;

[0029] Identify and analyze multiple vehicles within its range and their location information based on each frame of vehicle driving image data;

[0030] The vehicle's driving trajectory is obtained based on the acquired multiple frames of continuous information about multiple vehicles and their positions.

[0031] In some optional implementations, the calculation of the vehicle's acceleration specifically includes:

[0032] Extract the location information of the vehicle at different times;

[0033] Calculate the position distance difference between two moments of the vehicle based on the position information of the vehicle at different moments;

[0034] Calculate the speed of the vehicle based on the position distance difference between the vehicle at two times and the time difference between the vehicle at two times;

[0035] The acceleration of the vehicle is calculated based on the speed of the vehicle calculated at the current moment and the speed of the vehicle calculated at the previous moment.

[0036] In some optional implementations, the vehicle and surrounding vehicles are reminded, specifically including:

[0037] Submit the dangerous driving information of the abnormally moving vehicle to the road management service backend so that the road management service backend can remind the driver of the abnormally moving vehicle;

[0038] And / or, broadcast the dangerous driving information of the abnormally moving vehicle to surrounding vehicles through the RSU to remind surrounding vehicles to avoid and stay away from danger;

[0039] And / or, the dangerous driving information of the abnormally moving vehicle is synchronized to the navigation system, and the navigation system marks the location of the abnormally moving vehicle as a dangerous area reminder, and reminds other vehicles to avoid and stay away from the danger.

[0040] According to another object of an embodiment of the present invention, there is provided an abnormal vehicle detection and safety reminder device, comprising:

[0041] A data acquisition module, used to obtain vehicle driving video data;

[0042] A calculation module, used to calculate the vehicle's driving trajectory based on the vehicle's driving video data and to calculate the vehicle's speed and acceleration based on the vehicle's driving trajectory;

[0043] A judgment module is used to judge whether the vehicle is changing lanes abnormally according to the vehicle's driving trajectory, and to judge whether the vehicle is accelerating or decelerating abnormally according to the vehicle's acceleration, and further to judge whether the vehicle is in abnormal driving;

[0044] A first reminder module, used to provide safety reminders to the driver of the vehicle in abnormal driving;

[0045] The second reminder module is used to provide safety reminders to surrounding vehicles.

[0046] According to another object of an embodiment of the present invention, there is provided an abnormal vehicle detection and safety reminder device, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other through the communication bus;

[0047] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the operation of the abnormal vehicle detection method as described above.

[0048] According to another object of an embodiment of the present invention, a computer-readable storage medium is provided, on which instructions are stored. When the instructions are executed by a processor, the steps of the abnormal vehicle detection method as described above are implemented.

[0049] Compared with the prior art, the present invention has the following advantages:

[0050] The present invention provides an abnormal vehicle detection method, which calculates the vehicle's driving trajectory and acceleration based on vehicle driving video data, and then determines whether the vehicle is driving abnormally based on the vehicle's driving trajectory and acceleration. After the abnormally driving vehicle is determined, the driver and surrounding vehicles are reminded in a variety of ways, which greatly improves the coverage of dangerous driving behavior interference reminders and danger avoidance, reduces traffic accidents, reduces casualties and losses, and improves traffic safety.

[0051] The above description is only an overview of the technical solution of the embodiment of the present invention. In order to more clearly understand the technical means of the embodiment of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the embodiment of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The accompanying drawings are only used to illustrate the embodiments and are not to be considered as limiting the present invention. In addition, the same reference symbols are used to represent the same components throughout the accompanying drawings. In the accompanying drawings:

[0053] Figure 1 A schematic diagram of a process of detecting an abnormal vehicle provided by an embodiment of the present invention is shown;

[0054] Figure 2 A schematic diagram of a vehicle lane change structure in an abnormal vehicle detection method provided by an embodiment of the present invention is shown;

[0055] Figure 3 A schematic diagram of the structure of an abnormal vehicle detection device provided by an embodiment of the present invention is shown;

[0056] Figure 4 A schematic structural diagram of an abnormal vehicle detection device provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0057] Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0058] In order to solve the abnormal vehicle detection method in the prior art, this embodiment uses V2X technology to avoid dangerous driving behaviors. There are problems such as the low penetration rate of vehicle V2X installation, many vehicles cannot send vehicle status information through V2X broadcast, and abnormal driving of the vehicle and surrounding vehicles cannot be detected, so that the vehicle cannot stay away from danger in time; DMS technology is used to identify the driver's dangerous driving behavior. There is a problem that DMS technology can only detect driving behaviors in dangerous situations such as driver fatigue, distraction, making phone calls, smoking, etc., and cannot detect driving behaviors caused by vehicle failures, nor can it actively notify surrounding vehicles to avoid danger. An abnormal vehicle detection method is provided.

[0059] Figure 1 A flow chart of an abnormal vehicle detection method provided by an embodiment of the present invention is shown. The abnormal vehicle detection method is mainly used to detect dangerous vehicles on highways, thereby reminding vehicles to avoid dangers, thereby improving the driving safety of vehicles on highways and reducing the accident rate.

[0060] This embodiment provides a method for detecting abnormal vehicles. Figure 1 As shown, the following steps are included:

[0061] S10. Acquire vehicle driving video data, and acquire the vehicle's driving trajectory based on the vehicle driving video data.

[0062] In this step, the vehicle driving video data is the vehicle driving video data on the highway collected by the camera on the highway. Then the camera sends the collected vehicle driving video data to MEC via Ethernet, and MEC processes the vehicle driving video data to obtain the vehicle's driving trajectory.

[0063] S20. Calculate the acceleration of the vehicle according to the driving trajectory of the vehicle and the sampling frequency of the data frame.

[0064] In this step, the vehicle's driving trajectory obtained through the above steps can extract the vehicle's position information at multiple consecutive moments, calculate the vehicle's speed in combination with the sampling frequency of the data frame of the vehicle's driving video data, and then calculate the vehicle's acceleration based on the calculated vehicle speed.

[0065] In addition, in this embodiment, it should be clarified that acceleration is the ratio of the change in velocity to the time taken for this change, that is, Δv / Δt, and the unit is meter per second squared. Acceleration is a vector, and its direction is the same as the direction of the change in the velocity of the object and the direction of the resultant external force. When the acceleration and velocity are in the same direction, the value of acceleration is positive, indicating that the vehicle is accelerating; when they are in opposite directions, the value of acceleration is negative, indicating that the vehicle is decelerating.

[0066] In some literature, negative acceleration is named deceleration, and deceleration is a physics term published in 2019.

[0067] S30. Determine whether the vehicle is moving abnormally based on the vehicle's moving trajectory and acceleration.

[0068] In this step, it can be determined whether the vehicle is changing lanes abnormally based on the vehicle's driving trajectory obtained above.

[0069] If so, it can be determined whether the vehicle is accelerating or decelerating abnormally based on the acceleration of the vehicle obtained as described above.

[0070] Finally, by judging that the vehicle is in abnormal lane change and abnormal acceleration and deceleration, it is determined that the vehicle is driving abnormally.

[0071] S40. If it is determined that the vehicle is in abnormal driving, a reminder is given to the vehicle and surrounding vehicles.

[0072] In this step, when it is determined that the vehicle is in abnormal driving, MEC is used to provide safety reminders to the vehicle itself and surrounding vehicles.

[0073] The present embodiment provides an abnormal vehicle detection method, which obtains vehicle driving video data through a camera on the highway, calculates the vehicle's driving trajectory and acceleration based on the vehicle's driving video data, and then determines whether the vehicle is driving abnormally based on the vehicle's driving trajectory and acceleration. After the abnormally driving vehicle is determined, the driver and surrounding vehicles are reminded in a variety of ways, thereby greatly improving the coverage of dangerous driving behavior interference reminders and danger avoidance, reducing traffic accidents, reducing casualties and losses, and improving traffic safety.

[0074] In some optional embodiments, the calculation process of the vehicle's driving trajectory is optimized.

[0075] The calculation of the vehicle's driving trajectory specifically includes:

[0076] Continuously extract multiple frames of vehicle driving image data from the vehicle driving video data.

[0077] This step is specifically as follows: MEC performs image analysis on the vehicle driving video data and detects continuous frame image data in the vehicle driving video data.

[0078] Based on each frame of vehicle driving image data, multiple vehicles within its range and their location information are identified and analyzed.

[0079] This step specifically includes: performing identification and analysis on each frame of vehicle driving image data, thereby identifying and analyzing multiple vehicles and their position information within the range of each frame of vehicle driving image data.

[0080] The vehicle's travel trajectory is obtained based on multiple vehicles and their position information in the acquired continuous multiple-frame vehicle travel image data.

[0081] This step is specifically as follows: combining the multiple vehicles and their position information identified from each frame of vehicle driving image data, multiple vehicles and their position information in multiple consecutive frames of vehicle driving image data can be obtained, and then the vehicle's driving trajectory can be obtained.

[0082] In this step, the vehicle's location information includes the lane and longitude and latitude of the vehicle.

[0083] In this embodiment, the calculation process of the vehicle's driving trajectory is illustrated by way of example:

[0084] The vehicle driving image data at time t+1 is obtained, and based on the vehicle driving image data, the vehicle A1 and the position information B1(i1,x1,y1) of vehicle A1, the vehicle A2 and the position information B2(i2,x2,y2) of vehicle A2, the vehicle A3 and the position information B3(i3,x3,y3), and the vehicle A4 and the position information B4(i4,x4,y4) within its range are identified and analyzed.

[0085] See Table 1 below for details

[0086]

[0087]

[0088] The vehicle driving image data at time t+2 is obtained, and based on the vehicle driving image data, the vehicle A1 and the position information B1(i1,x1,y1) of vehicle A1, the vehicle A2 and the position information B2(i2,x2,y2) of vehicle A2, the vehicle A3 and the position information B3(i3,x3,y3), and the vehicle A4 and the position information B4(i4,x4,y4) within its range are identified and analyzed.

[0089] See Table 2 below for details.

[0090] time vehicle Lane longitude Dimensions Turn signal on t+2 A1 i1 x1 y1 1 t+2 A2 i 2 x2 y2 1 t+2 A3 i3 x3 y3 0 t+2 A4 i4 x4 y4 0 …… …… …… …… …… ……

[0091] The vehicle driving image data at time t+n is obtained, and based on the vehicle driving image data, the vehicle A1 and the position information B1(i1,x1,y1) of vehicle A1, the vehicle A2 and the position information B2(i2,x2,y2) of vehicle A2, the vehicle A3 and the position information B3(i3,x3,y3), and the vehicle A4 and the position information B4(i4,x4,y4) within its range are identified and analyzed.

[0092] See Table 3 below for details

[0093] time vehicle Lane longitude Dimensions Turn signal on t+n A1 i1 x1 y1 1 t+n A2 i 2 x2 y2 1 t+n A3 i3 x3 y3 0 t+n A4 i4 x4 y4 0 …… …… …… …… …… ……

[0094] The number of vehicles identified in the above-mentioned multiple frames of vehicle driving image data may be the same or different, and the vehicle identified in a subsequent frame of vehicle driving image data is not necessarily the same as the vehicle identified in a previous frame of vehicle driving image data.

[0095] Then, the driving trajectory of a certain vehicle is obtained by identifying the vehicles A1, A2, A3, A4 / or An and their position information in the multi-frame vehicle driving image data.

[0096] In some optional embodiments, the specific calculation process of the vehicle's acceleration is optimized.

[0097] In this embodiment, the calculation of the vehicle's acceleration specifically includes:

[0098] Extract the vehicle's location information at different times.

[0099] This step can be understood as: based on the acquisition process of the driving trajectory of the above-mentioned vehicle, a vehicle is designated as a target vehicle, and then the position information of the vehicle at different times is extracted.

[0100] The position distance difference between two moments of the vehicle is calculated based on the position information of the vehicle at different moments.

[0101] This step can be understood as: based on the position information of the vehicle at different times extracted in the above step, calculating the position distance difference of the vehicle between two times.

[0102] The speed of the vehicle is calculated based on the position distance difference between the vehicle at two times and the time difference between the vehicle at two times.

[0103] This step can be understood as: based on the position distance difference between the two moments of the vehicle calculated in the above step, then calculating the time difference between the two moments of the vehicle, and calculating the speed of the vehicle through the position distance difference and the time difference.

[0104] The acceleration of the vehicle is calculated based on the speed of the vehicle calculated at the current moment and the speed of the vehicle calculated at the previous moment.

[0105] This step can be understood as: calculating the acceleration of the vehicle through the speeds at two adjacent moments.

[0106] In some optional embodiments, the abnormal lane change judgment process of the vehicle is optimized.

[0107] In this embodiment, determining whether the vehicle is changing lanes abnormally specifically includes:

[0108] According to the driving trajectory of the vehicle, it is determined whether multiple vehicles identified at multiple moments change lanes.

[0109] This step can be understood as: based on the calculation process of the driving trajectory of the above-mentioned vehicle, multiple vehicles A1, A2, A3... and their position information are identified, and then it is determined whether the vehicle changes driving in different lanes according to the vehicle's position information.

[0110] If a vehicle changes lanes continuously in different lanes and there are no other vehicles in between when changing lanes.

[0111] This step can be understood as follows: Assume that vehicle A1, A2 or A3 changes from lane i1 to lane i2 and then from lane i2 to i1, and when vehicle A1, A2 or A3 changes from lane i1 to lane i2 and from lane i2 to lane i1, there is no other vehicle in the middle of the corresponding time period, see Figure 2 shown.

[0112] Detect whether the vehicle turns on the turn signal during continuous lane changes.

[0113] This step can be understood as: detecting whether the turn signal of vehicle A1, A2 or A3 is turned on during the process of changing from lane i1 to lane i2 and then from lane i2 to i1.

[0114] If not, it is determined that the vehicle is changing lanes abnormally.

[0115] This step can be understood as: when the vehicle A1, A2 or A3 changes from lane i1 to lane i2 and then from lane i2 to i1 without turning on the turn signal, it is determined that the vehicle A1, A2 or A3 is changing lanes abnormally.

[0116] In the above steps, the abnormal lane change is not limited to the above-mentioned vehicle changing from lane i1 to lane i2 and then from lane i2 to i1, and there are no other vehicles in the middle of the vehicle's lane change curve. The abnormal lane change can also be the vehicle changing from lane i1 to lane i3 and then from lane i3 to i1, and there are no other vehicles in the middle of the vehicle's lane change curve; at the same time, the vehicle does not turn on the turn signal during the lane change process.

[0117] In some optional embodiments, the abnormal acceleration and deceleration process of the vehicle is optimized.

[0118] In this embodiment, determining whether the vehicle is accelerating or decelerating abnormally specifically includes:

[0119] Determine whether the vehicle's acceleration α is greater than a preset threshold.

[0120] If so, determine whether the current distance difference is less than the safety distance.

[0121] If so, it is determined that the vehicle is in abnormal acceleration or deceleration.

[0122] For example, when the vehicle accelerates, that is, the acceleration of the vehicle is in the same direction as the speed, the value of acceleration α is positive, and it is determined whether the acceleration α of the vehicle is greater than a preset threshold. If so, it is determined whether the current distance difference is less than the safety distance. If so, it is determined that the vehicle is in abnormal acceleration.

[0123] In some optional embodiments, when the value of acceleration α is negative, that is, the vehicle decelerates and the acceleration of the vehicle is opposite to the direction of the speed, at this time, it is determined whether the acceleration α of the vehicle is greater than a preset threshold. If so, it is determined whether the current distance difference is greater than the safety distance. If so, it is determined that the vehicle is in abnormal deceleration.

[0124] If the vehicle is in abnormal acceleration or abnormal deceleration, it is determined that the vehicle is in abnormal acceleration or deceleration.

[0125] In the above steps, the distance difference refers to the distance between two adjacent vehicles, and the safety distance can be understood as the safe braking distance.

[0126] Through the above steps, it can be determined whether the vehicle is in abnormal acceleration or deceleration.

[0127] Based on the above judgment, the vehicle is in abnormal lane change and the vehicle is in abnormal acceleration and deceleration, and it is determined that the vehicle is in abnormal driving.

[0128] In some optional embodiments, after determining that the vehicle is in abnormal driving, the safety reminder process of the vehicle and surrounding vehicles is also optimized.

[0129] In this embodiment, the reminder of the vehicle and surrounding vehicles specifically includes:

[0130] The dangerous driving information of the vehicle in abnormal driving is submitted to the road management service background so that the road management service background can remind the driver of the vehicle in abnormal driving.

[0131] Specifically, when an abnormally driven vehicle is detected, MEC uploads the dangerous driving information of the vehicle to the highway management service backend. The highway management service backend automatically searches for the driver's phone number based on the vehicle license plate information, and intelligently dials the phone to remind the driver to take safety measures.

[0132] Among them, vehicle dangerous driving information includes vehicle number, vehicle location, dangerous driving type, etc.

[0133] And / or, the dangerous driving information of the abnormally moving vehicle is broadcast to surrounding vehicles through the RSU to remind the surrounding vehicles to avoid and stay away from danger.

[0134] Specifically: MEC broadcasts the dangerous driving information of the vehicle to the surrounding vehicles through RSU. The surrounding vehicles equipped with OBU modules can avoid and stay away from danger after receiving the RSU broadcast message.

[0135] And / or, synchronize the dangerous driving information of the abnormally moving vehicle to the navigation system, and the navigation system will mark the location of the abnormally moving vehicle as a dangerous area reminder, and remind other vehicles to avoid and stay away from the danger.

[0136] Specifically: MEC synchronizes the vehicle's dangerous driving information to the navigation, and the navigation marks the location of the dangerously driven vehicle as a dangerous area reminder, reminding other vehicles to avoid and stay away from danger.

[0137] This embodiment provides an abnormal vehicle detection method, which detects dangerous driving vehicles through cameras on the highway in combination with MEC, and reminds the driver and surrounding vehicles in various ways, thereby greatly improving the coverage of dangerous driving behavior interference reminders and danger avoidance, reducing traffic accidents, reducing casualties and losses, and improving traffic safety.

[0138] The abnormal vehicle detection in this implementation can not only cover dangerous driving such as S-shaped driving caused by driving fatigue and distraction, abnormal acceleration and deceleration, but also detect abnormal driving caused by vehicle failure. It improves the detection rate of dangerous driving behavior and further improves traffic safety.

[0139] In some optional embodiments, the embodiments of the present invention further disclose an abnormal vehicle detection and safety reminder device.

[0140] Figure 3 A schematic structural diagram of an abnormal vehicle detection and safety reminder device provided in this embodiment is shown.

[0141] like Figure 3 As shown, the abnormal vehicle detection and safety reminder device includes: a data acquisition module 100, a calculation module 200, a judgment module 300, a first reminder module 400 and a second reminder module 500. The data acquisition module 100 is communicatively connected to the calculation module 200, the calculation module 200 is communicatively connected to the judgment module 300, and the judgment module 300 is communicatively connected to the first reminder module 400 and the second reminder module 500 respectively.

[0142] The data acquisition module 100 is used to obtain vehicle driving video data on the highway.

[0143] The data acquisition module 100 includes but is not limited to cameras installed on the highway.

[0144] The calculation module 200 is used to calculate the vehicle's driving trajectory based on the vehicle driving video data and to calculate the vehicle's speed and acceleration based on the vehicle's driving trajectory.

[0145] The calculation module 200 includes but is not limited to MEC. MEC recognizes and calculates the vehicle driving video data collected by the data collection module 100, thereby calculating the vehicle's driving trajectory, and calculates the speed and acceleration of the scattered vehicle according to the vehicle's driving trajectory.

[0146] The specific calculation process of the calculation module 200 calculating the vehicle's driving trajectory, vehicle speed and acceleration, refer to the calculation process of the vehicle's driving trajectory, vehicle speed and acceleration in the above-mentioned abnormal vehicle detection method, which will not be repeated in this embodiment.

[0147] The judgment module 300 is used to judge whether the vehicle is changing lanes abnormally according to the vehicle's driving trajectory, and to judge whether the vehicle is accelerating or decelerating abnormally according to the vehicle's acceleration, and further to judge whether the vehicle is in abnormal driving.

[0148] The judgment module 300 includes but is not limited to MEC. MEC judges whether the vehicle is changing lanes abnormally according to the vehicle's driving trajectory, and judges whether the vehicle is accelerating or decelerating abnormally according to the calculated acceleration of the vehicle. When the vehicle is in abnormal lane change and abnormal acceleration or deceleration, the vehicle is judged to be an abnormal driving vehicle.

[0149] The specific judgment process of the judgment module 300 in judging whether the vehicle is abnormally changing lanes, the specific judgment process in judging whether the vehicle is abnormally accelerating or decelerating, and the specific judgment process in judging whether the vehicle is an abnormally driving vehicle refer to the judgment process of abnormal lane changing, abnormal acceleration or deceleration, and abnormal driving of the vehicle in the above-mentioned abnormal vehicle detection method, and will not be repeated in this embodiment.

[0150] The first reminder module 400 is used to provide safety reminders to the driver of the vehicle that is in abnormal driving.

[0151] Specifically, the first reminder module 400 includes but is not limited to the highway management service background. When an abnormally driven vehicle is detected, the MEC uploads the dangerous driving information of the vehicle to the highway management service background. The highway management service background automatically searches for the driver's phone number based on the vehicle license plate information, and intelligently dials the phone to remind the driver to take safety measures.

[0152] The second reminder module 500 is used to provide safety reminders to surrounding vehicles.

[0153] Specifically: the second reminder module 500 includes but is not limited to RSU, OBU module or navigation. When an abnormally driven vehicle is detected, MEC broadcasts the vehicle's dangerous driving information to surrounding vehicles through RSU. Vehicles around with OBU modules can avoid and stay away from danger after receiving the RSU broadcast message; or, MEC synchronizes the vehicle's dangerous driving information to the navigation, and the navigation marks the location of the dangerously driven vehicle as a dangerous area reminder to remind other vehicles to avoid and stay away from danger.

[0154] The abnormal vehicle detection and safety reminder device provided in this embodiment detects dangerously driven vehicles through cameras on the highway in combination with MEC, and reminds the driver and surrounding vehicles in various ways, thereby greatly improving the coverage of dangerous driving behavior interference reminders and danger avoidance, reducing traffic accidents, reducing casualties and losses, and improving traffic safety.

[0155] In some optional embodiments, the embodiments of the present invention further disclose an abnormal vehicle detection and safety reminder device.

[0156] Figure 4 A schematic structural diagram of an abnormal vehicle detection and safety reminder device provided by an embodiment of the present invention is shown.

[0157] like Figure 4 As shown, the abnormal vehicle detection and safety reminder device includes: a processor 610, a memory 620, a communication interface 630 and a communication bus 640. The processor 610, the memory 620 and the communication interface 630 communicate with each other through the communication bus 640.

[0158] In this embodiment, the memory 620 is used to store at least one executable instruction, and the executable instruction enables the processor 620 to perform an operation of an abnormal vehicle detection method as described in any of the above embodiments; the communication interface 630 is used to communicate with other devices such as a client or other server network elements. The processor 610 is used to execute the program 650, and specifically can execute the relevant steps in the above abnormal vehicle detection method embodiment.

[0159] Specifically, the program 650 may include program code including computer executable instructions.

[0160] The processor 610 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiment of the present invention. The one or more processors included in the abnormal vehicle detection and safety reminder device may be processors of the same type, such as one or more CPUs; or may be processors of different types, such as one or more CPUs and one or more ASICs.

[0161] The memory 620 is used to store the program 650. The memory 620 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory.

[0162] Program 650 may be specifically called by processor 610 to enable the abnormal vehicle detection and safety reminder device to perform an operation of an abnormal vehicle detection method described in any of the above embodiments.

[0163] In some optional embodiments, the embodiments of the present invention further disclose a computer-readable storage medium, wherein at least one executable instruction is stored in the storage medium. When the executable instruction is executed on the abnormal vehicle detection and safety reminder device / apparatus, the abnormal vehicle detection and safety reminder device / apparatus executes the steps of an abnormal vehicle detection method in any of the above-mentioned method embodiments.

[0164] The specific implementation process of the abnormal vehicle detection method described in this embodiment can be found in any of the above method embodiments, which will not be repeated in this embodiment.

[0165] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. Similarly, in order to simplify the present invention and help understand one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, the various features of the embodiments of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. Wherein, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, wherein each claim itself is a separate embodiment of the present invention.

[0166] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and further may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive.

[0167] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be understood as limitations on the order of execution.

Claims

1. A method for detecting abnormal vehicles, characterized in that: The following steps are involved: Acquire vehicle driving video data, and acquire the vehicle's driving trajectory based on the vehicle driving video data; Calculate the acceleration of the vehicle according to the vehicle's driving trajectory and the sampling frequency of the data frame; Determine whether the vehicle is moving abnormally based on its driving trajectory and acceleration; If the vehicle is judged to be in abnormal driving, the vehicle and surrounding vehicles will be reminded.

2. The abnormal vehicle detection method according to claim 1, characterized in that: Determine whether the vehicle is operating abnormally, including: Determine whether the vehicle is changing lanes abnormally based on the vehicle's driving trajectory; If so, judging whether the vehicle is accelerating or decelerating abnormally according to the acceleration of the vehicle; If so, it is determined that the vehicle is in abnormal driving.

3. The abnormal vehicle detection method according to claim 2, characterized in that: Determine whether the vehicle is changing lanes abnormally based on the vehicle's driving trajectory, including: According to the driving trajectory of the vehicle, determine whether multiple vehicles identified at multiple times change lanes; If a vehicle changes lanes continuously in different lanes and there are no other vehicles in between when changing lanes; Detect whether the vehicle turns on the turn signal during the continuous lane change process; If not, it is determined that the vehicle is changing lanes abnormally.

4. The abnormal vehicle detection method according to claim 2, characterized in that: Determine whether the vehicle is accelerating or decelerating abnormally, including: Determining whether the acceleration of the vehicle is greater than a preset threshold; If so, determine whether the current distance difference is less than the safety distance; If so, it is determined that the vehicle is in abnormal acceleration or deceleration.

5. The abnormal vehicle detection method according to claim 1, characterized in that: The calculation of the vehicle's driving trajectory includes: Continuously extracting multiple frames of vehicle driving image data from vehicle driving video data; Identify and analyze multiple vehicles within its range and their location information based on each frame of vehicle driving image data; The vehicle's driving trajectory is obtained based on the acquired multiple frames of continuous information about multiple vehicles and their positions.

6. The abnormal vehicle detection method according to claim 1, characterized in that: The calculation of vehicle acceleration includes: Extract the location information of the vehicle at different times; Calculate the position distance difference between two moments of the vehicle based on the position information of the vehicle at different moments; Calculate the speed of the vehicle based on the position distance difference between the vehicle at two times and the time difference between the vehicle at two times; The acceleration of the vehicle is calculated based on the speed of the vehicle calculated at the current moment and the speed of the vehicle calculated at the previous moment.

7. The abnormal vehicle detection method according to claim 1, characterized in that: Prompt the vehicle and surrounding vehicles, including: Submit the dangerous driving information of the abnormally moving vehicle to the road management service backend so that the road management service backend can remind the driver of the abnormally moving vehicle; And / or, broadcast the dangerous driving information of the abnormally moving vehicle to surrounding vehicles through the RSU to remind surrounding vehicles to avoid and stay away from danger; And / or, the dangerous driving information of the abnormally moving vehicle is synchronized to the navigation system, and the navigation system marks the location of the abnormally moving vehicle as a dangerous area reminder, and reminds other vehicles to avoid and stay away from the danger.

8. An abnormal vehicle detection and safety reminder device, characterized in that: include: A data acquisition module, used to obtain vehicle driving video data; A calculation module, used to calculate the vehicle's driving trajectory based on the vehicle's driving video data and to calculate the vehicle's speed and acceleration based on the vehicle's driving trajectory; A judgment module is used to judge whether the vehicle is changing lanes abnormally according to the vehicle's driving trajectory, and to judge whether the vehicle is accelerating or decelerating abnormally according to the vehicle's acceleration, and further judge whether the vehicle is in abnormal driving; A first reminder module, used to provide safety reminders to the driver of the vehicle in abnormal driving; The second reminder module is used to provide safety reminders to surrounding vehicles.

9. An abnormal vehicle detection and safety reminder device, characterized in that: include: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the operation of an abnormal vehicle detection method as described in any one of claims 1-7.

10. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the steps of an abnormal vehicle detection method as described in any one of claims 1-7 are implemented.

Images