A target vehicle detection system and method for high-speed roads

Abstract

The present invention relates to the field of target vehicle detection technology, and discloses a target vehicle detection system and method for highways, comprising the following steps: Step 1: collecting driving data of a target vehicle during driving time, and obtaining driving parameters of the target vehicle; wherein the driving data includes the driving track and driving speed of the target vehicle during driving time; Step 2: comparing the driving parameters with a threshold. The present invention first collects the driving track and driving speed of the target vehicle during driving time, and calculates the driving parameters by obtaining the number of lane changes, the abnormal area ratio, and the unstable time point ratio. The larger the number of lane changes, the abnormal area ratio, and the unstable time point ratio, the more unstable the driving of the target vehicle is. The driving parameters are compared with the driving parameter threshold, and a normal driving signal or an abnormal driving signal is identified and generated, so that the driving condition of the target vehicle on the highway can be detected.

Description

Technical Field

[0001] The present invention relates to the technical field of target vehicle detection, and in particular to a target vehicle detection system and method for expressways. Background Art

[0002] With the acceleration of urbanization and the rapid development of transportation, highways, as an important part of the modern transportation system, have seen a continuous increase in traffic volume and vehicle density. To ensure the safe and efficient operation of highways, it is particularly important to conduct real-time and accurate detection of vehicles on the road.

[0003] However, although there is a process for detecting target vehicles on highways, the detection method is relatively direct and single, and it is not possible to perform integrated detection of the number of lane changes and speed of the target vehicle, and it is not possible to detect and analyze the dangerous blocking behavior of the target vehicle, so it is impossible to issue timely warnings for such dangerous driving behaviors, causing safety problems;

[0004] In view of this, we propose a target vehicle detection system and method for highways. Summary of the invention

[0005] The object of the present invention is to provide a target vehicle detection system and method for highways to solve the problems in the above background that the number of lane changes and speed of the target vehicle cannot be detected in a fusion manner, and the dangerous swerving behavior of the target vehicle cannot be detected and analyzed.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] A target vehicle detection system and method for a highway, comprising the following steps: Step 1: collecting driving data of a target vehicle during driving time to obtain driving parameters of the target vehicle; wherein the driving data includes the driving trajectory and driving speed of the target vehicle during driving time; Step 2: comparing the driving parameters with a threshold value to generate a driving abnormality signal; Step 3: based on the above-generated driving abnormality signal, obtaining driving parameters of a target vehicle that has driven abnormally on the same road section during driving time, and calculating an abnormal overlap characterization value; Step 4: comparing the abnormal overlap characterization value with a threshold value to generate a high overlap signal; Step 5: based on the above-generated high overlap signal, calculating a behavior judgment value of the target vehicle, and comparing them to determine the active vehicle of the vehicle-cutting behavior.

[0008] As a further solution of the present invention: the process of obtaining the driving parameters of the target vehicle is:

[0009] Obtain the number of lane changes CS, the abnormal area ratio value YZ, and the abnormal slope ratio value WZ;

[0010] Substitute the number of lane changes CS, the abnormal area proportion value YZ and the abnormal slope proportion value WZ into the formula to calculate the driving parameter XS, where a, b, and c are preset proportional coefficients.

[0011] As a further solution of the present invention: the process of obtaining the number of lane changes CS and the abnormal area ratio YZ is as follows:

[0012] Obtain the driving trajectory of the target vehicle within the driving time, and obtain the number of lane changes CS of the target vehicle according to the driving trajectory;

[0013] Obtain the driving speed value of the target vehicle within the driving time;

[0014] Establish an XY two-dimensional coordinate system, with the driving time as the X-axis and the corresponding driving speed as the Y-axis. Establish a standard line parallel to the X-axis in the coordinate system with the maximum value of the speed threshold range, recorded as the first standard line, and establish a standard line parallel to the X-axis in the coordinate system with the minimum value of the speed threshold range, recorded as the second standard line. Substitute the real-time driving speed into the two-dimensional coordinate system to draw a driving speed curve;

[0015] The portion of the driving speed above the first standard line and below the second standard line is marked as an abnormal speed area, and the portion of the driving speed below the first standard line and above the second standard line is marked as a normal speed area;

[0016] Obtain the area value of the speed abnormal area and the area value of the speed normal area, and perform ratio processing to obtain the abnormal area ratio value YZ;

[0017] As a further solution of the present invention: the process of obtaining the abnormal slope ratio value WZ is:

[0018] Divide the travel time into several time units, obtain the tangent slope value corresponding to the middle time point of each time unit, and mark it as a single slope value;

[0019] comparing the single slope value to a slope value threshold;

[0020] If the single slope value is less than or equal to the slope value threshold, mark the normal slope;

[0021] If a single slope value is greater than the slope value threshold, an abnormal slope is marked;

[0022] The number of abnormal slope values ​​and the number of normal slope values ​​are obtained, and the sum is calculated to obtain the total slope value. The abnormal slope value is ratioed to the total slope value to obtain the abnormal slope ratio value WZ.

[0023] As a further solution of the present invention: the generation process of the driving abnormality signal is:

[0024] Acquire a driving parameter XS, and compare the driving parameter XS with a driving parameter threshold;

[0025] If the driving parameter XS is greater than the driving parameter threshold, a driving abnormality signal is generated.

[0026] As a further solution of the present invention: the process of obtaining the abnormal coincidence characterization value is:

[0027] Obtain the number deviation value GP of the abnormal time period, the total deviation value QZ of the start time, and the total deviation value JZ of the end time;

[0028] Substitute the abnormal time period number deviation value GP, the start time deviation total value QZ and the end time deviation total value JZ into the formula , the abnormal coincidence characterization value YB is calculated, where S1 and S2 are weight coefficients, and S1+S2+S2=1, S1>S2.

[0029] As a further solution of the present invention: the process of obtaining the abnormal time period number deviation value GP, the start time deviation total value QZ and the end time deviation total value JZ is as follows:

[0030] Obtain target vehicles with abnormal driving parameters on the same road section, and mark them as the first target vehicle and the second target vehicle;

[0031] An XY two-dimensional coordinate system is established, with the driving time as the X-axis and the corresponding driving parameter as the Y-axis. A reference line parallel to the X-axis is established in the coordinate system using the driving parameter threshold. The real-time driving parameters of the first target vehicle and the second target vehicle are substituted into the two-dimensional coordinate system to draw driving parameter curves of the first target vehicle and the second target vehicle.

[0032] The portion of the driving parameter above the baseline is marked as a normal driving parameter area;

[0033] Obtain the time period and total number of time periods in the abnormal driving parameter area of ​​the first target vehicle and the second target vehicle;

[0034] Subtract the total number of abnormal time periods of the first target vehicle from the total number of abnormal time periods of the second target vehicle to obtain the absolute value of the difference, which is recorded as the abnormal time period number deviation value GP;

[0035] Subtract the start time of the first target vehicle abnormal area time period of the overlapping time period from the start time of the second target vehicle abnormal area time period to obtain the absolute value of the start time deviation, and then subtract the end time of the first target vehicle abnormal area time period of the overlapping time period from the end time of the second target vehicle abnormal area time period to obtain the absolute value of the end time deviation;

[0036] All the absolute values ​​of the start time deviation and the absolute values ​​of the end time deviation are summed up and calculated respectively to obtain the total value of the start time deviation QZ and the total value of the end time deviation JZ;

[0037] As a further solution of the present invention: the generation process of the high coincidence signal is:

[0038] Obtain an abnormal coincidence characterization value YB, and compare the abnormal coincidence characterization value YB with an abnormal coincidence characterization threshold;

[0039] If the abnormal overlap characterization value YB is less than or equal to the abnormal overlap characterization threshold, a high overlap signal is generated.

[0040] As a further solution of the present invention, the specific process of determining the active vehicle's behavior of cutting off another vehicle is as follows:

[0041] Obtaining time periods of the driving parameter abnormality areas of the first target vehicle and the second target vehicle, summing the abnormal time periods of the first target vehicle to obtain a total value of the driving parameter abnormality time of the first target vehicle, and summing the abnormal time periods of the second target vehicle to obtain a total value of the driving parameter abnormality time of the second target vehicle;

[0042] Obtaining the acceleration time periods during the driving time of the first target vehicle and the second target vehicle, calculating the acceleration of the acceleration time period, summing and averaging the accelerations of all acceleration time periods of the first target vehicle to obtain the average acceleration value of the first target vehicle, and summing and averaging the accelerations of all acceleration time periods of the second target vehicle to obtain the average acceleration value of the second target vehicle;

[0043] The total value of the abnormal time of the driving parameter of the first target vehicle and the average value of the acceleration of the first target vehicle are summed to obtain a behavior determination value of the first target vehicle;

[0044] The total value of the abnormal time of the driving parameter of the second target vehicle and the average value of the acceleration of the second target vehicle are summed to obtain a behavior determination value of the second target vehicle;

[0045] comparing the behavior determination value of the first target vehicle with the behavior determination value of the second target vehicle;

[0046] If the behavior determination value of the first target vehicle is greater than the behavior determination value of the second target vehicle, marking the first target vehicle as an active vehicle;

[0047] If the behavior determination value of the first target vehicle is less than the behavior determination value of the second target vehicle, the second target vehicle is marked as an active vehicle.

[0048] As a further solution of the present invention: specifically comprising: a driving data collection and processing module: collecting driving data of the target vehicle during driving time to obtain driving parameters of the target vehicle;

[0049] Driving parameter detection and judgment module: compares the driving parameters with the threshold value and generates a driving abnormality signal;

[0050] Target vehicle anomaly calculation module: obtains the driving parameters of the target vehicle that is driving abnormally on the same road section during the driving time, and calculates the abnormal coincidence representation value;

[0051] Coincidence judgment module: compares the abnormal coincidence characterization value with the threshold value to generate a high coincidence signal;

[0052] Comparison warning module: calculates the behavior judgment value of the target vehicle, compares it, and determines the active vehicle in the different vehicle behaviors.

[0053] Beneficial effects of the present invention:

[0054] The present invention first collects the driving trajectory and driving speed of the target vehicle during the driving time, and calculates the driving parameters by obtaining the number of lane changes, the abnormal area ratio and the unstable time point ratio. The larger the number of lane changes, the abnormal area ratio and the unstable time point ratio, the more unstable the driving of the target vehicle is. The driving parameters are compared with the driving parameter threshold, and a normal driving signal or an abnormal driving signal is identified and generated, thereby detecting the driving condition of the target vehicle on the highway.

[0055] The present invention marks two vehicles that are driving abnormally on the same road section, obtains the driving parameters of the two vehicles during the driving time, obtains the abnormal coincidence characterization value of the two vehicles' driving abnormalities through processing and calculation, and finally compares the abnormal coincidence characterization value with the threshold value, so as to detect whether the two vehicles are performing dangerous cutting behavior;

[0056] The present invention calculates the behavior determination values ​​of the target vehicles, compares the behavior determination values, defines the target vehicle with the larger behavior determination value as the active vehicle, and warns the active vehicle, thereby reducing the safety hazards caused by the behavior of cutting in. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The present invention will be further described below in conjunction with the accompanying drawings.

[0058] Figure 1 It is a flow chart of a method for detecting a target vehicle on a highway according to the present invention;

[0059] Figure 2 It is a schematic diagram of a process of acquiring driving parameters in a target vehicle detection method for a highway according to the present invention;

[0060] Figure 3 It is a schematic diagram of a process for obtaining an abnormal coincidence characterization value in a target vehicle detection method for a highway in the present invention. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Embodiment 1

[0062] See also Figure 1-3 As shown, the present invention is a method for detecting a target vehicle on a highway, comprising the following steps:

[0063] Step 1: Collect the driving data of the target vehicle during its driving time to obtain the driving parameters of the target vehicle;

[0064] Among them, the driving data includes the driving trajectory and driving speed of the target vehicle during the driving time;

[0065] In some embodiments, a driving trajectory of the target vehicle during the driving time is obtained, and the number of lane changes CS of the target vehicle is obtained according to the driving trajectory;

[0066] Obtain the driving speed value of the target vehicle within the driving time;

[0067] Establish an XY two-dimensional coordinate system, with the driving time as the X-axis and the corresponding driving speed as the Y-axis. Establish a standard line parallel to the X-axis in the coordinate system with the maximum value of the speed threshold range, recorded as the first standard line, and establish a standard line parallel to the X-axis in the coordinate system with the minimum value of the speed threshold range, recorded as the second standard line. Substitute the real-time driving speed into the two-dimensional coordinate system to draw a driving speed curve;

[0068] Among them, the speed threshold range is the high-speed road driving range [60,120];

[0069] The portion of the driving speed above the first standard line and below the second standard line is marked as an abnormal speed area, and the portion of the driving speed below the first standard line and above the second standard line is marked as a normal speed area;

[0070] Obtain the area value of the speed abnormal area and the area value of the speed normal area, and perform ratio processing to obtain the abnormal area ratio value YZ;

[0071] Divide the travel time into several time units, obtain the tangent slope value corresponding to the middle time point of each time unit, and mark it as a single slope value;

[0072] comparing the single slope value with a slope value threshold (the slope value threshold is set empirically by a person skilled in the art);

[0073] If the single slope value is less than or equal to the slope value threshold, it means that the speed change rate of the target vehicle at each time point is small, and the normal slope is marked;

[0074] If a single slope value is greater than the slope value threshold, it means that the target vehicle's speed change rate at each time point is large, and the abnormal slope is marked;

[0075] Obtain the number of abnormal slope values ​​and the number of normal slope values, sum them up, and obtain the total slope value. Ratio the abnormal slope value to the total slope value to obtain the abnormal slope ratio value WZ;

[0076] Substitute the number of lane changes CS, the abnormal area ratio value YZ and the abnormal slope ratio value WZ into the formula to calculate the driving parameter XS, where a, b, and c are preset proportional coefficients;

[0077] Step 2: Compare the driving parameters with the threshold value to generate a normal driving signal or an abnormal driving signal;

[0078] In some embodiments, a driving parameter XS is obtained, and the driving parameter XS is compared with a driving parameter threshold;

[0079] The driving parameter threshold is an empirical value obtained by those skilled in the art from historical experimental data;

[0080] If the driving parameter XS is less than or equal to the driving parameter threshold, it means that the target vehicle is relatively stable during driving, and a normal driving signal is generated;

[0081] If the driving parameter XS is greater than the driving parameter threshold, it means that the target vehicle is relatively unstable during driving, and a driving abnormality signal is generated.

[0082] The core idea of ​​this embodiment is as follows: first, the driving trajectory and driving speed of the target vehicle during the driving time are collected, and the driving parameters are calculated by obtaining the number of lane changes, the proportion of abnormal areas and the proportion of unstable time points. The larger the number of lane changes, the proportion of abnormal areas and the proportion of unstable time points, the more unstable the driving of the target vehicle is. The driving parameters are compared with the driving parameter threshold, and a normal driving signal or an abnormal driving signal is identified and generated, thereby detecting the driving condition of the target vehicle on the highway. Embodiment 2

[0083] Based on the above embodiments, when vehicles are driving on a highway, two vehicles may pass each other, causing driving abnormalities. The present invention is a target vehicle detection method for a highway, which also includes the following steps:

[0084] Step 3: Based on the above-mentioned generation of the driving abnormality signal, the driving parameters of the target vehicle that has driven abnormally on the same road section during the driving time are obtained, and the abnormal coincidence characterization value is calculated;

[0085] Among them, the abnormal coincidence characterization value is calculated by the time period and individual values ​​of the time period when the target vehicle driving parameters are abnormal;

[0086] In some embodiments, target vehicles with abnormal driving parameters on the same road section are obtained and marked as a first target vehicle and a second target vehicle;

[0087] An XY two-dimensional coordinate system is established, with the driving time as the X-axis and the corresponding driving parameter as the Y-axis. A reference line parallel to the X-axis is established in the coordinate system using the driving parameter threshold. The real-time driving parameters of the first target vehicle and the second target vehicle are substituted into the two-dimensional coordinate system to draw driving parameter curves of the first target vehicle and the second target vehicle.

[0088] The portion of the driving parameter above the baseline is marked as an abnormal driving parameter area;

[0089] Obtain the time period and total number of time periods in the abnormal driving parameter area of ​​the first target vehicle and the second target vehicle;

[0090] Subtract the total number of abnormal time periods of the first target vehicle from the total number of abnormal time periods of the second target vehicle to obtain the absolute value of the difference, which is recorded as the abnormal time period number deviation value GP;

[0091] Subtract the start time of the first target vehicle abnormal area time period from the start time of the second target vehicle abnormal area time period of the overlapping time period (the overlapping time period is the situation where there is a time intersection between the first target vehicle abnormal area time period and the second target vehicle abnormal area time period) to obtain the absolute value of the start time deviation, and then subtract the end time of the first target vehicle abnormal area time period from the end time of the second target vehicle abnormal area time period of the overlapping time period to obtain the absolute value of the end time deviation;

[0092] All the absolute values ​​of the start time deviation and the absolute values ​​of the end time deviation are summed up and calculated respectively to obtain the total value of the start time deviation QZ and the total value of the end time deviation JZ;

[0093] Substitute the abnormal time period number deviation value GP, the start time deviation total value QZ and the end time deviation total value JZ into the formula , calculate the abnormal coincidence characterization value YB, where S1 and S2 are weight coefficients, and S1+S2+S2=1, S1>S2, indicating that the influence of the deviation value of the number of abnormal time periods is greater than the total deviation value of the starting time, and the influence of the total deviation value of the starting time is equal to the influence of the total deviation value of the ending time;

[0094] Step 4: Compare the abnormal coincidence characterization value with the threshold value to generate a high coincidence signal or a low coincidence signal;

[0095] In some embodiments, the abnormal overlap characterization value YB is obtained, and the abnormal overlap characterization value YB is compared with the abnormal overlap characterization threshold;

[0096] The abnormal coincidence characterization threshold is an empirical value obtained by technicians in this field from historical experimental data;

[0097] If the abnormal overlap characterization value YB is less than or equal to the abnormal overlap characterization threshold, it means that the driving abnormal overlap between the first target vehicle and the second target vehicle is high, and a high overlap signal is generated;

[0098] If the abnormal overlap characterization value YB is greater than the abnormal overlap characterization threshold, it means that the driving abnormal overlap between the first target vehicle and the second target vehicle is low, and a low overlap signal is generated;

[0099] The core idea of ​​this embodiment is: first, by marking two vehicles with abnormal driving on the same road section, and obtaining the driving parameters of the two vehicles during the driving time, the abnormal overlap characterization value of the two vehicles' driving abnormalities is obtained through processing and calculation, and finally the abnormal overlap characterization value is compared with the threshold, so as to detect whether the two vehicles are performing dangerous cutting behavior. Embodiment 3

[0100] Based on the above embodiments, the present invention is a method for detecting a target vehicle on a highway, further comprising the following steps:

[0101] Step 5: Based on the high overlap signal generated above, the behavior judgment value of the target vehicle is calculated and compared to determine the active vehicle in the cross traffic behavior and warn it;

[0102] In some embodiments, the behavior determination value is obtained by summing the total value of the abnormal time of the target vehicle driving parameter and the average value of the acceleration of all acceleration stages during the target vehicle driving time;

[0103] Obtaining time periods of the driving parameter abnormality areas of the first target vehicle and the second target vehicle, summing the abnormal time periods of the first target vehicle to obtain a total value of the driving parameter abnormality time of the first target vehicle, and summing the abnormal time periods of the second target vehicle to obtain a total value of the driving parameter abnormality time of the second target vehicle;

[0104] Obtaining the acceleration time periods during the driving time of the first target vehicle and the second target vehicle, calculating the acceleration of the acceleration time period, summing and averaging the accelerations of all acceleration time periods of the first target vehicle to obtain the average acceleration value of the first target vehicle, and summing and averaging the accelerations of all acceleration time periods of the second target vehicle to obtain the average acceleration value of the second target vehicle;

[0105] The total value of the abnormal time of the driving parameter of the first target vehicle and the average value of the acceleration of the first target vehicle are summed to obtain a behavior determination value of the first target vehicle;

[0106] The total value of the abnormal time of the driving parameter of the second target vehicle and the average value of the acceleration of the second target vehicle are summed to obtain a behavior determination value of the second target vehicle;

[0107] comparing the behavior determination value of the first target vehicle with the behavior determination value of the second target vehicle;

[0108] If the behavior determination value of the first target vehicle is greater than the behavior determination value of the second target vehicle, the first target vehicle is marked as an active vehicle and the second target vehicle is marked as a passive vehicle;

[0109] If the behavior determination value of the first target vehicle is less than the behavior determination value of the second target vehicle, the second target vehicle is marked as an active vehicle and the first target vehicle is marked as a passive vehicle;

[0110] If the behavior determination value of the first target vehicle is equal to the behavior determination value of the second target vehicle, the number of lane changes of the first target vehicle and the second target vehicle is analyzed, and then a judgment is made, and the vehicle with a large number of lane changes is marked as an active vehicle, and the vehicle with a small number of lane changes is marked as a passive vehicle;

[0111] Among them, the warning methods for active vehicles include but are not limited to: using the vehicle system, APP push and roadside display board to warn the driver;

[0112] The core idea of ​​this embodiment is: by calculating the behavior judgment values ​​of the target vehicles and comparing the behavior judgment values, the target vehicle with a larger behavior judgment value is defined as an active vehicle, and the active vehicle is warned, thereby reducing the safety hazards caused by the behavior of cutting in. Embodiment 4

[0113] Based on the above embodiment, a target vehicle detection system for a highway specifically includes:

[0114] Driving data collection and processing module: collects driving data of the target vehicle during driving time and obtains driving parameters of the target vehicle;

[0115] Driving parameter detection and judgment module: compares the driving parameters with the threshold value and generates a driving abnormality signal;

[0116] Target vehicle anomaly calculation module: obtains the driving parameters of the target vehicle that is driving abnormally on the same road section during the driving time, and calculates the abnormal coincidence representation value;

[0117] Coincidence judgment module: compares the abnormal coincidence characterization value with the threshold value to generate a high coincidence signal;

[0118] Comparison warning module: calculates the behavior judgment value of the target vehicle, compares it, and determines the active vehicle in the different vehicle behaviors.

[0119] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A target vehicle detection method for a highway, characterized in that: The following steps are involved: Step 1: Collect the driving data of the target vehicle during the driving time to obtain the driving parameters of the target vehicle, wherein the driving data includes the driving trajectory and driving speed of the target vehicle during the driving time; The process of obtaining the driving parameters of the target vehicle is as follows: Obtain the driving trajectory of the target vehicle within the driving time, and obtain the number of lane changes CS of the target vehicle according to the driving trajectory; Obtain the driving speed value of the target vehicle within the driving time; Establish an XY two-dimensional coordinate system, with the driving time as the X-axis and the corresponding driving speed as the Y-axis. Establish a standard line parallel to the X-axis in the coordinate system with the maximum value of the speed threshold range, recorded as the first standard line, and establish a standard line parallel to the X-axis in the coordinate system with the minimum value of the speed threshold range, recorded as the second standard line. Substitute the real-time driving speed into the two-dimensional coordinate system to draw a driving speed curve; The portion of the driving speed above the first standard line and below the second standard line is marked as an abnormal speed area, and the portion of the driving speed below the first standard line and above the second standard line is marked as a normal speed area; Obtain the area value of the speed abnormal area and the area value of the speed normal area, and perform ratio processing to obtain the abnormal area ratio value YZ; Divide the travel time into several time units, obtain the tangent slope value corresponding to the middle time point of each time unit, and mark it as a single slope value; comparing the single slope value to a slope value threshold; If the single slope value is less than or equal to the slope value threshold, mark the normal slope; If a single slope value is greater than the slope value threshold, an abnormal slope is marked; Obtain the number of abnormal slope values ​​and the number of normal slope values, sum them up, and obtain the total slope value. Ratio the abnormal slope value to the total slope value to obtain the abnormal slope ratio value WZ; The driving parameter XS is calculated based on the number of lane changes CS, the abnormal area ratio YZ and the abnormal slope ratio WZ; Step 2: Compare the driving parameters with the threshold value to generate a driving abnormality signal; Step 3: Based on the above-mentioned generation of the driving abnormality signal, the driving parameters of the target vehicle that has driven abnormally on the same road section during the driving time are obtained, and the abnormal coincidence characterization value is calculated; The process of obtaining the abnormal coincidence characterization value is as follows: Obtain target vehicles with abnormal driving parameters on the same road section, and mark them as the first target vehicle and the second target vehicle; An XY two-dimensional coordinate system is established, with the driving time as the X-axis and the corresponding driving parameter as the Y-axis. A reference line parallel to the X-axis is established in the coordinate system using the driving parameter threshold. The real-time driving parameters of the first target vehicle and the second target vehicle are substituted into the two-dimensional coordinate system to draw driving parameter curves of the first target vehicle and the second target vehicle. The portion of the driving parameter above the baseline is marked as an abnormal driving parameter area; Obtain the time period and total number of time periods in the abnormal driving parameter area of ​​the first target vehicle and the second target vehicle; Subtract the total number of abnormal time periods of the first target vehicle from the total number of abnormal time periods of the second target vehicle to obtain the absolute value of the difference, which is recorded as the abnormal time period number deviation value GP; Subtract the start time of the first target vehicle abnormal area time period of the overlapping time period from the start time of the second target vehicle abnormal area time period to obtain the absolute value of the start time deviation, and then subtract the end time of the first target vehicle abnormal area time period of the overlapping time period from the end time of the second target vehicle abnormal area time period to obtain the absolute value of the end time deviation; All the absolute values ​​of the start time deviation and the absolute values ​​of the end time deviation are summed up and calculated respectively to obtain the total value of the start time deviation QZ and the total value of the end time deviation JZ; Substitute the abnormal time period number deviation value GP, the start time deviation total value QZ and the end time deviation total value JZ into the formula , calculate the abnormal coincidence characterization value YB, where S1 and S2 are weight coefficients, and S1+S2+S2=1, S1>S2; Step 4: Compare the abnormal coincidence characterization value with the threshold value to generate a high coincidence signal; Step 5: Based on the high overlap signal generated above, the behavior judgment value of the target vehicle is calculated and compared to determine the active vehicle in the cut-off behavior; Obtaining time periods of the driving parameter abnormality areas of the first target vehicle and the second target vehicle, summing the abnormal time periods of the first target vehicle to obtain a total value of the driving parameter abnormality time of the first target vehicle, and summing the abnormal time periods of the second target vehicle to obtain a total value of the driving parameter abnormality time of the second target vehicle; Obtaining the acceleration time periods during the driving time of the first target vehicle and the second target vehicle, calculating the acceleration of the acceleration time period, summing and averaging the accelerations of all acceleration time periods of the first target vehicle to obtain the average acceleration value of the first target vehicle, and summing and averaging the accelerations of all acceleration time periods of the second target vehicle to obtain the average acceleration value of the second target vehicle; The total value of the abnormal time of the driving parameter of the first target vehicle and the average value of the acceleration of the first target vehicle are summed to obtain a behavior determination value of the first target vehicle; The total value of the abnormal time of the driving parameter of the second target vehicle and the average value of the acceleration of the second target vehicle are summed to obtain a behavior determination value of the second target vehicle; comparing the behavior determination value of the first target vehicle with the behavior determination value of the second target vehicle; If the behavior determination value of the first target vehicle is greater than the behavior determination value of the second target vehicle, marking the first target vehicle as an active vehicle; If the behavior determination value of the first target vehicle is less than the behavior determination value of the second target vehicle, the second target vehicle is marked as an active vehicle.

2. A target vehicle detection method for a highway according to claim 1, characterized in that: The generation process of driving abnormality signal is as follows: Acquire a driving parameter XS, and compare the driving parameter XS with a driving parameter threshold; If the driving parameter XS is greater than the driving parameter threshold, a driving abnormality signal is generated.

3. A target vehicle detection method for a highway according to claim 1, characterized in that: The generation process of high coincidence signal is: Obtain an abnormal coincidence characterization value YB, and compare the abnormal coincidence characterization value YB with an abnormal coincidence characterization threshold; If the abnormal overlap characterization value YB is less than or equal to the abnormal overlap characterization threshold, a high overlap signal is generated.

4. A target vehicle detection system for a highway, the system implementing the method according to any one of claims 1 to 3, characterized in that: Specifically include: Driving data collection and processing module: collects driving data of the target vehicle during driving time and obtains driving parameters of the target vehicle; Driving parameter detection and judgment module: compares the driving parameters with the threshold value and generates a driving abnormality signal; Target vehicle anomaly calculation module: obtains the driving parameters of the target vehicle that is driving abnormally on the same road section during the driving time, and calculates the abnormal coincidence representation value; Coincidence judgment module: compares the abnormal coincidence characterization value with the threshold value to generate a high coincidence signal; Comparison warning module: calculates the behavior judgment value of the target vehicle, compares it, and determines the active vehicle in the different vehicle behaviors.

Images