Truck abnormal lane occupation identification method based on roadside millimeter wave radar

Abstract

The invention discloses a truck abnormal lane occupation identification method based on a roadside millimeter wave radar, and belongs to the technical field of radar monitoring, and the method comprises the following steps: numbering lanes of a to-be-monitored road section; acquiring driving information of a driving vehicle on the to-be-monitored road section; forming a driving record of the vehicle; obtaining a marked driving record; obtaining an association set of the marked vehicles; performing primary judgment and secondary judgment on the abnormal road occupying behavior of the marked vehicle; generating an abnormal vehicle, and screening out an abnormal associated vehicle associated with the abnormal vehicle; forming a rechecking material; carrying out manual re-checking on the re-checking material, and carrying out abnormity reporting and material retention; according to the invention, the accurate identification of the abnormal road-occupying behavior of the truck is realized, the identification capability of the abnormal road-occupying behavior of the truck is improved, the misjudgment and missed judgment risks caused by manual judgment and camera monitoring are reduced, and the traffic accident handling capability and the overall performance of traffic management are improved.

Description

Technical Field

[0001] The present invention belongs to the field of radar monitoring technology, and specifically relates to a method for identifying abnormal road occupation by trucks based on roadside millimeter-wave radar. Background Art

[0002] Millimeter-wave radar is a radar that works in the millimeter-wave band. Usually, millimeter waves refer to the 30-300 GHz frequency domain. Compared with centimeter-wave radar, millimeter-wave radar has stronger anti-interference ability, stronger maneuverability and better concealment. At the same time, millimeter-wave radar can identify multiple targets at the same time. Abnormal occupation of passenger lanes by trucks on highways is a long-standing and highly concerned issue. Compared with passenger cars, trucks travel at a lower speed on highways. If trucks occupy passenger lanes abnormally for a long time, it is easy to cause traffic accidents, reduce traffic efficiency, disrupt the normal traffic order of highways, and hinder special vehicles from performing emergency tasks. In the current traffic management system, the classification of abnormal road occupation by trucks usually relies on manual judgment, camera recognition or simple rules. These methods often cannot accurately reflect abnormal road occupation by trucks in real time, resulting in misjudgment and omission of abnormal trucks, which reduces the ability to handle traffic accidents and the overall performance of traffic management. Therefore, people urgently need a method for identifying abnormal road occupation by trucks based on roadside millimeter-wave radar to solve the above problems. Summary of the invention

[0003] The purpose of the present invention is to provide a method for identifying abnormal road occupation by trucks based on roadside millimeter-wave radar to solve the problems raised in the above-mentioned background technology.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: A method for identifying abnormal road occupation by trucks based on roadside millimeter-wave radar, the method comprising the following steps: S1. Obtain the number of lanes of the road section to be monitored and number the lanes of the road section to be monitored; set up radars on the road section to be monitored and set up roadside monitoring cameras between adjacent radars, obtain driving information of vehicles on the road section to be monitored through the radars, and obtain videos of vehicles on the road section to be monitored through the roadside monitoring cameras; S2, extracting all driving information of the same vehicle when it is traveling on the road section to be monitored, forming a driving record of the vehicle; marking the vehicle traveling on the road section to be monitored to obtain a marked vehicle; extracting the driving information of the marked vehicle to obtain a marked driving record; S3. Determine and extract lane change information of the marked vehicle according to the marked driving record of the marked vehicle; perform matching according to the lane change information to obtain an associated set of the marked vehicles; S4. Based on the associated set of marked vehicles, a primary judgment and a secondary judgment are made on the abnormal road-occupying behavior of the marked vehicles; S5. When the result of the first judgment is that the marked vehicle has an abnormal road-occupying behavior, a second judgment is performed to determine whether the abnormal road-occupying behavior of the marked vehicle is a misjudgment; S6. If the result of one judgment is that there is no misjudgment of the abnormal road-occupying behavior of the marked vehicle, an abnormal vehicle is generated, driving information of other vehicles traveling on the road to be monitored is obtained, abnormal associated vehicles associated with the abnormal vehicle are screened out according to the driving information of the vehicles, and rechecked associated vehicles are screened out from the abnormal associated vehicles, and the rechecked associated vehicles and the abnormal vehicles are manually rechecked together; S7. Extract the driving records and videos of abnormal vehicles and review related vehicles to form review materials; manually review the review materials, report abnormalities and retain the materials.

[0005] According to the above technical solution, step S1 includes the following: S1-1, obtaining the number of lanes of the road section to be monitored, numbering the lanes of the road section to be monitored from right to left according to the driving direction of the vehicle, and obtaining the lane number of the road section to be monitored; obtaining the monitoring range of the radar, taking the monitoring range of the radar as the interval distance between adjacent radars, and setting radars on the road section to be monitored according to the interval distance between adjacent radars, so that the monitoring ranges of all radars that have been set up cover the entire road section to be monitored; setting roadside monitoring cameras between adjacent radars according to the preset interval distance between roadside monitoring cameras; S1-2, when a vehicle enters the road section to be monitored, after the radar detects the vehicle, the authentication information of the vehicle in the database is obtained, the vehicle type of the vehicle is extracted, and the vehicle number corresponding to the vehicle is generated; When the vehicle is traveling on the road section to be monitored, the radar collects information about the vehicle once and generates a driving information corresponding to the vehicle; the driving information includes the vehicle number, vehicle type, driving lane number, position stake number, driving direction, driving speed and timestamp; the vehicle types include passenger cars and trucks; The position stake number is the highway stake number corresponding to the longitude and latitude of the vehicle during driving after conversion; wherein the highway stake number is the mileage calculated from a certain starting point along the highway route, used to identify the position on the highway, and is a linear position representation method that is convenient for engineering construction, traffic management, etc.; the radar can output the longitude and latitude of the vehicle in real time; the conversion process is to use the Beidou high-precision positioning system to form a high-precision comparison table with the highway stake number and its actual longitude and latitude, and combine the longitude and latitude of the vehicle output in real time by the radar, and compare the longitude and latitude of the vehicle during driving with the high-precision comparison table to generate the position stake number; When the vehicle passes by the roadside monitoring camera, the roadside monitoring camera collects information about the vehicle and generates a video of the vehicle traveling on the road section to be monitored.

[0006] According to the above technical solution, step S2 includes the following: S2-1, according to the timestamps in the driving information corresponding to the same vehicle, extract all driving information of the vehicle when it is driving on the road section to be monitored from the earliest to the latest in the order of the timestamps, to form a driving record of the vehicle; S2-2, according to the vehicle type in the driving information, a vehicle that is traveling on the road section to be monitored and whose vehicle type is a truck is used as a marked vehicle; and the driving record of the marked vehicle is extracted as a marked driving record; Using 94GHz long-range traffic radar, the effective longitudinal detection distance can reach 1000m, and the effective lateral detection distance can reach 50m, which can meet the vehicle detection requirements of 12 lanes in both directions of the highway; it can detect and track 1024 targets at the same time, and assign an independent number to each target according to its characteristics; the radar detection accuracy error is less than 0.2m, which meets the requirements of lane-level tracking; the radar can output the data of the monitored object in real time.

[0007] According to the above technical solution, step S3 includes the following: S3-1, when the driving lane numbers of adjacent driving information in the marked driving record of the marked vehicle are different, extract the timestamp in the corresponding next driving information as the lane change time of the marked vehicle; extract the driving lane number in the corresponding next driving information as the lane change number of the marked vehicle; extract the position stake number in the corresponding next driving information as the lane change stake number of the marked vehicle; The driving information of the lane change time, lane change number and lane change stake number is extracted as the lane change information of the marked vehicle; S3-2, matching the driving information of other vehicles according to the lane change time, lane change number and lane change stake number in the lane change information, and matching the driving information that meets the following conditions: the timestamp in the driving information is the same as the lane change time in the lane change information, the driving direction in the driving information is the same as the driving direction in the lane change information, the vehicle corresponding to the driving information is located in front of the vehicle corresponding to the lane change information, and the first threshold is set to A1, and |B-B1|≤A1; wherein B1 represents the position stake number in the driving information, and B represents the lane change stake number in the lane change information; The process of determining that the vehicle corresponding to the driving information is located in front of the vehicle corresponding to the lane change information is as follows: According to the position stake numbers in the adjacent driving information in the marked driving record of the marked vehicle, the position stake number in the corresponding previous driving information is subtracted from the position stake number in the corresponding next driving information, and the positive or negative result is used as the judgment condition; if the positive or negative result of the position stake number in a certain driving information subtracted from the position stake number in the lane change information is the same as the judgment condition, it means that the vehicle corresponding to the driving information is located in front of the vehicle corresponding to the lane change information; if the positive or negative result of the position stake number in a certain driving information subtracted from the position stake number in the lane change information is not the same as the judgment condition, it means that the vehicle corresponding to the driving information is located behind the vehicle corresponding to the lane change information; S3-3, counting the driving information matched by the lane change information, and generating a matching record of the lane change information; Counting all lane change information of the marked vehicle and the matching records corresponding to each lane change information to form a data set, and obtaining an associated set of the marked vehicle; The acquired data is analyzed to obtain the lane-changing behavior of trucks and the vehicles affected by the lane-changing behavior, laying the foundation for the determination of abnormal lane-occupying behavior.

[0008] According to the above technical solution, step S4 includes the following: S4-1. Mark the lane numbers according to the number of lanes on the road section to be monitored, marking the truck driving lanes, the truck temporarily occupied lanes and the truck prohibited lanes; S4-2. If the lane change number in the associated set of the marked vehicle corresponds to a lane prohibited for trucks, then the result of a primary determination is that the marked vehicle has engaged in abnormal lane occupation behavior; S4-3. If there is no lane change number corresponding to a lane prohibited for trucks in the associated set of the marked vehicle, and there is a lane change number corresponding to a lane temporarily occupied by trucks; Extracting the lane change information of a truck temporarily occupying a lane corresponding to a lane change number in the associated set of the marked vehicle, and the next lane change information adjacent to the lane change information; Calculate the time difference between the lane change time in the lane change information and the lane change time in the next lane change information adjacent to the lane change information, set a second threshold, and if the time difference between the lane change time in the lane change information and the lane change time in the next lane change information adjacent to the lane change information is greater than the second threshold, then the result of a primary judgment is that the marked vehicle does not have an abnormal lane occupying behavior; If the time difference between the lane change time in the lane change information and the lane change time in the next lane change information adjacent to the lane change information is less than or equal to the second threshold: According to the lane change time and lane change stake number in the lane change information, and the lane change time and lane change number in the next lane change information adjacent to the lane change information, the driving information in the associated set of the marked vehicle is screened to select the driving information that meets the following conditions: the timestamp in the driving information is the same as the lane change time in the lane change information, and the driving lane number in the driving information of the vehicle is the same as the lane change number in the next lane change information adjacent to the lane change information; The position stake number in the filtered driving information is recorded as B2; it is calculated with the lane change stake number B in the lane change information, and the calculation formula is |B-B2|. According to the size of |B-B2|, the filtered driving information is sorted from small to large, and the vehicle corresponding to the driving information with the first ranking is used as the first associated vehicle of the lane change information; the vehicle corresponding to the driving information with the second ranking is used as the second associated vehicle of the lane change information; Extracting a driving record in which a lane change time in a subsequent lane change information whose timestamp is adjacent to the lane change information of the first associated vehicle is the same as the lane change time as the first driving record; extracting a driving record in which a lane change time in a subsequent lane change information whose timestamp is adjacent to the lane change information of the second associated vehicle is the same as the lane change time as the second driving record; Extracting the position stake number in the first driving record, subtracting the position stake number in the first driving record from the lane change stake number in the lane change information, and using the result as the first associated parameter; extracting the position stake number in the second driving record, subtracting the position stake number in the second driving record from the lane change stake number in the lane change information, and using the result as the second associated parameter; If the first associated parameter and the second associated parameter satisfy that the first associated parameter is greater than zero and the second associated parameter is less than zero, then the result of a judgment is that the marked vehicle has not committed abnormal road-occupying behavior; If the first associated parameter and the second associated parameter do not satisfy that the first associated parameter is greater than zero and the second associated parameter is less than zero, then the result of the first judgment is that the marked vehicle has abnormal road occupation behavior; S4-4. If all lane change numbers in the associated set of the marked vehicle correspond to lanes where trucks are traveling, then the result of a judgment is that the marked vehicle has not committed any abnormal lane-occupying behavior; According to the lane-changing behavior of trucks while driving, different lane-changing situations are divided and different analyses are performed for different situations, which reduces missed judgments, more accurately reflects the abnormal lane occupation by trucks, and improves the ability to handle traffic accidents.

[0009] According to the above technical solution, step S5 includes the following: S5-1, when the marked vehicle has abnormal road occupation behavior, according to the lane change pile number corresponding to the lane change information in the associated set, obtain the radar corresponding to the lane change pile number; according to the radar corresponding to the lane change pile number, divide the to-be-monitored section covered by the radar corresponding to the lane change pile number as the abnormal section of the marked vehicle; S5-2, according to the lane change time corresponding to the lane change information in the association set, obtaining the road information corresponding to the abnormal road section of the marked vehicle from the database; the road information includes road construction, vehicle accident, road construction pile number and vehicle accident pile number; S5-3. If, in the associated set, the lane change time of the lane change information does not involve road construction or vehicle accidents on the abnormal road section corresponding to the marked vehicle, then the result of the secondary judgment is that there is no misjudgment of the abnormal road occupation behavior of the marked vehicle; S5-4. If, in the associated set, the lane change time of the lane change information corresponds to a road construction or a vehicle accident on the abnormal road section corresponding to the marked vehicle, the distance between the lane change pile number corresponding to the lane change information in the associated set and the road construction pile number or the vehicle accident pile number is calculated, and a third threshold is set. If the distance between the lane change pile number corresponding to the lane change information in the associated set and the road construction pile number or the vehicle accident pile number is less than or equal to the third threshold, the result of the secondary judgment is that the abnormal road occupation behavior of the marked vehicle is misjudged; If, for the lane change time corresponding to the lane change information in the associated set, there is road construction or a vehicle accident on the abnormal road section corresponding to the marked vehicle, and the lane change pile number corresponding to the lane change information in the associated set and the road construction pile number or the vehicle accident pile number are greater than the third threshold, then the result of the secondary judgment is that there is no misjudgment of the abnormal lane occupying behavior of the marked vehicle; Conduct misjudgment analysis based on actual road conditions to reduce misjudgments caused by objective road conditions and improve the reliability and practicality of the system.

[0010] According to the above technical solution, step S6 includes the following: S6-1. If the result of the secondary judgment is that there is no misjudgment of the abnormal lane-occupying behavior of the marked vehicle, then when there is no lane change number corresponding to a prohibited lane for trucks in the associated set of the marked vehicle, and there is a lane change number corresponding to a lane temporarily occupied by trucks, the result of the primary judgment is that the abnormal lane-occupying behavior of the marked vehicle occurs, and an analysis is performed; The marked vehicle is recorded as an abnormal vehicle, and the lane change information corresponding to the lane change number of the truck temporarily occupying the lane in the associated set of the abnormal vehicle is recorded as the abnormal start information of the abnormal vehicle; the next lane change information adjacent to the abnormal start information corresponding to the abnormal vehicle is recorded as the abnormal end information of the abnormal vehicle; The lane changing time in the abnormal start information of the abnormal vehicle is recorded as the abnormal start time of the abnormal vehicle; the lane changing time in the abnormal end information of the abnormal vehicle is recorded as the abnormal end time of the abnormal vehicle; S6-2, obtain the matching record of the abnormal start information, and filter the driving records in the matching record. The filtering process is as follows: According to the lane change stake number of the abnormal start information and the driving information in the matching record corresponding to the abnormal start information, the absolute value of the result of subtracting the position stake number of the abnormal start information from the position stake number in a certain driving information in the matching record is calculated, and according to the lane number in the driving information in the matching record, one driving information is selected from each lane number: the absolute value of the result of subtracting the position stake number of the abnormal start information from the position stake number in the driving information is the smallest among all the driving information corresponding to the lane number in the driving information; The vehicle corresponding to the filtered driving information is used as the abnormal associated vehicle of the abnormal start information; S6-2, obtaining the driving information of the abnormality-related vehicle between the abnormality start time and the abnormality end time; If a certain abnormality-related vehicle is in the same lane as the abnormal vehicle at the abnormal start time, compare the driving speed of the abnormality-related vehicle in the driving information between the abnormal start time and the abnormal end time. If the abnormality-related vehicle has decelerated between the abnormal start time and the abnormal end time, it will be regarded as the review-related vehicle of the abnormal vehicle; if the abnormality-related vehicle has not decelerated, it will not be regarded as the review-related vehicle of the abnormal vehicle; If a certain abnormal associated vehicle is in a lane with a different number from the abnormal vehicle at the abnormal start time, the lane number in the driving information of the abnormal associated vehicle between the abnormal start time and the abnormal end time is screened. If the abnormal associated vehicle has a lane change behavior to the lane with the number of the abnormal vehicle between the abnormal start time and the abnormal end time, it will be regarded as the review associated vehicle of the abnormal vehicle; if the abnormal associated vehicle has no lane change behavior to the lane with the number of the abnormal vehicle between the abnormal start time and the abnormal end time, it will not be regarded as the review associated vehicle of the abnormal vehicle; A more comprehensive analysis is conducted on abnormal vehicles related to trucks that violate the road-occupying regulations, providing more information support for the generation of review materials and further improving the accuracy of abnormal behavior judgments.

[0011] According to the above technical solution, step S7 includes the following: Extract the driving records and videos of abnormal vehicles and related vehicles from the abnormal start time to the abnormal end time to form review materials; manually review the review materials to determine whether the abnormal vehicles have abnormal road-occupying behavior. If the manual review finds that the abnormal vehicles do not have abnormal road-occupying behavior, no abnormal report is required; if the manual review finds that the abnormal vehicles have abnormal road-occupying behavior, an abnormal report needs to be made and the materials retained; Ensure the accuracy of abnormal behavior identification, reduce errors in automatic system judgment, and provide a complete chain of abnormal evidence to facilitate subsequent department processing.

[0012] Compared with the prior art, the beneficial effects achieved by the present invention are: The present invention monitors and analyzes vehicle driving data collected by millimeter-wave radar in real time, obtains key parameters such as the lane changing behavior of trucks, and combines road information to determine the abnormal road occupying behavior of trucks, effectively distinguishes between legal lane changing and abnormal road occupying behavior, and realizes the accurate identification of abnormal road occupying behavior of trucks; improves the identification ability of abnormal road occupying behavior of trucks, reduces the risk of misjudgment and missed judgment caused by manual judgment and camera monitoring, and improves the ability to handle traffic accidents as well as the real-time and accuracy of traffic management. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 It is a flow chart of a method for identifying abnormal road occupation by trucks based on roadside millimeter wave radar according to the present invention; Figure 2 It is a flow chart of the process of judging abnormal road-occupying behavior of marked vehicles according to the present invention. DETAILED DESCRIPTION

[0014] 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.

[0015] See also Figure 1 , the present invention provides a technical solution: A method for identifying abnormal road occupation by trucks based on roadside millimeter-wave radar, the method comprising the following steps: S1. Obtain the number of lanes of the road section to be monitored and number the lanes of the road section to be monitored; set up radars on the road section to be monitored and set up roadside monitoring cameras between adjacent radars, obtain driving information of vehicles on the road section to be monitored through the radars, and obtain videos of vehicles on the road section to be monitored through the roadside monitoring cameras; According to the above technical solution, step S1 includes the following: S1-1, obtaining the number of lanes of the road section to be monitored, numbering the lanes of the road section to be monitored from right to left according to the driving direction of the vehicle, and obtaining the lane number of the road section to be monitored; obtaining the monitoring range of the radar, taking the monitoring range of the radar as the interval distance between adjacent radars, and setting radars on the road section to be monitored according to the interval distance between adjacent radars, so that the monitoring ranges of all radars that have been set up cover the entire road section to be monitored; setting roadside monitoring cameras between adjacent radars according to the preset interval distance between roadside monitoring cameras; S1-2, when a vehicle enters the road section to be monitored, after the radar detects the vehicle, the authentication information of the vehicle in the database is obtained, the vehicle type of the vehicle is extracted, and the vehicle number corresponding to the vehicle is generated; When the vehicle is traveling on the road section to be monitored, the radar collects information about the vehicle once and generates a driving information corresponding to the vehicle; the driving information includes the vehicle number, vehicle type, driving lane number, position stake number, driving direction, driving speed and timestamp; the vehicle types include passenger cars and trucks; The position stake number is the highway stake number corresponding to the longitude and latitude of the vehicle during driving after conversion; wherein the highway stake number is the mileage calculated from a certain starting point along the highway route, used to identify the position on the highway, and is a linear position representation method that is convenient for engineering construction, traffic management, etc.; the radar can output the longitude and latitude of the vehicle in real time; the conversion process is to use the Beidou high-precision positioning system to form a high-precision comparison table with the highway stake number and its actual longitude and latitude, and combine the longitude and latitude of the vehicle output in real time by the radar, and compare the longitude and latitude of the vehicle during driving with the high-precision comparison table to generate the position stake number; When the vehicle passes by the roadside monitoring camera, the roadside monitoring camera collects information about the vehicle and generates a video of the vehicle traveling on the road section to be monitored.

[0016] S2, extracting all driving information of the same vehicle when it is traveling on the road section to be monitored, forming a driving record of the vehicle; marking the vehicle traveling on the road section to be monitored to obtain a marked vehicle; extracting the driving information of the marked vehicle to obtain a marked driving record; According to the above technical solution, step S2 includes the following: S2-1, according to the timestamps in the driving information corresponding to the same vehicle, extract all driving information of the vehicle when it is driving on the road section to be monitored from the earliest to the latest in the order of the timestamps, to form a driving record of the vehicle; S2-2, according to the vehicle type in the driving information, a vehicle that is traveling on the road section to be monitored and whose vehicle type is a truck is used as a marked vehicle; and the driving record of the marked vehicle is extracted as a marked driving record; Using 94GHz long-range traffic radar, the effective longitudinal detection distance can reach 1000m, and the effective lateral detection distance can reach 50m, which can meet the vehicle detection requirements of 12 lanes in both directions of the highway; it can detect and track 1024 targets at the same time, and assign an independent number to each target according to its characteristics; the radar detection accuracy error is less than 0.2m, which meets the requirements of lane-level tracking; the radar can output the data of the monitored object in real time.

[0017] S3. Determine and extract lane change information of the marked vehicle according to the marked driving record of the marked vehicle; perform matching according to the lane change information to obtain an associated set of the marked vehicles; According to the above technical solution, step S3 includes the following: S3-1, when the driving lane numbers of adjacent driving information in the marked driving record of the marked vehicle are different, extract the timestamp in the corresponding next driving information as the lane change time of the marked vehicle; extract the driving lane number in the corresponding next driving information as the lane change number of the marked vehicle; extract the position stake number in the corresponding next driving information as the lane change stake number of the marked vehicle; The driving information of the lane change time, lane change number and lane change stake number is extracted as the lane change information of the marked vehicle; S3-2, matching the driving information of other vehicles according to the lane change time, lane change number and lane change stake number in the lane change information, and matching the driving information that meets the following conditions: the timestamp in the driving information is the same as the lane change time in the lane change information, the driving direction in the driving information is the same as the driving direction in the lane change information, the vehicle corresponding to the driving information is located in front of the vehicle corresponding to the lane change information, and the first threshold is set to A1, and |B-B1|≤A1; wherein B1 represents the position stake number in the driving information, and B represents the lane change stake number in the lane change information; The process of determining that the vehicle corresponding to the driving information is located in front of the vehicle corresponding to the lane change information is as follows: According to the position stake numbers in the adjacent driving information in the marked driving record of the marked vehicle, the position stake number in the corresponding previous driving information is subtracted from the position stake number in the corresponding next driving information, and the positive or negative result is used as the judgment condition; if the positive or negative result of the position stake number in a certain driving information subtracted from the position stake number in the lane change information is the same as the judgment condition, it means that the vehicle corresponding to the driving information is located in front of the vehicle corresponding to the lane change information; if the positive or negative result of the position stake number in a certain driving information subtracted from the position stake number in the lane change information is not the same as the judgment condition, it means that the vehicle corresponding to the driving information is located behind the vehicle corresponding to the lane change information; S3-3, counting the driving information matched by the lane change information, and generating a matching record of the lane change information; Counting all lane change information of the marked vehicle and the matching records corresponding to each lane change information to form a data set, and obtaining an associated set of the marked vehicle; The acquired data is analyzed to obtain the lane-changing behavior of trucks and the vehicles affected by the lane-changing behavior, laying the foundation for the determination of abnormal lane-occupying behavior.

[0018] S4. Based on the associated set of marked vehicles, the abnormal road occupation behavior of the marked vehicles is judged once and twice. Please refer to Figure 2 ; According to the above technical solution, step S4 includes the following: S4-1. Mark the lane numbers according to the number of lanes on the road section to be monitored, marking the truck driving lanes, the truck temporarily occupied lanes and the truck prohibited lanes; S4-2. If the lane change number in the associated set of the marked vehicle corresponds to a lane prohibited for trucks, then the result of a primary determination is that the marked vehicle has engaged in abnormal lane occupation behavior; S4-3. If there is no lane change number corresponding to a lane prohibited for trucks in the associated set of the marked vehicle, and there is a lane change number corresponding to a lane temporarily occupied by trucks; Extracting the lane change information of a truck temporarily occupying a lane corresponding to a lane change number in the associated set of the marked vehicle, and the next lane change information adjacent to the lane change information; Calculate the time difference between the lane change time in the lane change information and the lane change time in the next lane change information adjacent to the lane change information, set a second threshold, and if the time difference between the lane change time in the lane change information and the lane change time in the next lane change information adjacent to the lane change information is greater than the second threshold, then the result of a primary judgment is that the marked vehicle does not have an abnormal lane occupying behavior; If the time difference between the lane change time in the lane change information and the lane change time in the next lane change information adjacent to the lane change information is less than or equal to the second threshold: According to the lane change time and lane change stake number in the lane change information, and the lane change time and lane change number in the next lane change information adjacent to the lane change information, the driving information in the associated set of the marked vehicle is screened to select the driving information that meets the following conditions: the timestamp in the driving information is the same as the lane change time in the lane change information, and the driving lane number in the driving information of the vehicle is the same as the lane change number in the next lane change information adjacent to the lane change information; The position stake number in the filtered driving information is recorded as B2; it is calculated with the lane change stake number B in the lane change information, and the calculation formula is |B-B2|. According to the size of |B-B2|, the filtered driving information is sorted from small to large, and the vehicle corresponding to the driving information with the first ranking is used as the first associated vehicle of the lane change information; the vehicle corresponding to the driving information with the second ranking is used as the second associated vehicle of the lane change information; Extracting a driving record in which a lane change time in a subsequent lane change information whose timestamp is adjacent to the lane change information of the first associated vehicle is the same as the lane change time as the first driving record; extracting a driving record in which a lane change time in a subsequent lane change information whose timestamp is adjacent to the lane change information of the second associated vehicle is the same as the lane change time as the second driving record; Extracting the position stake number in the first driving record, subtracting the position stake number in the first driving record from the lane change stake number in the lane change information, and using the result as the first associated parameter; extracting the position stake number in the second driving record, subtracting the position stake number in the second driving record from the lane change stake number in the lane change information, and using the result as the second associated parameter; If the first associated parameter and the second associated parameter satisfy that the first associated parameter is greater than zero and the second associated parameter is less than zero, then the result of a judgment is that the marked vehicle has not committed abnormal road-occupying behavior; If the first associated parameter and the second associated parameter do not satisfy that the first associated parameter is greater than zero and the second associated parameter is less than zero, then the result of the first judgment is that the marked vehicle has abnormal road occupation behavior; For example: A highway has three lanes, which are respectively a truck driving lane, a truck temporarily occupied lane and a truck prohibited lane from right to left. The lane changing time corresponding to a truck changing from a truck driving lane to a truck temporarily occupied lane is T1, and the lane changing time corresponding to changing from a truck temporarily occupied lane to a truck driving lane is T2. The time difference from T1 to T2 is T3. The second threshold is set to T4, and T3 is less than or equal to T4. When T1 is obtained, the first associated vehicle and the second associated vehicle are located in the driving lane of the truck and in front of the truck; and if the first associated parameter is greater than zero and the second associated parameter is less than zero, then the result of a judgment is that the truck has not committed abnormal road occupation behavior; S4-4. If all lane change numbers in the associated set of the marked vehicle correspond to lanes where trucks are traveling, then the result of a judgment is that the marked vehicle has not committed any abnormal lane-occupying behavior; According to the lane-changing behavior of trucks while driving, different lane-changing situations are divided and different analyses are performed for different situations, which reduces missed judgments, more accurately reflects the abnormal lane occupation by trucks, and improves the ability to handle traffic accidents.

[0019] S5. When the result of the first judgment is that the marked vehicle has an abnormal road-occupying behavior, a second judgment is performed to determine whether the abnormal road-occupying behavior of the marked vehicle is a misjudgment; According to the above technical solution, step S5 includes the following: S5-1, when the marked vehicle has abnormal road occupation behavior, according to the lane change pile number corresponding to the lane change information in the associated set, obtain the radar corresponding to the lane change pile number; according to the radar corresponding to the lane change pile number, divide the to-be-monitored section covered by the radar corresponding to the lane change pile number as the abnormal section of the marked vehicle; S5-2, according to the lane change time corresponding to the lane change information in the association set, obtaining the road information corresponding to the abnormal road section of the marked vehicle from the database; the road information includes road construction, vehicle accident, road construction pile number and vehicle accident pile number; S5-3. If, in the associated set, the lane change time of the lane change information does not involve road construction or vehicle accidents on the abnormal road section corresponding to the marked vehicle, then the result of the secondary judgment is that there is no misjudgment of the abnormal road occupation behavior of the marked vehicle; S5-4. If, in the associated set, the lane change time of the lane change information corresponds to a road construction or a vehicle accident on the abnormal road section corresponding to the marked vehicle, the distance between the lane change pile number corresponding to the lane change information in the associated set and the road construction pile number or the vehicle accident pile number is calculated, and a third threshold is set. If the distance between the lane change pile number corresponding to the lane change information in the associated set and the road construction pile number or the vehicle accident pile number is less than or equal to the third threshold, the result of the secondary judgment is that the abnormal road occupation behavior of the marked vehicle is misjudged; If, for the lane change time corresponding to the lane change information in the associated set, there is road construction or a vehicle accident on the abnormal road section corresponding to the marked vehicle, and the lane change pile number corresponding to the lane change information in the associated set and the road construction pile number or the vehicle accident pile number are greater than the third threshold, then the result of the secondary judgment is that there is no misjudgment of the abnormal lane occupying behavior of the marked vehicle; Conduct misjudgment analysis based on actual road conditions to reduce misjudgments caused by objective road conditions and improve the reliability and practicality of the system.

[0020] S6. If the result of one judgment is that there is no misjudgment of the abnormal road-occupying behavior of the marked vehicle, an abnormal vehicle is generated, driving information of other vehicles traveling on the road to be monitored is obtained, abnormal associated vehicles associated with the abnormal vehicle are screened out according to the driving information of the vehicles, and rechecked associated vehicles are screened out from the abnormal associated vehicles, and the rechecked associated vehicles and the abnormal vehicles are manually rechecked together; According to the above technical solution, step S6 includes the following: S6-1. If the result of the secondary judgment is that there is no misjudgment of the abnormal lane-occupying behavior of the marked vehicle, then when there is no lane change number corresponding to a prohibited lane for trucks in the associated set of the marked vehicle, and there is a lane change number corresponding to a lane temporarily occupied by trucks, the result of the primary judgment is that the abnormal lane-occupying behavior of the marked vehicle occurs, and an analysis is performed; The marked vehicle is recorded as an abnormal vehicle, and the lane change information corresponding to the lane change number of the truck temporarily occupying the lane in the associated set of the abnormal vehicle is recorded as the abnormal start information of the abnormal vehicle; the next lane change information adjacent to the abnormal start information corresponding to the abnormal vehicle is recorded as the abnormal end information of the abnormal vehicle; The lane changing time in the abnormal start information of the abnormal vehicle is recorded as the abnormal start time of the abnormal vehicle; the lane changing time in the abnormal end information of the abnormal vehicle is recorded as the abnormal end time of the abnormal vehicle; S6-2, obtain the matching record of the abnormal start information, and filter the driving records in the matching record. The filtering process is as follows: According to the lane change stake number of the abnormal start information and the driving information in the matching record corresponding to the abnormal start information, the absolute value of the result of subtracting the position stake number of the abnormal start information from the position stake number in a certain driving information in the matching record is calculated, and according to the lane number in the driving information in the matching record, one driving information is selected from each lane number: the absolute value of the result of subtracting the position stake number of the abnormal start information from the position stake number in the driving information is the smallest among all the driving information corresponding to the lane number in the driving information; The vehicle corresponding to the filtered driving information is used as the abnormal associated vehicle of the abnormal start information; S6-2, obtaining the driving information of the abnormality-related vehicle between the abnormality start time and the abnormality end time; If a certain abnormality-related vehicle is in the same lane as the abnormal vehicle at the abnormal start time, compare the driving speed of the abnormality-related vehicle in the driving information between the abnormal start time and the abnormal end time. If the abnormality-related vehicle has decelerated between the abnormal start time and the abnormal end time, it will be regarded as the review-related vehicle of the abnormal vehicle; if the abnormality-related vehicle has not decelerated, it will not be regarded as the review-related vehicle of the abnormal vehicle; If a certain abnormal associated vehicle is in a lane with a different number from the abnormal vehicle at the abnormal start time, the lane number in the driving information of the abnormal associated vehicle between the abnormal start time and the abnormal end time is screened. If the abnormal associated vehicle has a lane change behavior to the lane with the number of the abnormal vehicle between the abnormal start time and the abnormal end time, it will be regarded as the review associated vehicle of the abnormal vehicle; if the abnormal associated vehicle has no lane change behavior to the lane with the number of the abnormal vehicle between the abnormal start time and the abnormal end time, it will not be regarded as the review associated vehicle of the abnormal vehicle; A more comprehensive analysis is conducted on abnormal vehicles related to trucks that violate the road-occupying regulations, providing more information support for the generation of review materials and further improving the accuracy of abnormal behavior judgments.

[0021] S7. Extract the driving records and videos of abnormal vehicles and review the related vehicles to form review materials; manually review the review materials, report abnormalities and retain the materials; According to the above technical solution, step S7 includes the following: Extract the driving records and videos of abnormal vehicles and related vehicles from the abnormal start time to the abnormal end time to form review materials; manually review the review materials to determine whether the abnormal vehicles have abnormal road-occupying behavior. If the manual review finds that the abnormal vehicles do not have abnormal road-occupying behavior, no abnormal report is required; if the manual review finds that the abnormal vehicles have abnormal road-occupying behavior, an abnormal report needs to be made and the materials retained; Ensure the accuracy of abnormal behavior identification, reduce errors in automatic system judgment, and provide a complete chain of abnormal evidence to facilitate subsequent department processing.

[0022] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0023] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for identifying abnormal road occupation by trucks based on roadside millimeter wave radar, characterized in that: The method comprises the following steps: S1. Obtain the number of lanes of the road section to be monitored and number the lanes of the road section to be monitored; set up radars on the road section to be monitored and set up roadside monitoring cameras between adjacent radars, obtain driving information of vehicles on the road section to be monitored through the radars, and obtain videos of vehicles on the road section to be monitored through the roadside monitoring cameras; S2, extracting all driving information of the same vehicle when it is traveling on the road section to be monitored, forming a driving record of the vehicle; marking the vehicle traveling on the road section to be monitored to obtain a marked vehicle; extracting the driving information of the marked vehicle to obtain a marked driving record; S3. Determine and extract lane change information of the marked vehicle according to the marked driving record of the marked vehicle; perform matching according to the lane change information to obtain an associated set of the marked vehicles; S4. Based on the associated set of marked vehicles, a primary judgment and a secondary judgment are made on the abnormal road-occupying behavior of the marked vehicles; S5. When the result of the first judgment is that the marked vehicle has an abnormal road-occupying behavior, a second judgment is performed to determine whether the abnormal road-occupying behavior of the marked vehicle is a misjudgment; S6. If the result of one judgment is that there is no misjudgment of the abnormal road-occupying behavior of the marked vehicle, an abnormal vehicle is generated, driving information of other vehicles traveling on the road to be monitored is obtained, abnormal associated vehicles associated with the abnormal vehicle are screened out according to the driving information of the vehicles, and rechecked associated vehicles are screened out from the abnormal associated vehicles, and the rechecked associated vehicles and the abnormal vehicles are manually rechecked together; S7. Extract the driving records and videos of abnormal vehicles and review related vehicles to form review materials; manually review the review materials, report abnormalities and retain the materials.

2. The method for identifying abnormal road occupation by trucks based on roadside millimeter wave radar according to claim 1 is characterized by: The step S1 comprises the following: S1-1. Obtain the number of lanes of the road section to be monitored, and number the lanes of the road section to be monitored from right to left according to the driving direction of the vehicle to obtain the lane number of the road section to be monitored; The monitoring range of the radar is obtained, and the monitoring range of the radar is used as the interval distance between adjacent radars. According to the interval distance between adjacent radars, radars are set on the road section to be monitored, and the monitoring range of all radars that have been set covers the entire road section to be monitored; according to the preset interval distance between roadside monitoring cameras, roadside monitoring cameras are set between adjacent radars; S1-2, when a vehicle enters the road section to be monitored, after the radar detects the vehicle, the authentication information of the vehicle in the database is obtained, the vehicle type of the vehicle is extracted, and the vehicle number corresponding to the vehicle is generated; When the vehicle is traveling on the road section to be monitored, the radar collects information about the vehicle once and generates a driving information corresponding to the vehicle; the driving information includes the vehicle number, vehicle type, driving lane number, position stake number, driving direction, driving speed and timestamp; the vehicle types include passenger cars and trucks; When the vehicle passes by the roadside monitoring camera, the roadside monitoring camera collects information about the vehicle and generates a video of the vehicle traveling on the road section to be monitored.

3. The method for identifying abnormal road occupation by trucks based on roadside millimeter wave radar according to claim 2 is characterized by: The step S2 comprises the following: S2-1, according to the timestamps in the driving information corresponding to the same vehicle, extract all driving information of the vehicle when it is driving on the road section to be monitored from the earliest to the latest in the order of the timestamps, to form a driving record of the vehicle; S2-2, according to the vehicle type in the driving information, a vehicle of truck type traveling on the road section to be monitored is used as a marked vehicle; The driving record of the marked vehicle is extracted as the marked driving record.

4. The method for identifying abnormal road occupation by trucks based on roadside millimeter wave radar according to claim 3 is characterized by: The step S3 includes the following: S3-1, when the driving lane numbers of adjacent driving information in the marked driving record of the marked vehicle are different, extract the timestamp in the corresponding next driving information as the lane change time of the marked vehicle; extract the driving lane number in the corresponding next driving information as the lane change number of the marked vehicle; extract the position stake number in the corresponding next driving information as the lane change stake number of the marked vehicle; The driving information of the lane change time, lane change number and lane change stake number is extracted as the lane change information of the marked vehicle; S3-2, matching the driving information of other vehicles according to the lane change time, lane change number and lane change stake number in the lane change information, and matching the driving information that meets the following conditions: the timestamp in the driving information is the same as the lane change time in the lane change information, the driving direction in the driving information is the same as the driving direction in the lane change information, the vehicle corresponding to the driving information is located in front of the vehicle corresponding to the lane change information, and the first threshold is set to A1, and |B-B1|≤A1; wherein B1 represents the position stake number in the driving information, and B represents the lane change stake number in the lane change information; The process of determining that the vehicle corresponding to the driving information is located in front of the vehicle corresponding to the lane change information is as follows: According to the position stake numbers in the adjacent driving information in the marked driving record of the marked vehicle, the position stake number in the corresponding previous driving information is subtracted from the position stake number in the corresponding next driving information, and the positive or negative result is used as the judgment condition; if the positive or negative result of the position stake number in a certain driving information subtracted from the position stake number in the lane change information is the same as the judgment condition, it means that the vehicle corresponding to the driving information is located in front of the vehicle corresponding to the lane change information; if the positive or negative result of the position stake number in a certain driving information subtracted from the position stake number in the lane change information is not the same as the judgment condition, it means that the vehicle corresponding to the driving information is located behind the vehicle corresponding to the lane change information; S3-3, counting the driving information matched by the lane change information, and generating a matching record of the lane change information; All lane change information of the marked vehicle and the matching records corresponding to each lane change information are counted to form a data set, and the associated set of the marked vehicle is obtained.

5. The method for identifying abnormal road occupation by trucks based on roadside millimeter wave radar according to claim 4 is characterized by: The step S4 comprises the following: S4-1. Mark the lane numbers according to the number of lanes on the road section to be monitored, marking the truck driving lanes, the truck temporarily occupied lanes and the truck prohibited lanes; S4-2. If the lane change number in the associated set of the marked vehicle corresponds to a lane prohibited for trucks, then the result of a primary determination is that the marked vehicle has engaged in abnormal lane occupation behavior; S4-3. If there is no lane change number corresponding to a lane prohibited for trucks in the associated set of the marked vehicle, and there is a lane change number corresponding to a lane temporarily occupied by trucks; Extracting the lane change information of a truck temporarily occupying a lane corresponding to a lane change number in the associated set of the marked vehicle, and the next lane change information adjacent to the lane change information; Calculate the time difference between the lane change time in the lane change information and the lane change time in the next lane change information adjacent to the lane change information, set a second threshold, and if the time difference between the lane change time in the lane change information and the lane change time in the next lane change information adjacent to the lane change information is greater than the second threshold, then the result of a primary judgment is that the marked vehicle does not have an abnormal lane occupying behavior; If the time difference between the lane change time in the lane change information and the lane change time in the next lane change information adjacent to the lane change information is less than or equal to the second threshold: According to the lane change time and lane change stake number in the lane change information, and the lane change time and lane change number in the next lane change information adjacent to the lane change information, the driving information in the associated set of the marked vehicle is screened to select the driving information that meets the following conditions: the timestamp in the driving information is the same as the lane change time in the lane change information, and the driving lane number in the driving information of the vehicle is the same as the lane change number in the next lane change information adjacent to the lane change information; The position stake number in the filtered driving information is recorded as B2; it is calculated with the lane change stake number B in the lane change information, and the calculation formula is |B-B2|. According to the size of |B-B2|, the filtered driving information is sorted from small to large, and the vehicle corresponding to the driving information with the first ranking is used as the first associated vehicle of the lane change information; the vehicle corresponding to the driving information with the second ranking is used as the second associated vehicle of the lane change information; Extracting a driving record in which the lane change time in the next lane change information whose timestamp is adjacent to the lane change information in the first associated vehicle is the same as the lane change information, as the first driving record; Extracting a driving record in which the lane change time in the next lane change information whose timestamp is adjacent to the lane change information in the second associated vehicle is the same as the lane change information, as the second driving record; Extracting the position stake number in the first driving record, subtracting the position stake number in the first driving record from the lane change stake number in the lane change information, and using the result as the first associated parameter; extracting the position stake number in the second driving record, subtracting the position stake number in the second driving record from the lane change stake number in the lane change information, and using the result as the second associated parameter; If the first associated parameter and the second associated parameter satisfy that the first associated parameter is greater than zero and the second associated parameter is less than zero, then the result of a judgment is that the marked vehicle has not committed abnormal road-occupying behavior; If the first associated parameter and the second associated parameter do not satisfy that the first associated parameter is greater than zero and the second associated parameter is less than zero, then the result of the first judgment is that the marked vehicle has abnormal road occupation behavior; S4-4. If all lane change numbers in the associated set of the marked vehicle correspond to lanes for trucks, then a judgment result is that the marked vehicle has not committed any abnormal lane occupying behavior.

6. The method for identifying abnormal road occupation by trucks based on roadside millimeter wave radar according to claim 5 is characterized by: The step S5 comprises the following: S5-1, when the marked vehicle has abnormal road occupation behavior, according to the lane change pile number corresponding to the lane change information in the associated set, obtain the radar corresponding to the lane change pile number; according to the radar corresponding to the lane change pile number, divide the to-be-monitored section covered by the radar corresponding to the lane change pile number as the abnormal section of the marked vehicle; S5-2, according to the lane change time corresponding to the lane change information in the association set, obtaining the road information corresponding to the abnormal road section of the marked vehicle from the database; the road information includes road construction, vehicle accident, road construction pile number and vehicle accident pile number; S5-3. If, in the associated set, the lane change time of the lane change information does not involve road construction or vehicle accidents on the abnormal road section corresponding to the marked vehicle, then the result of the secondary judgment is that there is no misjudgment of the abnormal road occupation behavior of the marked vehicle; S5-4. If, in the associated set, the lane change time of the lane change information corresponds to a road construction or a vehicle accident on the abnormal road section corresponding to the marked vehicle, the distance between the lane change pile number corresponding to the lane change information in the associated set and the road construction pile number or the vehicle accident pile number is calculated, and a third threshold is set. If the distance between the lane change pile number corresponding to the lane change information in the associated set and the road construction pile number or the vehicle accident pile number is less than or equal to the third threshold, the result of the secondary judgment is that the abnormal road occupation behavior of the marked vehicle is misjudged; If, for the lane changing time corresponding to the lane changing information in the associated set, there is road construction or a vehicle accident on the abnormal road section corresponding to the marked vehicle, and the lane changing pile number corresponding to the lane changing information in the associated set and the road construction pile number or the vehicle accident pile number are greater than the third threshold, then the result of the secondary judgment is that there is no misjudgment of the abnormal lane occupying behavior of the marked vehicle.

7. The method for identifying abnormal road occupation by trucks based on roadside millimeter wave radar according to claim 6 is characterized by: The step S6 comprises the following: S6-1. If the result of the secondary judgment is that there is no misjudgment of the abnormal lane-occupying behavior of the marked vehicle, then when there is no lane change number corresponding to a prohibited lane for trucks in the associated set of the marked vehicle, and there is a lane change number corresponding to a lane temporarily occupied by trucks, the result of the primary judgment is that the abnormal lane-occupying behavior of the marked vehicle occurs, and an analysis is performed; The marked vehicle is recorded as an abnormal vehicle, and the lane change information corresponding to the lane change number of the truck temporarily occupying the lane in the associated set of the abnormal vehicle is recorded as the abnormal start information of the abnormal vehicle; the next lane change information adjacent to the abnormal start information corresponding to the abnormal vehicle is recorded as the abnormal end information of the abnormal vehicle; The lane changing time in the abnormal start information of the abnormal vehicle is recorded as the abnormal start time of the abnormal vehicle; the lane changing time in the abnormal end information of the abnormal vehicle is recorded as the abnormal end time of the abnormal vehicle; S6-2, obtain the matching record of the abnormal start information, and filter the driving records in the matching record. The filtering process is as follows: According to the lane change stake number of the abnormal start information and the driving information in the matching record corresponding to the abnormal start information, the absolute value of the result of subtracting the position stake number of the abnormal start information from the position stake number in a certain driving information in the matching record is calculated, and according to the lane number in the driving information in the matching record, one driving information is selected from each lane number: the absolute value of the result of subtracting the position stake number of the abnormal start information from the position stake number in the driving information is the smallest among all the driving information corresponding to the lane number in the driving information; The vehicle corresponding to the filtered driving information is used as the abnormal associated vehicle of the abnormal start information; S6-2, obtaining the driving information of the abnormality-related vehicle between the abnormality start time and the abnormality end time; If a certain abnormality-related vehicle is in the same lane as the abnormal vehicle at the abnormal start time, compare the driving speed of the abnormality-related vehicle in the driving information between the abnormal start time and the abnormal end time. If the abnormality-related vehicle has decelerated between the abnormal start time and the abnormal end time, it will be regarded as the review-related vehicle of the abnormal vehicle; if the abnormality-related vehicle has not decelerated, it will not be regarded as the review-related vehicle of the abnormal vehicle; If an abnormal associated vehicle is located in a lane with a different number from the abnormal vehicle at the abnormal start time, the lane number in the driving information of the abnormal associated vehicle between the abnormal start time and the abnormal end time will be screened. If the abnormal associated vehicle changes lanes to the lane with the same number as the abnormal vehicle between the abnormal start time and the abnormal end time, it will be regarded as a review-associated vehicle of the abnormal vehicle; if the abnormal associated vehicle does not change lanes to the lane with the same number as the abnormal vehicle between the abnormal start time and the abnormal end time, it will not be regarded as a review-associated vehicle of the abnormal vehicle.

8. The method for identifying abnormal road occupation by trucks based on roadside millimeter wave radar according to claim 7 is characterized by: The step S7 includes the following: Extract the driving records and videos of abnormal vehicles and related vehicles between the start time and the end time of the abnormality to form review materials; manually review the review materials to determine whether the abnormal vehicle has any abnormal road-occupying behavior. If the manual review is that the abnormal vehicle does not have any abnormal road-occupying behavior, there is no need to report the abnormality; if the manual review is that the abnormal vehicle has any abnormal road-occupying behavior, it is necessary to report the abnormality and retain the materials.

Images