Intelligent identification method and system for illegal reversing of vehicle

Abstract

The invention relates to the technical field of intelligent traffic systems, and discloses an intelligent recognition method and system for illegal reversing of a vehicle, and the method comprises the steps: determining a to-be-recognized vehicle which is located in a monitored road and needs to be subjected to the illegal reversing recognition of the vehicle, and determining a current vehicle information queue and a comprehensive historical vehicle information set of the monitored road; according to the current vehicle information queue and the comprehensive historical vehicle information set, judging whether an illegal reversing recognition execution condition is met or not, if yes, judging whether the to-be-recognized vehicle meets an illegal reversing state condition or not according to the current vehicle information queue and the comprehensive historical vehicle information set, and if yes, determining that the to-be-recognized vehicle is in an illegal reversing state. Visibly, the comprehensiveness and rationality of the determination mode of the illegal reversing state of the vehicle can be improved, the triggering execution timeliness and accuracy of the illegal reversing recognition operation of the vehicle are further improved, and therefore the recognition accuracy, reliability, efficiency, convenience and timeliness of the illegal reversing of the vehicle are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent transportation systems, and in particular to an intelligent identification method and system for vehicle illegal reversing. BACKGROUND

[0002] With the acceleration of urbanization, the number of motor vehicles is growing rapidly, and road traffic management is facing unprecedented pressure. Among them, illegal reversing behavior has become one of the key problems in traffic management because of its strong suddenness, high concealment and great harm.

[0003] Currently, the main identification method for vehicle illegal reversing is for staff to continuously sit in front of the monitoring screen for a long time to visually check the driving vehicles on the monitored road and subjectively judge whether it is illegal reversing. However, the subjective consciousness of the staff will be affected by many factors, such as the staff's poor mental state during vehicle illegal reversing identification, different staff's different considerations, emphases and judgment criteria for analyzing whether the same vehicle driving behavior is illegal reversing, etc. To some extent, even under the same conditions, the identification results of the same vehicle's illegal reversing phenomenon will be biased, which makes the identification efficiency, timeliness and accuracy of vehicle illegal reversing low. Therefore, it is particularly important to provide a new vehicle illegal reversing identification method to improve the identification efficiency and accuracy of vehicle illegal reversing. SUMMARY

[0004] The present application provides an intelligent identification method and system for vehicle illegal reversing, which can improve the identification accuracy, efficiency and timeliness of vehicle illegal reversing.

[0005] To solve the above technical problems, the present application discloses an intelligent identification method for vehicle illegal reversing, characterized in that the method comprises: determining a to-be-identified vehicle in a monitored road that needs to be identified for vehicle illegal reversing, determining a current vehicle information queue of the monitored road, and determining a comprehensive historical vehicle information set of the monitored road, the comprehensive historical vehicle information set comprising one or more vehicle information queues; judging whether the to-be-identified vehicle meets a preset illegal reversing identification execution condition according to the current vehicle information queue and the comprehensive historical vehicle information set; when it is judged that the to-be-identified vehicle meets the illegal reversing identification execution condition, judging whether the to-be-identified vehicle meets a preset illegal reversing state condition according to the current vehicle information queue and the comprehensive historical vehicle information set; When it is judged that the to-be-identified vehicle meets the illegal reversing condition, the state identification result of the to-be-identified vehicle is determined as the illegal reversing state.

[0006] As an optional implementation, in the first aspect of the present application, the judging whether the to-be-identified vehicle meets the preset illegal reversing condition according to the current vehicle information queue and the comprehensive historical vehicle information set comprises: performing a corresponding vehicle static state monitoring operation on the to-be-identified vehicle based on the current vehicle information queue and the comprehensive historical vehicle information set; when the vehicle static state of the to-be-identified vehicle is detected, determining a first motion state in which the to-be-identified vehicle initially appears on the monitored road and a second motion state in which the to-be-identified vehicle appears after the vehicle static state according to the current vehicle information queue and the comprehensive historical vehicle information set; judging whether the to-be-identified vehicle meets a preset abnormal reverse direction conversion driving condition according to the first motion state and the second motion state; when it is judged that the to-be-identified vehicle meets the abnormal reverse direction conversion driving condition, determining that the to-be-identified vehicle meets the preset illegal reversing condition; when it is judged that the to-be-identified vehicle does not meet the abnormal reverse direction conversion driving condition, determining that the to-be-identified vehicle does not meet the preset illegal reversing condition; wherein the first motion state and the second motion state both include a vehicle upgoing state or a vehicle downgoing state.

[0007] As an optional implementation, in the first aspect of the present application, the judging whether the to-be-identified vehicle meets the preset abnormal reverse direction conversion driving condition according to the first motion state and the second motion state comprises: determining a first driving direction according to the first motion state and a second driving direction according to the second motion state; judging whether the first driving direction matches the second driving direction; when it is judged that the first driving direction matches the second driving direction, determining that the to-be-identified vehicle does not meet the preset abnormal reverse direction conversion driving condition; when it is judged that the first driving direction does not match the second driving direction, determining that the to-be-identified vehicle meets the preset abnormal reverse direction conversion driving condition.

[0008] As an optional implementation, in the first aspect of the present application, the vehicle static state monitoring operation performed on the to-be-identified vehicle based on the current vehicle information queue and the comprehensive historical vehicle information set comprises: determining first coordinate information of the to-be-identified vehicle in a current time period and second coordinate information of the to-be-identified vehicle in a previous time period based on the current vehicle information queue and the comprehensive historical vehicle information set; calculating a moving distance of the to-be-identified vehicle according to the first coordinate information and the second coordinate information; judging whether the moving distance is greater than or equal to a preset moving distance threshold value; when it is judged that the moving distance is greater than or equal to the moving distance threshold value, determining that the to-be-identified vehicle does not appear a vehicle static state; when it is judged that the moving distance is less than the moving distance threshold value, determining that the to-be-identified vehicle appears a vehicle static state.

[0009] As an optional implementation, in the first aspect of the present application, the judging whether the to-be-identified vehicle satisfies a preset illegal reverse driving identification execution condition based on the current vehicle information queue and the comprehensive historical vehicle information set comprises: determining a collected data amount of the to-be-identified vehicle based on the current vehicle information queue and the comprehensive historical vehicle information set; judging whether the collected data amount is greater than or equal to a preset collected data amount threshold value; when it is judged that the collected data amount is greater than or equal to the collected data amount threshold value, determining that the to-be-identified vehicle satisfies the preset illegal reverse driving identification execution condition; when it is judged that the collected data amount is less than the collected data amount threshold value, determining that the to-be-identified vehicle does not satisfy the preset illegal reverse driving identification execution condition.

[0010] As an optional implementation, in the first aspect of the present application, the method further comprises: determining an existing vehicle identifier corresponding to the comprehensive vehicle information set; determining a real-time vehicle identifier corresponding to a target vehicle currently on the monitored road, the target vehicle comprising the to-be-identified vehicle; determining a demand update type of the comprehensive vehicle information set according to the existing vehicle identifier and the real-time vehicle identifier, the demand update type comprising a content deletion type and / or a content addition type; when the demand update type comprises the content deletion type, determining a target existing vehicle identifier which does not match the real-time vehicle identifier from the existing vehicle identifiers; and performing a corresponding deletion operation on vehicle information associated with the target existing vehicle identifier in the comprehensive vehicle information set; when the demand update type comprises the content addition type, performing a corresponding content addition operation on the comprehensive vehicle information set based on the current vehicle information queue of the real-time vehicle identifier; Furthermore, the determination of the demand update type of the comprehensive vehicle information set based on the existing vehicle identifier and the real-time vehicle identifier comprises: when there is a target existing vehicle identifier which does not match the real-time vehicle identifier in the existing vehicle identifiers, determining that the demand update type of the comprehensive vehicle information set comprises the content deletion type; when the existing vehicle identifier does not comprise the real-time vehicle identifier or the existing vehicle identifier comprises the real-time vehicle identifier and the comprehensive vehicle information set does not comprise the current vehicle information queue, determining that the demand update type of the comprehensive vehicle information set comprises the content addition type.

[0011] As an optional implementation, in the first aspect of the present application, the determination of the to-be-identified vehicle which needs to be identified for vehicle illegal reversing in the monitored road and the determination of the current vehicle information queue of the monitored road comprise: performing a corresponding target detection operation on the obtained current road monitoring image of the monitored road to obtain a to-be-identified vehicle which needs to be identified for vehicle illegal reversing in the monitored road and corresponding position information and vehicle category information of the to-be-identified vehicle; performing a corresponding target tracking operation based on the position information and the vehicle category information of the to-be-identified vehicle to obtain vehicle tracking information of the to-be-identified vehicle, wherein the vehicle tracking information comprises position information, vehicle category information and a vehicle identifier; establishing a basic vehicle information queue based on the current road monitoring image; performing a corresponding information content filling operation on the basic vehicle information queue based on the vehicle tracking information to obtain the current vehicle information queue of the monitored road.

[0012] The second aspect of the present application discloses an intelligent identification system for vehicle illegal reversing, which comprises: an information determination module configured to determine a to-be-identified vehicle which needs to be identified for vehicle illegal reversing in a monitored road, to determine a current vehicle information queue of the monitored road, and to determine a comprehensive historical vehicle information set of the monitored road, wherein the comprehensive historical vehicle information set comprises one or more vehicle information queues; The execution judgment module is configured to judge whether the to-be-identified vehicle meets a preset illegal reversing identification execution condition according to the current vehicle information queue and the comprehensive historical vehicle information set. The state judgment module is configured to judge whether the to-be-identified vehicle meets a preset illegal reversing state condition according to the current vehicle information queue and the comprehensive historical vehicle information set when the execution judgment module judges that the to-be-identified vehicle meets the illegal reversing identification execution condition. The state determination module is configured to determine that the state identification result of the to-be-identified vehicle is an illegal reversing state when the state judgment module judges that the to-be-identified vehicle meets the illegal reversing state condition.

[0013] As an optional implementation, in the second aspect, the state judgment module judges whether the to-be-identified vehicle meets a preset illegal reversing state condition according to the current vehicle information queue and the comprehensive historical vehicle information set in the following manner: The to-be-identified vehicle is subjected to a corresponding vehicle stationary state monitoring operation based on the current vehicle information queue and the comprehensive historical vehicle information set. When the to-be-identified vehicle is detected to appear in a vehicle stationary state, a first motion state in which the to-be-identified vehicle initially appears on the monitored road and a second motion state in which the to-be-identified vehicle appears after appearing in the vehicle stationary state are determined according to the current vehicle information queue and the comprehensive historical vehicle information set. Whether the to-be-identified vehicle meets a preset abnormal reverse direction conversion driving condition is judged according to the first motion state and the second motion state. When it is judged that the to-be-identified vehicle meets the abnormal reverse direction conversion driving condition, it is determined that the to-be-identified vehicle meets a preset illegal reversing state condition. When it is judged that the to-be-identified vehicle does not meet the abnormal reverse direction conversion driving condition, it is determined that the to-be-identified vehicle does not meet a preset illegal reversing state condition. The first motion state and the second motion state both include a vehicle upward state or a vehicle downward state.

[0014] As an optional implementation, in the second aspect, the state judgment module judges whether the to-be-identified vehicle meets a preset illegal reversing state condition according to the first motion state and the second motion state in the following manner: A first driving direction is determined according to the first motion state, and a second driving direction is determined according to the second motion state. Whether the first driving direction matches the second driving direction is judged. when it is judged that the first driving direction matches the second driving direction, it is determined that the to-be-identified vehicle does not satisfy the preset abnormal reverse direction conversion driving condition; when it is judged that the first driving direction does not match the second driving direction, it is determined that the to-be-identified vehicle satisfies the preset abnormal reverse direction conversion driving condition.

[0015] As an optional implementation, in the second aspect, the manner in which the state judgment module performs the corresponding vehicle stationary state monitoring operation on the to-be-identified vehicle based on the current vehicle information queue and the comprehensive historical vehicle information set specifically includes: based on the current vehicle information queue and the comprehensive historical vehicle information set, determining first coordinate information of the to-be-identified vehicle in a current time period and determining second coordinate information of the to-be-identified vehicle in a previous time period; calculating a moving distance of the to-be-identified vehicle according to the first coordinate information and the second coordinate information; judging whether the moving distance is greater than or equal to a preset moving distance threshold value; when it is judged that the moving distance is greater than or equal to the moving distance threshold value, it is determined that the to-be-identified vehicle does not appear a vehicle stationary state; when it is judged that the moving distance is less than the moving distance threshold value, it is determined that the to-be-identified vehicle appears a vehicle stationary state.

[0016] As an optional implementation, in the second aspect, the manner in which the execution judgment module judges whether the to-be-identified vehicle satisfies a preset illegal reverse driving identification execution condition according to the current vehicle information queue and the comprehensive historical vehicle information set specifically includes: determining a collected data amount of the to-be-identified vehicle according to the current vehicle information queue and the comprehensive historical vehicle information set; judging whether the collected data amount is greater than or equal to a preset collected data amount threshold value; when it is judged that the collected data amount is greater than or equal to the collected data amount threshold value, it is determined that the to-be-identified vehicle satisfies the preset illegal reverse driving identification execution condition; when it is judged that the collected data amount is less than the collected data amount threshold value, it is determined that the to-be-identified vehicle does not satisfy the preset illegal reverse driving identification execution condition.

[0017] As an optional implementation, in the second aspect, the system further includes: The information set updating module is configured to determine an existing vehicle identifier corresponding to the comprehensive vehicle information set; determine a real-time vehicle identifier corresponding to a target vehicle currently on the monitored road, the target vehicle including the to-be-identified vehicle; determine a required updating type of the comprehensive vehicle information set according to the existing vehicle identifier and the real-time vehicle identifier, the required updating type including a content deletion type and / or a content addition type; when the required updating type includes the content deletion type, determine a target existing vehicle identifier that does not match the real-time vehicle identifier from the existing vehicle identifier; perform a corresponding deletion operation on vehicle information associated with the target existing vehicle identifier in the comprehensive vehicle information set; and when the required updating type includes the content addition type, perform a corresponding content incorporation addition operation on the comprehensive vehicle information set based on a current vehicle information queue of the real-time vehicle identifier.

[0018] As an optional implementation, in the second aspect of the present application, the manner in which the information set updating module determines the required updating type of the comprehensive vehicle information set according to the existing vehicle identifier and the real-time vehicle identifier specifically includes: when there is a target existing vehicle identifier that does not match the real-time vehicle identifier in the existing vehicle identifier, determining that the required updating type of the comprehensive vehicle information set includes the content deletion type; when the existing vehicle identifier does not include the real-time vehicle identifier or the existing vehicle identifier includes the real-time vehicle identifier and the comprehensive vehicle information set does not include the current vehicle information queue, determining that the required updating type of the comprehensive vehicle information set includes the content addition type.

[0019] As an optional implementation, in the second aspect of the present application, the manner in which the information determining module determines a to-be-identified vehicle that needs to be identified for vehicle illegal reverse driving on a monitored road and determines a current vehicle information queue of the monitored road specifically includes: performing a corresponding target detection operation on the obtained current road monitoring image of the monitored road to obtain a to-be-identified vehicle that needs to be identified for vehicle illegal reverse driving on the monitored road and corresponding position information and vehicle category information of the to-be-identified vehicle; performing a corresponding target tracking operation based on the position information and the vehicle category information of the to-be-identified vehicle to obtain vehicle tracking information of the to-be-identified vehicle, the vehicle tracking information including position information, vehicle category information, and a vehicle identifier; establishing a basic vehicle information queue based on the current road monitoring image; performing a corresponding information content filling operation on the basic vehicle information queue according to the vehicle tracking information to obtain the current vehicle information queue of the monitored road.

[0020] The third aspect of the present application discloses another intelligent identification system for vehicle illegal reversing, the system comprises: a memory storing executable program codes; a processor coupled with the memory; the processor invokes the executable program codes stored in the memory to execute the intelligent identification method for vehicle illegal reversing disclosed in the first aspect of the present application.

[0021] The fourth aspect of the present application discloses a computer storage medium storing computer instructions, when the computer instructions are invoked, the computer instructions are used to execute the intelligent identification method for vehicle illegal reversing disclosed in the first aspect of the present application.

[0022] Compared with the prior art, the embodiments of the present application have the following beneficial effects: In the embodiments of the present application, the to-be-identified vehicle needing to be identified for vehicle illegal reversing is determined in the monitored road, the current vehicle information queue of the monitored road is determined, and the comprehensive historical vehicle information set of the monitored road is determined, and the comprehensive historical vehicle information set comprises one or more vehicle information queues; whether the to-be-identified vehicle meets the preset illegal reversing identification execution condition is judged according to the current vehicle information queue and the comprehensive historical vehicle information set; when it is judged that the to-be-identified vehicle meets the illegal reversing identification execution condition, whether the to-be-identified vehicle meets the preset illegal reversing state condition is judged according to the current vehicle information queue and the comprehensive historical vehicle information set; when it is judged that the to-be-identified vehicle meets the illegal reversing state condition, the state identification result of the to-be-identified vehicle is determined as the illegal reversing state. It can be seen that, based on the current vehicle information queue and the comprehensive historical vehicle information set, when the to-be-identified vehicle meets the illegal reversing identification execution condition and meets the illegal reversing state condition, the state identification result of the to-be-identified vehicle is determined as the illegal reversing state, which is beneficial to improve the comprehensiveness and rationality of the vehicle illegal reversing state determination method, and further beneficial to improve the timeliness and accuracy of the triggering execution of the vehicle illegal reversing identification operation, thereby beneficial to improve the identification accuracy and reliability of the vehicle illegal reversing, and beneficial to improve the identification efficiency, convenience and timeliness of the vehicle illegal reversing. BRIEF DESCRIPTION OF DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0024] Figure 1is a flow diagram of an intelligent identification method for vehicle illegal reversing disclosed by an embodiment of the present application; Figure 2 is a flow diagram of another intelligent identification method for vehicle illegal reversing disclosed by an embodiment of the present application; Figure 3 is a structural diagram of an intelligent identification system for vehicle illegal reversing disclosed by an embodiment of the present application; Figure 4 is a structural diagram of another intelligent identification system for vehicle illegal reversing disclosed by an embodiment of the present application; Figure 5 is a structural diagram of another intelligent identification system for vehicle illegal reversing disclosed by an embodiment of the present application; Figure 6 is a flow diagram of another intelligent identification method for vehicle illegal reversing disclosed by an embodiment of the present application; Figure 7 is a schematic diagram of a road monitoring image disclosed by an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable persons skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by persons skilled in the art without creative labor fall within the scope of protection of the present application.

[0026] The terms "first", "second", and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish different objects, and are not used to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product, or end including a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed, or can optionally include other steps or units inherent to the process, method, product, or end.

[0027] In this document, the term "embodiment" means that the specific features, structures, or characteristics described in connection with the embodiment can be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily mean the same embodiment, nor is it independent or alternative to other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0028] The application discloses an intelligent identification method and system for vehicle illegal reversing, which can determine the state identification result of a to-be-identified vehicle as an illegal reversing state when the to-be-identified vehicle meets the illegal reversing identification execution condition and the illegal reversing state condition based on the current vehicle information queue and the comprehensive historical vehicle information set, thereby improving the comprehensiveness and rationality of the vehicle illegal reversing state determination mode, and further improving the timely execution and accuracy of the vehicle illegal reversing identification operation, so as to improve the identification accuracy and reliability of the vehicle illegal reversing, and improve the identification efficiency, convenience and timeliness of the vehicle illegal reversing.

[0029] Embodiment one Please refer to Figure 1 , Figure 1 is a flowchart of an intelligent identification method for vehicle illegal reversing disclosed by the application. Wherein, Figure 1 The method described can be applied to an intelligent identification system for vehicle illegal reversing, wherein the system can include a server, wherein the server includes a local server or a cloud server, and the application embodiments are not limited. As shown in Figure 1 The intelligent identification method for vehicle illegal reversing includes the following operations: 101. Determine a to-be-identified vehicle in a monitored road that needs to be identified for vehicle illegal reversing, determine a current vehicle information queue of the monitored road, and determine a comprehensive historical vehicle information set of the monitored road, wherein the comprehensive historical vehicle information set includes one or more vehicle information queues.

[0030] Optionally, the current vehicle information queue can be understood as vector <object position>All the detected and tracked Object Position elements {Position, class, object id} in the current road monitoring image of the monitored road, and the application embodiments are not limited thereto.

[0031] 102. According to the current vehicle information queue and the comprehensive historical vehicle information set, it is judged whether the to-be-identified vehicle meets the preset violation reverse identification execution condition.

[0032] Optionally, the current vehicle information queue and the comprehensive historical vehicle information set are exemplified as follows: the current vector is read in a loop <object position> <object position>That is, find the collected data of the target (i.e., the vehicle to be identified) in the comprehensive historical vehicle information set, and the embodiments of the present application are not limited.

[0033] Optionally, the illegal reversing identification execution condition can be understood as: when the collected data amount of the vehicle to be identified is greater than or equal to the corresponding collected data amount threshold, the illegal reversing identification operation of the vehicle to be identified is performed, otherwise, the monitoring data of the vehicle to be identified is continuously collected, and the embodiments of the present application are not limited.

[0034] Further optionally, when it is judged that the vehicle to be identified does not meet the preset illegal reversing identification execution condition, the comprehensive historical vehicle information set is continuously updated based on the newly obtained current road monitoring image until the collected data amount of the vehicle to be identified reaches the corresponding threshold requirement, and the corresponding illegal reversing identification execution judgment operation and illegal reversing state judgment operation are performed on the next vehicle to be identified, and the embodiments of the present application are not limited.

[0035] 103、When it is judged that the vehicle to be identified meets the illegal reversing identification execution condition, whether the vehicle to be identified meets the preset illegal reversing state condition is judged according to the current vehicle information queue and the comprehensive historical vehicle information set.

[0036] Further optionally, when it is judged that the vehicle to be identified does not meet the preset illegal reversing state condition, steps 101-102 are executed again, and the embodiments of the present application are not limited.

[0037] 104、When it is judged that the vehicle to be identified meets the illegal reversing state condition, it is determined that the state identification result of the vehicle to be identified is the illegal reversing state.

[0038] Optionally, the vehicle target is identified and tracked based on the yolov8 target detection algorithm and the ByteTrack tracking algorithm based on deep learning. The algorithm model is quantized and deployed on a low-power edge computing platform to realize real-time detection and tracking of the motor vehicle target. The position information (x, y, w, h) and category information (class) of the target in the image output by the target detection algorithm and the vehicle identification information (object id) output by the tracking algorithm are used to construct the target trajectory information structure ObjectPostion. All target trajectory information structures in one frame of road detection image are constructed into an ObjectPosition queue. The historical position information of the current target is analyzed, and whether the vehicle appears illegal reversing is judged through the historical trajectory of the vehicle target, and the embodiments of the present application are not limited.

[0039] It can be seen that the intelligent identification method for vehicle illegal reversing described in the embodiment of the application can determine that the state identification result of the to-be-identified vehicle is an illegal reversing state when the to-be-identified vehicle meets the illegal reversing identification execution condition and meets the illegal reversing state condition based on the current vehicle information queue and the comprehensive historical vehicle information set, which is beneficial to improving the comprehensiveness and rationality of the vehicle illegal reversing state determination manner, and further beneficial to improving the timely execution and accuracy of the vehicle illegal reversing identification operation, thereby beneficial to improving the identification accuracy and reliability of the vehicle illegal reversing, and beneficial to improving the identification efficiency, convenience and timeliness of the vehicle illegal reversing.

[0040] In an optional embodiment, the above determining whether the to-be-identified vehicle meets the preset illegal reversing state condition according to the current vehicle information queue and the comprehensive historical vehicle information set can include: performing a corresponding vehicle stationary state monitoring operation on the to-be-identified vehicle based on the current vehicle information queue and the comprehensive historical vehicle information set; when detecting that the to-be-identified vehicle appears in a vehicle stationary state, determining a first motion state in which the to-be-identified vehicle initially appears on the monitored road and a second motion state in which the to-be-identified vehicle appears after appearing in the vehicle stationary state according to the current vehicle information queue and the comprehensive historical vehicle information set; determining whether the to-be-identified vehicle meets a preset abnormal reverse direction conversion driving condition according to the first motion state and the second motion state; when it is determined that the to-be-identified vehicle meets the abnormal reverse direction conversion driving condition, determining that the to-be-identified vehicle meets the preset illegal reversing state condition; when it is determined that the to-be-identified vehicle does not meet the abnormal reverse direction conversion driving condition, determining that the to-be-identified vehicle does not meet the preset illegal reversing state condition; wherein the first motion state and the second motion state both include a vehicle upward state or a vehicle downward state.

[0041] Optionally, the vehicle initially appears in a picture in a motion state, and the initial state is necessarily in an upward or downward state (status1 or status2). When the vehicle appears in status3, the vehicle is in a stationary state. Then, when the vehicle appears in an upward or downward state again, it is determined whether the vehicle was upward or downward before being stationary. The specific determination conditions are as follows: for example, when the initial state is upward (status1 appears) and then the vehicle is stationary and downward after being stationary, it is determined that the vehicle is illegally reversing. For another example, when the initial state is downward (status2 appears) and then the vehicle is stationary and upward after being stationary, it is determined that the vehicle is illegally reversing. The embodiment of the application does not limit this.

[0042] Optionally, the first motion state in which the to-be-identified vehicle initially appears on the monitored road and the second motion state in which the to-be-identified vehicle appears after the vehicle static state is determined according to the current vehicle information queue and the comprehensive historical vehicle information set. For example, the collected vehicle information of the to-be-identified vehicle is determined according to the current vehicle information queue and the comprehensive historical vehicle information set, and the first motion state in which the to-be-identified vehicle initially appears on the monitored road and the second motion state in which the to-be-identified vehicle appears after the vehicle static state are determined according to the collected vehicle information. The embodiments of the present application are not limited.

[0043] Further optionally, the data amount of the collected vehicle information is greater than or equal to a preset data amount threshold, and the embodiments of the present application are not limited.

[0044] It can be seen that the optional embodiment can determine the initial motion state and the motion state after the vehicle is static, and then determine the violation of the reverse driving state condition satisfaction result according to the determined abnormal reverse direction conversion driving condition satisfaction result, which is beneficial to improve the comprehensiveness and rationality of the violation of the reverse driving state condition satisfaction result determination method, and then is beneficial to improve the accuracy and reliability of the determined violation of the reverse driving state condition satisfaction result, thereby being beneficial to improve the determination accuracy and reliability of the violation of the reverse driving state of the to-be-identified vehicle.

[0045] In another optional embodiment, the determination of whether the to-be-identified vehicle satisfies the preset abnormal reverse direction conversion driving condition according to the first motion state and the second motion state can include: determining a first driving direction according to the first motion state, and determining a second driving direction according to the second motion state; determining whether the first driving direction matches the second driving direction; when it is determined that the first driving direction matches the second driving direction, determining that the to-be-identified vehicle does not satisfy the preset abnormal reverse direction conversion driving condition; when it is determined that the first driving direction does not match the second driving direction, determining that the to-be-identified vehicle satisfies the preset abnormal reverse direction conversion driving condition.

[0046] Further optionally, the method can further include the following operations: when it is determined that the first driving direction does not match the second driving direction, determining a direction conversion angle of the to-be-identified vehicle according to the first driving direction and the second driving direction, and determining a current position of the to-be-identified vehicle; determining whether the to-be-identified vehicle satisfies a preset compliance turning condition according to the direction conversion angle and the current position; when it is determined that the to-be-identified vehicle satisfies the preset compliance turning condition, determining that the to-be-identified vehicle does not satisfy the preset abnormal reverse direction conversion driving condition; When it is judged that the to-be-identified vehicle does not meet the preset compliance U-turn condition, it is determined that the to-be-identified vehicle meets the preset abnormal reverse direction conversion driving condition.

[0047] Further optionally, the above judging whether the to-be-identified vehicle meets the preset compliance U-turn condition according to the direction conversion angle and the current position can include: judging whether the direction conversion angle is greater than or equal to a preset direction conversion angle threshold value; When it is judged that the direction conversion angle is greater than or equal to the preset direction conversion angle threshold value, it is judged whether the current position meets a preset reasonable U-turn position condition; When it is judged that the current position meets the preset reasonable U-turn position condition, it is determined that the to-be-identified vehicle meets the preset compliance U-turn condition; When it is judged that the direction conversion angle is less than the preset direction conversion angle threshold value, or when it is judged that the current position does not meet the preset reasonable U-turn position condition, it is determined that the to-be-identified vehicle meets the preset compliance U-turn condition.

[0048] Optionally, the direction conversion angle threshold value is set based on the angle change that can be generated by the vehicle performing a U-turn, such as the angle of performing a lane change and the angle of performing a U-turn being different, which is not limited by the embodiments of the present application.

[0049] It can be seen that the optional embodiment can determine the abnormal reverse direction conversion driving condition satisfaction result according to the matching of the determined first driving direction and the second driving direction, which is beneficial to improve the comprehensiveness and rationality of the abnormal reverse direction conversion driving condition satisfaction result determination method, and further beneficial to improve the accuracy and reliability of the determined abnormal reverse direction conversion driving condition satisfaction result.

[0050] In yet another optional embodiment, the above performing a corresponding vehicle stationary state monitoring operation on the to-be-identified vehicle based on the current vehicle information queue and the comprehensive historical vehicle information set can include: determining first coordinate information of the to-be-identified vehicle in a current time period and determining second coordinate information of the to-be-identified vehicle in a previous time period based on the current vehicle information queue and the comprehensive historical vehicle information set; calculating a moving distance of the to-be-identified vehicle according to the first coordinate information and the second coordinate information; judging whether the moving distance is greater than or equal to a preset moving distance threshold value; When it is judged that the moving distance is greater than or equal to the moving distance threshold value, it is determined that the to-be-identified vehicle does not appear a vehicle stationary state; When it is judged that the moving distance is less than the moving distance threshold value, it is determined that the to-be-identified vehicle appears a vehicle stationary state.

[0051] Optionally, the first coordinate information and the second coordinate information can be center coordinates of the target bounding box of the vehicle, including x coordinates and y coordinates, and the embodiments of the present application are not limited thereto.

[0052] Optionally, when the collected vehicle information data of the to-be-identified vehicle is greater than or equal to a corresponding threshold, the to-be-identified vehicle is determined to meet the preset violation reverse driving identification execution condition by determining a moving distance of the to-be-identified vehicle according to the current vehicle information queue and the comprehensive historical vehicle information set. n The moving distance of the to-be-identified vehicle is determined according to the formula, and the specific process is as follows:

[0053] wherein x and y are the center coordinates of the target bounding box of the vehicle, D is a set of d n , and the embodiments of the present application are not limited thereto.

[0054] Optionally, wherein s is the y value of the center coordinates of the target bounding box appearing in the current image minus the y value of the center coordinates of the target bounding box appearing in the last image, yn and y n-1 n-1 are the y values of the center coordinates of the target bounding box in the nth time and the n-1th time, and the embodiments of the present application are not limited thereto.

[0055] Optionally, the moving distance of the to-be-identified vehicle can be the moving distance of the center coordinates of the target bounding box appearing in the current image minus the center coordinates of the target bounding box appearing in the last image, and the embodiments of the present application are not limited thereto.

[0056] Optionally, status 1: when d> the first threshold value and s> 0, the vehicle is in a downward state; status 2: when d> the first threshold value and s< 0, the vehicle is in an upward state; status 3: when d< the first threshold value, regardless of s, the vehicle is in a static state, and the embodiments of the present application are not limited thereto.

[0057] It can be seen that the optional embodiment can provide a vehicle static state occurrence determination method, which determines the vehicle static state occurrence according to the comparison between the determined vehicle moving distance and the corresponding threshold value, thereby improving the comprehensiveness and rationality of the vehicle static state occurrence determination method, and further improving the accuracy and reliability of the determined vehicle static state occurrence.

[0058] In still another optional embodiment, the above-mentioned determining whether the to-be-identified vehicle meets the preset violation reverse driving identification execution condition according to the current vehicle information queue and the comprehensive historical vehicle information set can include: determining the collected data amount of the to-be-identified vehicle according to the current vehicle information queue and the comprehensive historical vehicle information set; judging whether the collected data amount is greater than or equal to a preset collected data amount threshold value; When it is judged that the collected data amount is greater than or equal to the collected data amount threshold value, it is determined that the to-be-identified vehicle meets the preset illegal reversing identification execution condition. When it is judged that the collected data amount is less than the collected data amount threshold value, it is determined that the to-be-identified vehicle does not meet the preset illegal reversing identification execution condition.

[0059] Optionally, it is judged whether the collected data amount of the current object id (i.e. the to-be-identified vehicle currently analyzed) is greater than or equal to the collected data amount threshold value, and if not, the current object id is not analyzed, and the next object id is jumped to, which is not limited by the embodiment of the application.

[0060] It can be seen that the optional embodiment can determine the illegal reversing identification execution condition meeting result of the to-be-identified vehicle according to the size comparison between the collected data amount of the to-be-identified vehicle and the corresponding threshold value, which is beneficial to improve the comprehensiveness and rationality of the illegal reversing identification execution condition meeting result determination manner, and further beneficial to improve the accuracy and reliability of the determined illegal reversing identification execution condition meeting result, thereby being beneficial to improve the timeliness and execution accuracy of the subsequent illegal reversing identification operation.

[0061] Embodiment two Please refer to Figure 2 , Figure 2 is another flowchart of the intelligent identification method for vehicle illegal reversing disclosed by the embodiment of the application. Among them, Figure 2 The method described can be applied to the intelligent identification system for vehicle illegal reversing, wherein the system can include a server, wherein the server includes a local server or a cloud server, which is not limited by the embodiment of the application. As Figure 2 shown, the intelligent identification method for vehicle illegal reversing includes the following operations: 201, determining a to-be-identified vehicle in a monitored road which needs to be identified for vehicle illegal reversing, determining a current vehicle information queue of the monitored road, and determining a comprehensive historical vehicle information set of the monitored road, wherein the comprehensive historical vehicle information set includes one or more vehicle information queues.

[0062] 202, judging whether the to-be-identified vehicle meets the preset illegal reversing identification execution condition according to the current vehicle information queue and the comprehensive historical vehicle information set.

[0063] 203, when it is judged that the to-be-identified vehicle meets the illegal reversing identification execution condition, judging whether the to-be-identified vehicle meets the preset illegal reversing state condition according to the current vehicle information queue and the comprehensive historical vehicle information set.

[0064] 204、When it is judged that the to-be-identified vehicle meets the condition of the illegal reversing state, the state identification result of the to-be-identified vehicle is determined as the illegal reversing state.

[0065] 205、Determine the existing vehicle identifier corresponding to the comprehensive vehicle information set.

[0066] Optionally, the existing vehicle identifier corresponding to the comprehensive vehicle information set can be understood as the vehicle identifier (i.e., Object id) corresponding to the stored vehicle information currently stored by the comprehensive vehicle information set, which is not limited by the embodiments of the present application.

[0067] 206、Determine the real-time vehicle identifier corresponding to the target vehicle currently on the monitored road, the target vehicle including the to-be-identified vehicle.

[0068] 207、According to the existing vehicle identifier and the real-time vehicle identifier, determine the demand update type of the comprehensive vehicle information set, the demand update type including the content deletion type and / or the content addition type.

[0069] Optionally, it is assumed that the current vehicle information queue of the real-time vehicle identifier is vector <object position>, the set of vehicle information is vector<vector <object position>>, for example: according to the current vector <object position>Update the vector<vector of Object ids inside <object position>The update method is: judging vector<vector <object position>Object id (i.e. existing vehicle identification) of the <object position>Object id (i.e. real-time vehicle identification), if not present (the reason for the absence is that the target vehicle has left the video monitoring range), delete vector<vector <object position>history data of the Object id; if exists, vector of the Object id <object position>integrate into vector<vector <object position>The embodiments of the present invention are not limited.

[0070] 208. When the demand update type includes content deletion type, identify the target existing vehicle identifier that does not match the real-time vehicle identifier from the existing vehicle identifiers; perform the corresponding deletion operation on the vehicle information associated with the target existing vehicle identifier in the comprehensive vehicle information set.

[0071] 209. When the demand update type includes the content addition type, based on the current vehicle information queue of the real-time vehicle identifier, perform the corresponding content merging and addition operation on the comprehensive vehicle information set.

[0072] Optionally, the current vehicle information queue of real-time vehicle identifiers can be incorporated into the comprehensive vehicle information set; however, this embodiment of the invention does not impose any limitations on this.

[0073] Alternatively, another flowchart for the intelligent recognition solution for illegal vehicle reversing can be found in the instruction manual. Figure 6 As shown, the embodiments of the present invention are not limited.

[0074] In this embodiment of the invention, for other descriptions of steps 201-209, please refer to the other detailed descriptions of steps 101-104 in Embodiment 1. These descriptions will not be repeated in this embodiment of the invention.

[0075] As can be seen, the embodiments of the present invention can determine the state of the vehicle to be identified as an illegal reversing state based on the current vehicle information queue and the comprehensive historical vehicle information set, when the vehicle to be identified meets the execution conditions for illegal reversing identification and the illegal reversing state conditions. This is beneficial to improving the comprehensiveness and rationality of the method for determining the illegal reversing state of a vehicle, thereby improving the timeliness and accuracy of triggering the illegal reversing identification operation, and thus improving the accuracy and reliability of illegal reversing identification, as well as the efficiency, convenience, and timeliness of illegal reversing identification. Furthermore, it can also provide a comprehensive vehicle information set update method, which performs corresponding information update operations according to the determined demand update type of the comprehensive vehicle information set. This is beneficial to improving the comprehensiveness and rationality of the comprehensive vehicle information update method, thereby improving the diversity, flexibility, and targeting of the comprehensive vehicle information update method, and thus improving the accuracy and timeliness of the comprehensive vehicle information update.

[0076] In an optional embodiment, determining the required update type of the integrated vehicle information set based on existing vehicle identifiers and real-time vehicle identifiers may include: When there is a target existing vehicle identifier that does not match the real-time vehicle identifier, the required update type for the comprehensive vehicle information set is determined to include content deletion type. When the real-time vehicle identifier is not included in the existing vehicle identifier or the existing vehicle identifier includes the real-time vehicle identifier and the comprehensive vehicle information set does not include the current vehicle information queue, it is determined that the demand update type of the comprehensive vehicle information set includes the content addition type.

[0077] Optionally, the real-time vehicle identifier is not included in the existing vehicle identifier, which can be understood as that the target vehicle has just entered the monitoring road, and therefore the comprehensive vehicle information set has not recorded the information of the target vehicle, which is not limited by the embodiments of the present application.

[0078] Optionally, the existing vehicle identifier includes the real-time vehicle identifier and the comprehensive vehicle information set does not include the current vehicle information queue, which can be understood as that the target vehicle has appeared on the monitoring road, but the comprehensive vehicle information set does not store the information of the target vehicle, which is not limited by the embodiments of the present application.

[0079] Optionally, the target existing vehicle identifier in the existing vehicle identifier does not match the real-time vehicle identifier, which can be understood as that the target existing vehicle has driven off the monitoring road, and therefore the real-time vehicle identifier does not exist the target existing vehicle identifier, which is not limited by the embodiments of the present application.

[0080] It can be seen that the optional embodiment can provide a specific determination method of the demand update type, which is beneficial to improve the comprehensiveness and rationality of the demand update type determination method, and is beneficial to improve the diversity, flexibility and pertinence of the demand update type determination method, and further is beneficial to improve the accuracy and reliability of the determined demand update type.

[0081] In another optional embodiment, the above determining the to-be-identified vehicle in the monitoring road which needs to be identified for vehicle illegal reverse driving and determining the current vehicle information queue of the monitoring road can include: performing a corresponding target detection operation on the obtained current road monitoring image of the monitoring road to obtain the to-be-identified vehicle in the monitoring road which needs to be identified for vehicle illegal reverse driving and corresponding position information and vehicle category information of the to-be-identified vehicle; performing a corresponding target tracking operation based on the position information and the vehicle category information of the to-be-identified vehicle to obtain vehicle tracking information of the to-be-identified vehicle, the vehicle tracking information including position information, vehicle category information and vehicle identifier; establishing a basic vehicle information queue based on the current road monitoring image; performing a corresponding information content filling operation on the basic vehicle information queue according to the vehicle tracking information to obtain the current vehicle information queue of the monitoring road.

[0082] Optionally, a target detection algorithm is started, a current road monitoring image is input, a yolov8 model is used to infer the current road monitoring image, vehicles (i.e. to be identified vehicles) in the image are detected, and Position and class (i.e. position information and vehicle category information) are obtained; further, Position and class are taken as inputs, a tracking algorithm is called, and the object id (i.e. vehicle identifier) of each tracking target is output; further, an Object Position queue (i.e. a basic vehicle information queue) is established, and all detected and tracked Object Position elements {Position, class, object id} of the current road monitoring image are added to the vector <object position>(i.e. the current vehicle information queue), and embodiments of the present application are not limited in this regard.

[0083] Optionally, the current road monitoring image and its corresponding target vehicle, position information, vehicle category information and vehicle identification can refer to the description of the accompanying drawings Figure 7 shown in the drawings, wherein Position(x, y, w, h) is the position information, x and y in Position(x, y, w, h) are the center coordinates of the vehicle target bounding box, w and h are the width and height of the bounding box; class is the vehicle category information, which can be divided into small cars and large cars; object id is the vehicle identification, and embodiments of the present application are not limited in this regard.

[0084] Optionally, the definition of 1 Object Position element is: {Position, class, object id}; one frame of road monitoring image will detect multiple vehicle targets, so there will be multiple Object Positions, and 1 Object Position queue (i.e. the vehicle information queue) uses vector <object position>represents, therefore, 1 Object Position queue is 1 frame road monitoring image inside all the detected vehicle information; further, use vector < vector < Object Position > > to represent the Object Position queue, and the Object Position queue is a two-dimensional array, the first dimension represents the queue number, the second dimension represents the Object Position queue information. <objectposition>The Object Position set representing the detected image (i.e., the comprehensive vehicle information set) can be understood as historical data of the Object Position, and the embodiments of the present application are not limited in this regard.

[0085] It can be seen that the optional embodiment can provide a determination manner of the to-be-identified vehicle, which is beneficial to improve the comprehensiveness and rationality of the determination manner of the to-be-identified vehicle, and further beneficial to improve the accuracy and reliability of the determined to-be-identified vehicle. In addition, the optional embodiment can also provide a determination manner of the current vehicle information queue, which is beneficial to improve the comprehensiveness and rationality of the determination manner of the current vehicle information queue, and further beneficial to improve the accuracy and reliability of the determined current vehicle information queue.

[0086] Embodiment Three Please refer to Figure 3 , Figure 3 is a structural schematic diagram of an intelligent identification system for vehicle illegal reversing disclosed by the embodiments of the present application. In the diagram, Figure 3 The system described can include a server, wherein the server includes a local server or a cloud server, and the embodiments of the present application are not limited in this regard. As Figure 3 indicated, the intelligent identification system for vehicle illegal reversing can include: An information determination module 301 is configured to determine a to-be-identified vehicle in a monitored road that needs to be identified for vehicle illegal reversing, determine a current vehicle information queue of the monitored road, and determine a comprehensive historical vehicle information set of the monitored road, wherein the comprehensive historical vehicle information set includes one or more vehicle information queues.

[0087] An execution judgment module 302 is configured to judge whether the to-be-identified vehicle meets a preset illegal reversing identification execution condition according to the current vehicle information queue and the comprehensive historical vehicle information set.

[0088] A state judgment module 303 is configured to, when the execution judgment module judges that the to-be-identified vehicle meets the illegal reversing identification execution condition, judge whether the to-be-identified vehicle meets a preset illegal reversing state condition according to the current vehicle information queue and the comprehensive historical vehicle information set.

[0089] A state determination module 304 is configured to, when the state judgment module judges that the to-be-identified vehicle meets the illegal reversing state condition, determine that a state identification result of the to-be-identified vehicle is an illegal reversing state.

[0090] It can be seen that the embodiments of the present application can provide a determination manner of a to-be-identified vehicle, which is beneficial to improve the comprehensiveness and rationality of the determination manner of the to-be-identified vehicle, and further beneficial to improve the accuracy and reliability of the determined to-be-identified vehicle. Figure 3 The intelligent identification system for vehicle illegal reversing described herein can determine that the state identification result of the to-be-identified vehicle is an illegal reversing state when the to-be-identified vehicle meets the illegal reversing identification execution condition and meets the illegal reversing state condition based on the current vehicle information queue and the comprehensive historical vehicle information set, which is beneficial to improving the comprehensiveness and rationality of the vehicle illegal reversing state determination manner, and thus is beneficial to improving the timeliness and accuracy of the triggering execution of the vehicle illegal reversing identification operation, thereby being beneficial to improving the identification accuracy and reliability of the vehicle illegal reversing, and being beneficial to improving the identification efficiency, convenience and timeliness of the vehicle illegal reversing.

[0091] In an optional embodiment, the manner in which the state judgment module 303 judges whether the to-be-identified vehicle meets the preset illegal reversing state condition according to the current vehicle information queue and the comprehensive historical vehicle information set specifically includes: performing a corresponding vehicle stationary state monitoring operation on the to-be-identified vehicle based on the current vehicle information queue and the comprehensive historical vehicle information set; when detecting that the to-be-identified vehicle appears in a vehicle stationary state, determining a first motion state in which the to-be-identified vehicle initially appears on the monitored road and a second motion state in which the to-be-identified vehicle appears after appearing in the vehicle stationary state according to the current vehicle information queue and the comprehensive historical vehicle information set; judging whether the to-be-identified vehicle meets a preset abnormal reverse direction conversion driving condition according to the first motion state and the second motion state; when judging that the to-be-identified vehicle meets the abnormal reverse direction conversion driving condition, determining that the to-be-identified vehicle meets the preset illegal reversing state condition; when judging that the to-be-identified vehicle does not meet the abnormal reverse direction conversion driving condition, determining that the to-be-identified vehicle does not meet the preset illegal reversing state condition; wherein the first motion state and the second motion state both include a vehicle upward state or a vehicle downward state.

[0092] It can be seen that the implementation Figure 4 The system described herein can determine the initial motion state and the motion state after being stationary of the vehicle, and then determine the illegal reversing state condition satisfaction result according to the determined abnormal reverse direction conversion driving condition satisfaction result, which is beneficial to improving the comprehensiveness and rationality of the illegal reversing state condition satisfaction result determination manner, and thus is beneficial to improving the accuracy and reliability of the determined illegal reversing state condition satisfaction result, thereby being beneficial to improving the determination accuracy and reliability of the illegal reversing state of the to-be-identified vehicle.

[0093] In another optional embodiment, the manner in which the state judgment module 303 judges whether the to-be-identified vehicle meets the preset abnormal reverse direction conversion driving condition according to the first motion state and the second motion state specifically includes: determine a first driving direction according to the first motion state, and determine a second driving direction according to the second motion state; determine whether the first driving direction matches the second driving direction; when it is determined that the first driving direction matches the second driving direction, determine that the to-be-identified vehicle does not satisfy the preset abnormal reverse direction conversion driving condition; when it is determined that the first driving direction does not match the second driving direction, determine that the to-be-identified vehicle satisfies the preset abnormal reverse direction conversion driving condition.

[0094] It can be seen that, by implementing the above-described system, the abnormal reverse direction conversion driving condition satisfaction result can be determined according to the matching of the first driving direction and the second driving direction, which is beneficial to improving the comprehensiveness and rationality of the abnormal reverse direction conversion driving condition satisfaction result determination manner, and further beneficial to improving the accuracy and reliability of the determined abnormal reverse direction conversion driving condition satisfaction result. Figure 4 The described system can also determine the abnormal reverse direction conversion driving condition satisfaction result according to the matching of the determined first driving direction and second driving direction, which is beneficial to improving the comprehensiveness and rationality of the abnormal reverse direction conversion driving condition satisfaction result determination manner, and further beneficial to improving the accuracy and reliability of the determined abnormal reverse direction conversion driving condition satisfaction result.

[0095] In yet another optional embodiment, the state determination module 303 determines whether the to-be-identified vehicle satisfies the preset abnormal reverse direction conversion driving condition based on the current vehicle information queue and the comprehensive historical vehicle information set in the following manner: determine first coordinate information of the to-be-identified vehicle in a current time period and determine second coordinate information of the to-be-identified vehicle in a previous time period based on the current vehicle information queue and the comprehensive historical vehicle information set; calculate a moving distance of the to-be-identified vehicle according to the first coordinate information and the second coordinate information; determine whether the moving distance is greater than or equal to a preset moving distance threshold; when it is determined that the moving distance is greater than or equal to the moving distance threshold, determine that the to-be-identified vehicle does not appear in a vehicle stationary state; when it is determined that the moving distance is less than the moving distance threshold, determine that the to-be-identified vehicle appears in a vehicle stationary state.

[0096] It can be seen that, by implementing the above-described system, the vehicle stationary state appearance condition can be determined according to the size comparison between the determined vehicle moving distance and the corresponding threshold, which is beneficial to improving the comprehensiveness and rationality of the vehicle stationary state appearance condition determination manner, and further beneficial to improving the accuracy and reliability of the determined vehicle stationary state appearance condition. Figure 4 The described system can also provide a vehicle stationary state appearance condition determination manner, which is beneficial to improving the comprehensiveness and rationality of the vehicle stationary state appearance condition determination manner, and further beneficial to improving the accuracy and reliability of the determined vehicle stationary state appearance condition.

[0097] In yet another optional embodiment, the execution determination module determines whether the to-be-identified vehicle satisfies the preset abnormal reverse direction conversion driving condition based on the current vehicle information queue and the comprehensive historical vehicle information set in the following manner: According to the current vehicle information queue and the comprehensive historical vehicle information set, the collected data amount of the to-be-identified vehicle is determined; It is judged whether the collected data amount is greater than or equal to a preset collected data amount threshold value; When it is judged that the collected data amount is greater than or equal to the collected data amount threshold value, it is determined that the to-be-identified vehicle meets the preset illegal reversing identification execution condition; When it is judged that the collected data amount is less than the collected data amount threshold value, it is determined that the to-be-identified vehicle does not meet the preset illegal reversing identification execution condition.

[0098] It can be seen that the system described in the embodiment Figure 4 The system described can also determine the illegal reversing identification execution condition meeting result of the to-be-identified vehicle according to the size comparison of the collected data amount of the to-be-identified vehicle and the corresponding threshold value, which is beneficial to improve the comprehensiveness and rationality of the illegal reversing identification execution condition meeting result determination method, and further beneficial to improve the accuracy and reliability of the determined illegal reversing identification execution condition meeting result, thereby beneficial to improve the timeliness and execution accuracy of the subsequent illegal reversing identification operation.

[0099] In yet another optional embodiment, as Figure 4 The system can also include: The information set updating module 305 is configured to determine an existing vehicle identifier corresponding to the comprehensive vehicle information set; determine a real-time vehicle identifier corresponding to a target vehicle currently on the monitored road, the target vehicle including the to-be-identified vehicle; determine a demand update type of the comprehensive vehicle information set according to the existing vehicle identifier and the real-time vehicle identifier, the demand update type including a content deletion type and / or a content addition type; when the demand update type includes the content deletion type, determine a target existing vehicle identifier that does not match the real-time vehicle identifier from the existing vehicle identifier; perform a corresponding deletion operation on the vehicle information associated with the target existing vehicle identifier in the comprehensive vehicle information set; and when the demand update type includes the content addition type, perform a corresponding content incorporation addition operation on the comprehensive vehicle information set based on the current vehicle information queue of the real-time vehicle identifier.

[0100] It can be seen that the system described in the embodiment Figure 4 The system described can also provide a comprehensive vehicle information set updating method, and perform a corresponding information updating operation according to the determined demand update type of the comprehensive vehicle information set, which is beneficial to improve the comprehensiveness and rationality of the comprehensive vehicle information updating method, and further beneficial to improve the diversity, flexibility and pertinence of the comprehensive vehicle information updating method, thereby beneficial to improve the updating accuracy and updating timeliness of the comprehensive vehicle information.

[0101] In still another optional embodiment, the manner in which the information set updating module 305 determines the required update type of the comprehensive vehicle information set according to the existing vehicle identification and the real-time vehicle identification specifically comprises: When the target existing vehicle identification that does not match the real-time vehicle identification exists in the existing vehicle identification, the required update type of the comprehensive vehicle information set is determined to include the content deletion type; When the real-time vehicle identification is not included in the existing vehicle identification or the existing vehicle identification includes the real-time vehicle identification and the comprehensive vehicle information set does not include the current vehicle information queue, the required update type of the comprehensive vehicle information set is determined to include the content addition type.

[0102] It can be seen that the implementation Figure 4 The described system can also provide a specific determination manner of the required update type, which is conducive to improving the comprehensiveness and rationality of the determination manner of the required update type, improving the diversity, flexibility and pertinence of the determination manner of the required update type, and further improving the accuracy and reliability of the determined required update type.

[0103] In still another optional embodiment, the manner in which the information set updating module 305 determines the to-be-identified vehicle that needs to be identified for vehicle illegal reversing in the monitored road and determines the current vehicle information queue of the monitored road specifically comprises: Performing a corresponding target detection operation on the obtained current road monitoring image for the monitored road to obtain the to-be-identified vehicle that needs to be identified for vehicle illegal reversing in the monitored road and corresponding position information and vehicle category information of the to-be-identified vehicle; Based on the position information and the vehicle category information of the to-be-identified vehicle, performing a corresponding target tracking operation to obtain vehicle tracking information of the to-be-identified vehicle, the vehicle tracking information including position information, vehicle category information and vehicle identification; Based on the current road monitoring image, establishing a basic vehicle information queue; According to the vehicle tracking information, performing a corresponding information content filling operation on the basic vehicle information queue to obtain the current vehicle information queue of the monitored road.

[0104] It can be seen that the implementation Figure 4 The described system can also provide a to-be-identified vehicle determination manner, which is conducive to improving the comprehensiveness and rationality of the to-be-identified vehicle determination manner, and further improving the accuracy and reliability of the determined to-be-identified vehicle. In addition, the described system can also provide a current vehicle information queue determination manner, which is conducive to improving the comprehensiveness and rationality of the current vehicle information queue determination manner, and further improving the accuracy and reliability of the determined current vehicle information queue.

[0105] Embodiment Four Please refer to Figure 5 , Figure 5 is another structural schematic diagram of an intelligent recognition system for vehicle illegal reversing disclosed by the embodiment of the present application. In the embodiment, Figure 5 The system described can include a server, wherein the server includes a local server or a cloud server, and the embodiment of the present application is not limited. As Figure 5 The system can include, as shown in the figure, a memory 401 storing executable program codes; a processor 402 coupled with the memory 401; Further, the system can further include an input interface 403 and an output interface 404 coupled with the processor 402; The processor 402 calls the executable program codes stored in the memory 401, and is used to execute the steps in the intelligent recognition method for vehicle illegal reversing described in the embodiment one or the embodiment two.

[0106] Embodiment five The embodiment of the present application discloses a computer storage medium storing a computer program for electronic data exchange, wherein the computer program makes the computer execute the steps in the intelligent recognition method for vehicle illegal reversing described in the embodiment one or the embodiment two.

[0107] Embodiment six The embodiment of the present application discloses a computer program product including a non-transitory computer readable storage medium storing a computer program, and the computer program is operable to make the computer execute the steps in the intelligent recognition method for vehicle illegal reversing described in the embodiment one or the embodiment two.

[0108] The device embodiments described above are only schematic, wherein the modules illustrated as separate components can or can not be physically separated, and the components illustrated as modules can or can not be physical modules, that is, can be located in one place, or can be distributed on multiple network modules. Part or all of the modules can be selected to achieve the purpose of the embodiment scheme according to actual needs. Those skilled in the art can understand and implement it without creative labor.

[0109] Those skilled in the art can clearly understand the implementation of the various embodiments by means of software and necessary general hardware platforms through the above specific description of the embodiments, and of course, the embodiments can also be implemented by hardware. Based on such understanding, the above technical solutions, essentially or in other words, the part of the prior art that makes a contribution, can be embodied in the form of a software product, and the computer software product can be stored in a computer readable storage medium, including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disk storage, a magnetic disk storage, a magnetic tape storage, or any other medium that can be used to carry or store data in a computer readable manner.

[0110] Finally, it should be noted that: the intelligent recognition method and system for vehicle illegal reversing disclosed by the embodiments of the present application are only the preferred embodiments of the present application, and are used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that; the technical solutions recorded in the foregoing embodiments can still be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.< / objectposition> < / object> < / object> < / object> < / object> < / object> < / object> < / object> < / object> < / object> < / object> < / object> < / object> ​< / object> < / object>

Claims

1. An intelligent identification method for vehicle illegal reversing, characterized in that, The method comprises: determining a to-be-identified vehicle in a monitored road requiring vehicle illegal reverse driving identification, determining a current vehicle information queue of the monitored road, and determining a comprehensive historical vehicle information set of the monitored road, the comprehensive historical vehicle information set comprising one or more vehicle information queues; judging whether the to-be-identified vehicle meets a preset illegal reverse driving identification execution condition according to the current vehicle information queue and the comprehensive historical vehicle information set; when it is judged that the to-be-identified vehicle meets the illegal reverse driving identification execution condition, judging whether the to-be-identified vehicle meets a preset illegal reverse driving state condition according to the current vehicle information queue and the comprehensive historical vehicle information set; when it is judged that the to-be-identified vehicle meets the illegal reverse driving state condition, determining that a state identification result of the to-be-identified vehicle is an illegal reverse driving state. 2.The intelligent identification method for vehicle illegal reversing according to claim 1, characterized in that, The judging whether the to-be-identified vehicle meets the preset illegal reverse driving state condition according to the current vehicle information queue and the comprehensive historical vehicle information set comprises: performing a corresponding vehicle stationary state monitoring operation on the to-be-identified vehicle based on the current vehicle information queue and the comprehensive historical vehicle information set; when the to-be-identified vehicle is detected to appear in a vehicle stationary state, determining a first motion state in which the to-be-identified vehicle initially appears in the monitored road and a second motion state in which the to-be-identified vehicle appears after appearing in the vehicle stationary state according to the current vehicle information queue and the comprehensive historical vehicle information set; judging whether the to-be-identified vehicle meets a preset abnormal reverse direction conversion driving condition according to the first motion state and the second motion state; when it is judged that the to-be-identified vehicle meets the abnormal reverse direction conversion driving condition, determining that the to-be-identified vehicle meets the preset illegal reverse driving state condition; when it is judged that the to-be-identified vehicle does not meet the abnormal reverse direction conversion driving condition, determining that the to-be-identified vehicle does not meet the preset illegal reverse driving state condition; wherein the first motion state and the second motion state both comprise a vehicle uplink state or a vehicle downlink state. 3.The intelligent identification method for vehicle illegal reversing according to claim 2, characterized in that, The judging whether the to-be-identified vehicle meets the preset abnormal reverse direction conversion driving condition according to the first motion state and the second motion state comprises: determining a first driving direction according to the first motion state and a second driving direction according to the second motion state; judging whether the first driving direction and the second driving direction match; when it is judged that the first driving direction and the second driving direction match, determining that the to-be-identified vehicle does not meet the preset abnormal reverse direction conversion driving condition; when it is judged that the first driving direction and the second driving direction do not match, determining that the to-be-identified vehicle meets the preset abnormal reverse direction conversion driving condition. 4.The intelligent identification method for vehicle illegal reversing according to claim 2, characterized in that, The performing the corresponding vehicle stationary state monitoring operation on the to-be-identified vehicle based on the current vehicle information queue and the comprehensive historical vehicle information set comprises: determine first coordinate information of the to-be-identified vehicle in a current time period and second coordinate information of the to-be-identified vehicle in a previous time period based on the current vehicle information queue and the comprehensive historical vehicle information set; calculate a moving distance of the to-be-identified vehicle according to the first coordinate information and the second coordinate information; determine whether the moving distance is greater than or equal to a preset moving distance threshold value; when it is determined that the moving distance is greater than or equal to the moving distance threshold value, determine that the to-be-identified vehicle does not appear in a vehicle stationary state; when it is determined that the moving distance is less than the moving distance threshold value, determine that the to-be-identified vehicle appears in a vehicle stationary state.

5. The intelligent identification method for vehicle illegal reversing according to claim 1, characterized in that, The determining whether the to-be-identified vehicle satisfies a preset illegal reversing identification execution condition based on the current vehicle information queue and the comprehensive historical vehicle information set comprises: determining a collected data amount of the to-be-identified vehicle based on the current vehicle information queue and the comprehensive historical vehicle information set; determining whether the collected data amount is greater than or equal to a preset collected data amount threshold value; when it is determined that the collected data amount is greater than or equal to the collected data amount threshold value, determining that the to-be-identified vehicle satisfies the preset illegal reversing identification execution condition; when it is determined that the collected data amount is less than the collected data amount threshold value, determining that the to-be-identified vehicle does not satisfy the preset illegal reversing identification execution condition.

6. The intelligent identification method for vehicle illegal reversing according to any one of claims 1-5, characterized in that, The method further comprises: determining an existing vehicle identifier corresponding to the comprehensive vehicle information set; determining a real-time vehicle identifier corresponding to a target vehicle currently on the monitored road, the target vehicle including the to-be-identified vehicle; determining a demand update type of the comprehensive vehicle information set based on the existing vehicle identifier and the real-time vehicle identifier, the demand update type including a content deletion type and / or a content addition type; when the demand update type includes the content deletion type, determining a target existing vehicle identifier that does not match the real-time vehicle identifier from the existing vehicle identifier; and performing a corresponding deletion operation on vehicle information associated with the target existing vehicle identifier in the comprehensive vehicle information set; when the demand update type includes the content addition type, performing a corresponding content incorporation addition operation on the comprehensive vehicle information set based on a current vehicle information queue of the real-time vehicle identifier; and the determining the demand update type of the comprehensive vehicle information set based on the existing vehicle identifier and the real-time vehicle identifier comprises: when there is a target existing vehicle identifier that does not match the real-time vehicle identifier in the existing vehicle identifier, determining that the demand update type of the comprehensive vehicle information set includes the content deletion type; when the existing vehicle identifier does not include the real-time vehicle identifier or the existing vehicle identifier includes the real-time vehicle identifier and the comprehensive vehicle information set does not include the current vehicle information queue, determining that the demand update type of the comprehensive vehicle information set includes the content addition type.

7. The intelligent identification method for vehicle illegal reversing according to claim 6, characterized in that, The method comprises the following steps: The target detection operation is performed on the obtained current road monitoring image of the monitoring road to obtain the to-be-identified vehicle in the monitoring road and the corresponding position information and vehicle category information of the to-be-identified vehicle; The target tracking operation is performed based on the position information and the vehicle category information of the to-be-identified vehicle to obtain the vehicle tracking information of the to-be-identified vehicle, wherein the vehicle tracking information comprises the position information, the vehicle category information and the vehicle identifier; The basic vehicle information queue is established based on the current road monitoring image; The information content filling operation is performed on the basic vehicle information queue based on the vehicle tracking information to obtain the current vehicle information queue of the monitoring road.

8. An intelligent identification system for vehicle illegal reversing, characterized in that, The system comprises: The information determination module is configured to determine the to-be-identified vehicle in the monitoring road and the current vehicle information queue of the monitoring road, and determine the comprehensive historical vehicle information set of the monitoring road, wherein the comprehensive historical vehicle information set comprises one or more vehicle information queues; The execution judgment module is configured to determine whether the to-be-identified vehicle meets the preset violation reversing identification execution condition based on the current vehicle information queue and the comprehensive historical vehicle information set; The state judgment module is configured to determine whether the to-be-identified vehicle meets the preset violation reversing state condition based on the current vehicle information queue and the comprehensive historical vehicle information set when the execution judgment module determines that the to-be-identified vehicle meets the violation reversing identification execution condition; The state determination module is configured to determine that the state identification result of the to-be-identified vehicle is the violation reversing state when the state judgment module determines that the to-be-identified vehicle meets the violation reversing state condition.

9. An intelligent identification system for vehicle illegal reversing, characterized in that, The system comprises: The memory stores executable program codes; The processor is coupled with the memory; The processor invokes the executable program codes stored in the memory to execute the intelligent identification method for vehicle violation reversing as claimed in any one of claims 1-7.

10. A computer storage medium, characterized in that, The computer storage medium stores computer instructions, and the computer instructions are invoked to execute the intelligent identification method for vehicle violation reversing as claimed in any one of claims 1-7.

Images