Vehicle abnormity identification method and device, computer equipment and readable storage medium

Abstract

The invention relates to a vehicle abnormity identification method and device, computer equipment, a computer readable storage medium and a computer program product, and the method comprises the steps: obtaining vehicle identification data and passing medium data of a passing vehicle collected by identification points, and enabling the identification points to be arranged at an entrance and an exit of a service area of a road, a vehicle identification device and a medium reading device are installed on the identification point, the vehicle identification device is used for collecting passing data of a passing vehicle and generating vehicle identification data of the passing vehicle according to the collected passing data, and the medium reading device is used for collecting passing medium data of the passing vehicle; fusing the vehicle identification data and the passing medium data of the same passing vehicle to obtain a fused data set of each passing vehicle; and comparing the data difference of the target passing vehicle at the entrance and the exit according to the fusion data set of the target passing vehicle so as to identify the abnormal behavior of the target passing vehicle. According to the invention, the screening efficiency of the abnormal behaviors of the vehicle in the service area can be improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent transportation technology, and in particular to a vehicle abnormality identification method, device, computer equipment, computer-readable storage medium and computer program product. Background Art

[0002] Nowadays, more and more vehicles are traveling on the expressway, and stopping at the service area has become a habit. As an important part of the expressway, the service area has the characteristics of a large number of vehicles, complex entry and exit conditions, and weak management. These characteristics also provide convenience for vehicles to evade tolls in the service area.

[0003] Traditional manual screening of these fee evasion behaviors is costly and inefficient. Summary of the invention

[0004] Based on this, it is necessary to provide a vehicle abnormality identification method, device, computer equipment, computer-readable storage medium and computer program product that can improve the efficiency of screening abnormal behavior of vehicles in service areas in response to the above technical problems.

[0005] In a first aspect, the present application provides a vehicle abnormality recognition method, comprising:

[0006] Acquiring vehicle identification data and passing medium data of a passing vehicle collected at an identification point, wherein the identification point is set at the entrance and exit of a service area of ​​a highway, and a vehicle identification device and a medium reading device are installed at the identification point, wherein the vehicle identification device is used to collect the passing data of the passing vehicle and generate the vehicle identification data of the passing vehicle according to the collected passing data, and the medium reading device is used to collect the passing medium data of the passing vehicle;

[0007] The vehicle identification data and the passing medium data of the same passing vehicle are fused to obtain a fused data set of each passing vehicle;

[0008] The data difference of the target passing vehicle at the entrance and the exit is compared according to the fused data set of the target passing vehicle to identify abnormal behavior of the target passing vehicle in the service area.

[0009] In a second aspect, the present application also provides a vehicle abnormality identification device, comprising:

[0010] an acquisition module, used to acquire vehicle identification data and passing medium data of a passing vehicle collected at an identification point, wherein the identification point is set at the entrance and exit of a service area of ​​a highway, and a vehicle identification device and a medium reading device are installed at the identification point, the vehicle identification device is used to collect the passing data of the passing vehicle and generate the vehicle identification data of the passing vehicle according to the collected passing data, and the medium reading device is used to collect the passing medium data of the passing vehicle;

[0011] A fusion module is used to fuse the vehicle identification data and the passing medium data of the same passing vehicle to obtain a fused data set of each passing vehicle;

[0012] The identification module is used to compare the data difference of the target passing vehicle at the entrance and the exit according to the fused data set of the target passing vehicle, so as to identify the abnormal behavior of the target passing vehicle in the service area.

[0013] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0014] Acquiring vehicle identification data and passing medium data of a passing vehicle collected at an identification point, wherein the identification point is set at the entrance and exit of a service area of ​​a highway, and a vehicle identification device and a medium reading device are installed at the identification point, wherein the vehicle identification device is used to collect the passing data of the passing vehicle and generate the vehicle identification data of the passing vehicle according to the collected passing data, and the medium reading device is used to collect the passing medium data of the passing vehicle;

[0015] The vehicle identification data and the passing medium data of the same passing vehicle are fused to obtain a fused data set of each passing vehicle;

[0016] The data difference of the target passing vehicle at the entrance and the exit is compared according to the fused data set of the target passing vehicle to identify abnormal behavior of the target passing vehicle in the service area.

[0017] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the following steps are implemented:

[0018] Acquiring vehicle identification data and passing medium data of a passing vehicle collected at an identification point, wherein the identification point is set at the entrance and exit of a service area of ​​a highway, and a vehicle identification device and a medium reading device are installed at the identification point, wherein the vehicle identification device is used to collect the passing data of the passing vehicle and generate the vehicle identification data of the passing vehicle according to the collected passing data, and the medium reading device is used to collect the passing medium data of the passing vehicle;

[0019] The vehicle identification data and the passing medium data of the same passing vehicle are fused to obtain a fused data set of each passing vehicle;

[0020] The data difference of the target passing vehicle at the entrance and the exit is compared according to the fused data set of the target passing vehicle to identify abnormal behavior of the target passing vehicle in the service area.

[0021] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0022] Acquiring vehicle identification data and passing medium data of a passing vehicle collected at an identification point, wherein the identification point is set at the entrance and exit of a service area of ​​a highway, and a vehicle identification device and a medium reading device are installed at the identification point, wherein the vehicle identification device is used to collect the passing data of the passing vehicle and generate the vehicle identification data of the passing vehicle according to the collected passing data, and the medium reading device is used to collect the passing medium data of the passing vehicle;

[0023] The vehicle identification data and the passing medium data of the same passing vehicle are fused to obtain a fused data set of each passing vehicle;

[0024] The data difference of the target passing vehicle at the entrance and the exit is compared according to the fused data set of the target passing vehicle to identify abnormal behavior of the target passing vehicle in the service area.

[0025] The above-mentioned vehicle abnormality identification method, device, computer equipment, computer-readable storage medium and computer program product obtain vehicle identification data and traffic medium data of passing vehicles collected by identification points, wherein the identification points are set at the entrance and exit of the service area of ​​the highway, and the identification points are equipped with vehicle identification devices and medium reading devices, the vehicle identification device is used to collect the traffic data of passing vehicles and generate the vehicle identification data of passing vehicles based on the collected traffic data, and the medium reading device is used to collect the traffic medium data of passing vehicles; the vehicle identification data and traffic medium data of the same passing vehicle are fused to obtain a fused data set of each passing vehicle; the data difference of the target passing vehicle at the entrance and exit is compared according to the fused data set of the target passing vehicle to identify the abnormal behavior of the target passing vehicle. By installing vehicle identification equipment and media reading equipment at the entrance of the service area, the vehicle identification data and the passing medium data of each passing vehicle entering the service area are obtained; by installing vehicle identification equipment and media reading equipment at the exit of the service area, the vehicle identification data and the passing medium data of each passing vehicle leaving the service area are obtained. A fused data set of the passing vehicle is generated separately based on the data of the same passing vehicle. The data differences of the passing vehicles entering and leaving the service area are analyzed in combination with the fused data set, and the abnormal behavior of the passing vehicles in the service area is automatically identified, thereby improving the screening efficiency of abnormal behavior of vehicles in the service area. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0027] FIG1 is a schematic diagram of a process flow of a vehicle abnormality identification method in one embodiment;

[0028] FIG2 is a schematic diagram of the architecture of a vehicle abnormality identification system in one embodiment;

[0029] FIG3 is a schematic diagram of the installation of equipment for identification points in one embodiment;

[0030] FIG4 is a schematic diagram of a network topology of a vehicle abnormality identification system in one embodiment;

[0031] Figure 5 A schematic diagram of a flow chart of a vehicle abnormality identification method in another embodiment;

[0032] Figure 6 is a structural block diagram of a vehicle abnormality identification device in one embodiment;

[0033] FIG7 is a diagram showing the internal structure of a computer device in one embodiment;

[0034] FIG. 8 is a diagram showing the internal structure of a computer device in another embodiment. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical scheme and advantages of the present application more clear, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used in the description of the present application. If there is a description of the first and the second, it is only for the purpose of distinguishing the technical features, and cannot be understood as indicating or implying the relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0036] In the description of this application, unless otherwise clearly defined, terms such as setting, installing, connecting, etc. should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meanings of the above terms in this application based on the specific content of the technical solution.

[0037] In an exemplary embodiment, as shown in FIG1 , a vehicle abnormality identification method is provided, comprising the following steps S202 to S206. In which:

[0038] Step S202, obtaining vehicle identification data and passing medium data of the passing vehicle collected by the identification point.

[0039] Among them, the identification points are set at the entrance and exit of the service area of ​​the highway. The highway may refer to an expressway, and a service area may be built on the highway. An identification point is set at the entrance of the service area, and an identification point is set at the exit of the service area. The identification point set at the entrance of the service area may be called an entry identification point, and the identification point set at the exit of the service area may be called an exit identification point. The identification points may be set on the entrance ramp and exit ramp of the service area, for example, one identification point is set on the entrance ramp of the service area, and one identification point is set on the exit ramp of the service area.

[0040] It should be noted that the identification points set at the entrance and exit of the service area in this application are set relatively, that is, identification points are set at the entrance and exit of the same server. This application does not limit the number of service areas on the road. There can be one or more service areas on the road. When there are multiple service areas on the road, identification points are set at the entrance and exit of each service area.

[0041] A vehicle identification device is installed at the identification point, and the vehicle identification device is used to collect the traffic data of the passing vehicles and generate the vehicle identification data of the passing vehicles according to the collected traffic data. At least one vehicle identification device can be installed at each identification point. This application does not limit the number of vehicle identification devices installed at the identification point.

[0042] The vehicle identification device may include, for example, a vehicle type identification device, a license plate number identification device, etc. The vehicle identification device is provided with an image acquisition device, and the vehicle identification device is used to collect the traffic data of the passing vehicles passing through the identification point. The image acquisition device may be, for example, a camera, and the traffic data may be traffic image data, including vehicle body images, license plate number images, etc. The vehicle body images may be, for example, vehicle front images, vehicle side images, vehicle rear images, etc., and the license plate number images are images containing the license plate number information of the passing vehicles. The vehicle identification device may be used to monitor the passing vehicles passing through the identification point.

[0043] In addition to the image acquisition device, the vehicle recognition device may also be provided with an image analysis device, which is used to analyze the passing image data of the passing vehicle acquired by the image acquisition device to generate vehicle data of the passing vehicle. For example, the image analysis device may use OCR recognition technology to extract vehicle data such as vehicle model data, axle data, and license plate number data from the passing image data.

[0044] A media reading device is also installed at the identification point, and the media reading device can be, for example, an ETC roadside unit antenna device. The media reading device is used to collect the passing medium data of the passing vehicle. At least one media reading device can be installed at each identification point, and this application does not limit the number of media reading devices installed at the identification point.

[0045] The passing medium is the passing medium used to collect fees from vehicles passing on the road in the networked toll collection system, including ETC cards, CPC cards and paper passes. Taking the ETC card as an example, it contains an electronic tag for identifying the vehicle. The electronic tag records the medium vehicle data such as the medium license plate data, medium axle data, and medium license plate data of the passing vehicle, and exchanges data with the toll collection system through special microwave communication equipment.

[0046] The medium reading device is used to collect the passing medium data of the passing vehicle, which is the medium vehicle data recorded in the passing medium of the passing vehicle, including medium vehicle license plate data, medium axle data, medium license plate data and other medium vehicle data and medium identification, etc. The medium identification can be, for example, the medium number.

[0047] The vehicle identification data collected by the identification point is the vehicle identification data generated by the vehicle identification device installed at the identification point based on the collected traffic data. The traffic medium data acquired by the identification point is the traffic medium data collected by the media reading device installed at the identification point. Among them, the vehicle identification data collected by the entry identification point is the entry vehicle identification data, the vehicle identification data collected by the exit identification point is the exit vehicle identification data, the traffic medium data collected by the entry identification point is the entry traffic medium data, and the traffic medium data collected by the exit identification point is the exit traffic medium data.

[0048] The vehicle identification data and the passing medium data collected by each identification point are uploaded and summarized to the server. Optionally, the passing vehicle data collected by the image acquisition device at each identification point can also be uploaded and summarized to the server. The passing data, as the original data of the passing vehicle, can support richer data analysis.

[0049] In one embodiment, when there are multiple service areas on a highway, the step of obtaining vehicle identification data and traffic medium data of passing vehicles collected by identification points includes: obtaining entry vehicle identification data and entry traffic medium data of passing vehicles collected by entry identification points of each service area, and obtaining exit vehicle identification data and exit traffic medium data of passing vehicles collected by exit identification points of each service area.

[0050] Step S204, fusing the vehicle identification data and the passing medium data of the same passing vehicle to obtain a fused data set of each passing vehicle.

[0051] In preparation for data analysis, it is necessary to sort out the acquired vehicle identification data and traffic cut-off data, fuse the vehicle identification data and traffic medium data of the same passing vehicles, and obtain a fused data set for each passing vehicle.

[0052] In one embodiment, the data acquired and aggregated to the server by the identification points of different service areas is very large. When the vehicle identification data and the traffic medium data of a passing vehicle come from more than one service area, the vehicle identification data and the traffic medium data of the same passing vehicle are merged to obtain a fused data set of each passing vehicle, which may include: determining the identification points corresponding to the vehicle identification data and the traffic medium data and the service areas where the corresponding identification points are located according to the collection locations of the vehicle identification data and the traffic medium data; according to the service areas corresponding to each vehicle identification data and the traffic medium data, the vehicle identification data and the traffic medium data of the same passing vehicle collected by the identification points of the same service area are merged to obtain a fused data set of each passing vehicle.

[0053] In one embodiment, a passing vehicle is considered to stop once from entering a service area to leaving the service area, and the passing vehicle may stop more than once in the service area. When the same passing vehicle stops more than once in the same service area, the vehicle identification data and the passing medium data of the same passing vehicle collected at the identification point of the same service area are fused according to the service area corresponding to each vehicle identification data and the passing medium data, and the fused data set of each passing vehicle is obtained. The fused data set of each passing vehicle may include: according to the time interval corresponding to the collection time of each vehicle identification data and the passing medium data, according to the service area and time interval corresponding to each vehicle identification data and the passing medium data, the vehicle identification data and the passing medium data of the same passing vehicle collected at the identification point of the same service area in the same time interval are fused to obtain the fused data set of each passing vehicle.

[0054] Exemplarily, the time interval may be set to be an interval with a starting point of the collection time of the entrance vehicle identification data or the entrance traffic medium and a preset stop time as the length.

[0055] The fused data set of the passing vehicle includes the vehicle identification data and the traffic medium data collected by the entrance identification point of the service area when the passing vehicle enters the service area, and the vehicle identification data and the traffic medium data collected by the exit identification point of the service area when the passing vehicle exits the service area. Optionally, the traffic data of the same passing vehicle can also be fused into the fused data set, which includes the traffic data collected by the image acquisition devices at the entrance identification point and the exit identification point, so as to achieve more diverse data analysis.

[0056] Step S206 , comparing the data difference of the target passing vehicle at the entrance and exit according to the fused data set of the target passing vehicle to identify abnormal behavior of the target passing vehicle.

[0057] The fused data set of the passing vehicles includes the entry vehicle identification data and exit traffic medium data of the passing vehicles entering the service area, and also includes the exit vehicle identification data and exit traffic medium data of the passing vehicles leaving the service area.

[0058] Based on the fused data set of each passing vehicle, it is possible to check whether each passing vehicle has abnormal behavior in the service area. Each passing vehicle can be used as a target communication vehicle in turn, or the passing vehicle to be checked can be used as a target passing vehicle, and the data difference of the target passing vehicle at the entrance and exit can be compared through the fused data set of the target passing vehicle to identify the abnormal behavior of the target communication vehicle in the service area.

[0059] Among them, abnormal behaviors may include, for example, the behavior of changing the vehicle model when the media vehicle model does not match the actual vehicle model, the behavior of replacing the axle when the media axle does not match the actual axle, the behavior of replacing the license plate when the media license plate does not match the actual license plate, the behavior of replacing the card signature when the media identification does not match the actual media identification, and the abnormal behavior of no signature when the pass medium is not set.

[0060] In one embodiment, comparing the data differences of the target passing vehicle at the entrance and exit through the fused data set of the target passing vehicle includes comparing the data differences of the entrance vehicle type identification data and the exit vehicle type identification data of the target passing vehicle, and comparing the data differences of the entrance traffic medium data and the exit traffic medium data of the target passing vehicle.

[0061] Optionally, comparing data differences may include comparing whether the data are identical or similar, whether the data error is within a certain range, etc. For example, if the vehicle type identification data collected at the entrance identification point and exit identification point of the service area by the target vehicle is identical, similar, or the data error is within a preset range, then it is determined that the target vehicle has no abnormal behavior in the service area; if the vehicle type identification data collected at the entrance identification point and exit identification point of the service area by the target vehicle is neither identical nor similar, and the data error is not within a preset range, then it is determined that the target vehicle has abnormal behavior in the service area, and the type of abnormal behavior is further determined based on the comparison result. The specific judgment criteria can be set according to actual needs, and this application does not impose any restrictions on this.

[0062] If abnormal behavior of a passing vehicle in a service area is identified, the vehicle data of the passing vehicle, such as license plate data, and the type of abnormal behavior of the passing vehicle can be uploaded to the management terminal of the highway to facilitate management by relevant personnel.

[0063] The above-mentioned vehicle abnormality identification method obtains the vehicle identification data and the passing medium data of the passing vehicles collected by the identification points, wherein the identification points are set at the entrances and exits of the service areas of the highway, and the identification points are equipped with vehicle identification devices and medium reading devices, the vehicle identification device is used to collect the passing data of the passing vehicles and generate the vehicle identification data of the passing vehicles according to the collected passing data, and the medium reading device is used to collect the passing medium data of the passing vehicles; the vehicle identification data and the passing medium data of the same passing vehicles are fused to obtain the fused data set of each passing vehicle; the data difference of the target passing vehicle at the entrance and exit is compared according to the fused data set of the target passing vehicle to identify the abnormal behavior of the target passing vehicle. By installing vehicle identification equipment and media reading equipment at the entrance of the service area, the vehicle identification data and the passing medium data of each passing vehicle entering the service area are obtained; by installing vehicle identification equipment and media reading equipment at the exit of the service area, the vehicle identification data and the passing medium data of each passing vehicle leaving the service area are obtained. A fused data set of the passing vehicle is generated separately based on the data of the same passing vehicle. The data differences of the passing vehicles entering and leaving the service area are analyzed in combination with the fused data set, and the abnormal behavior of the passing vehicles in the service area is automatically identified, thereby improving the screening efficiency of abnormal behavior of vehicles in the service area.

[0064] In one embodiment, the vehicle identification data and the passing medium data of the same passing vehicle are fused to obtain a fused data set of each passing vehicle, including:

[0065] The vehicle identification data of the same passing vehicles are determined by matching, and the vehicle identification data of the same passing vehicles are fused to obtain the fused vehicle identification data of the passing vehicles; the passing medium data of the same passing vehicles are matched according to the fused vehicle identification data, and the passing medium data and the fused vehicle identification data that meet the preset constraints are fused to obtain the fused data set of the passing vehicles.

[0066] In order to accurately check each passing vehicle, it is necessary to ensure that the fused data set of the passing vehicle contains the data of the same passing vehicle. To this end, the fused data set of the present application is obtained by fusing the vehicle identification data and the passing medium data of the same passing vehicle.

[0067] Optionally, when fusing the vehicle identification data and the traffic medium data of the same passing vehicle, the vehicle identification data of the same passing vehicle is first fused to obtain the fused vehicle identification data of the passing vehicle, and then the traffic medium data of the same passing vehicle is matched based on the fused vehicle identification data, and the matched traffic medium data is filtered using preset constraints, and the filtered traffic medium data and the fused vehicle identification data are fused into a fused data set of the passing vehicle.

[0068] Among them, when the vehicle identification data of the same passing vehicle are merged, the vehicle identification data of the same passing vehicle are first determined by matching. Each vehicle identification data can be used as the vehicle identification data to be matched in turn, and the vehicle identification data to be matched is matched with other vehicle identification data to match other vehicle identification data belonging to the same passing vehicle as the vehicle identification data to be matched.

[0069] In one embodiment, determining the vehicle identification data of the same passing vehicles by matching includes:

[0070] If at least two vehicle identification data contain license plate data, and the similarity of the license plate data contained in at least two vehicle identification data is greater than or equal to a first similarity threshold, the at least two vehicle identification data are determined to be vehicle identification data of the same passing vehicle; if at least two vehicle identification data do not contain license plate data, or the similarity of the contained license plate data is less than the first similarity threshold, vehicle characteristics of the at least two vehicle identification data are obtained, and if the similarity of the vehicle characteristics of the at least two vehicle identification data is greater than or equal to a second similarity threshold, the at least two vehicle identification data are determined to be vehicle identification data of the same passing vehicle.

[0071] When determining the vehicle identification data of the same passing vehicle through matching, it is determined whether the passing vehicle corresponding to the license plate identification data is a licensed vehicle or an unlicensed vehicle according to whether the vehicle identification data contains the license plate data. For example, when determining whether at least two vehicle identification data are vehicle identification data of the same passing vehicle, if at least two vehicle identification data contain the license plate data, it is determined that the passing vehicle corresponding to the vehicle identification data to be matched and the other vehicle identification data is a licensed vehicle, and further, the license plate data contained in the at least two vehicle identification data are subjected to license plate matching and license plate fuzzy matching. The license plate fuzzy matching may be, for example, determining whether the similarity of the license plate data contained in the two is greater than or equal to a preset first similarity threshold value. If so, it is determined that the license plate data of the at least two vehicle identification data match, and the at least two vehicle identification data may be determined as the vehicle identification data of the same passing vehicle; if not, the vehicle features of the at least two vehicle identification data are obtained, the similarity of the vehicle features of the at least two vehicle identification data is determined, and further determination is made based on the similarity of the vehicle features.

[0072] Among them, when obtaining the vehicle features of at least two vehicle identification data, the vehicle features of the vehicle identification data can be extracted from the traffic image data of the at least two vehicle identification data sources according to the image AI algorithm, and the image AI algorithm can be further used to determine the similarity of the vehicle features of the at least two vehicle identification data. If the similarity of the vehicle features of the at least two vehicle identification data is greater than or equal to the second similarity threshold, it is determined that the vehicle features of the at least two vehicle identification data match, and the at least two vehicle identification data can be determined as the vehicle identification data of the same passing vehicle. If the similarity of the vehicle features of the at least two vehicle identification data is less than the second similarity threshold, it is determined that the vehicle features of the at least two vehicle identification data do not match.

[0073] Optionally, if the at least two vehicle identification data do not both contain license plate data, the vehicle features of the at least two vehicle identification data can be directly obtained, and when the similarity of the vehicle features of the at least two vehicle identification data is greater than or equal to a second similarity threshold, the vehicle features of the at least two vehicle identification data are determined to match, and the at least two vehicle identification data are determined to be the vehicle identification data of the same passing vehicle.

[0074] In one embodiment, the vehicle identification data includes the entry vehicle identification data and the entry traffic medium data collected at the entry identification point, and the exit vehicle identification data and the exit traffic medium data collected at the exit identification point. The traffic medium data and the fused vehicle identification data that meet the preset constraint conditions are fused to obtain a fused data set of passing vehicles, including:

[0075] According to the entrance vehicle identification data in the fused vehicle identification data, the entrance traffic medium data that meets the preset constraints with the entrance vehicle identification data is matched; according to the exit vehicle identification data in the fused vehicle identification data, the exit traffic medium data that meets the preset constraints with the exit vehicle identification data is matched; the matched entrance traffic medium data and exit traffic medium data are fused with the fused vehicle identification data of the passing vehicles to obtain a fused data set of the passing vehicles.

[0076] After the vehicle identification data of the same passing vehicle are fused, the entrance medium data and exit medium data of the same passing vehicle are matched according to the obtained integrated vehicle identification data. The matching method of "entrance matches entrance, exit matches exit" is adopted during matching, that is, the constraint conditions are set in advance, and the entrance medium data that meets the preset constraint conditions with the entrance vehicle identification data is matched according to the entrance vehicle identification data in the fused vehicle identification data; and the exit medium data that meets the preset constraint conditions with the exit vehicle identification data is matched according to the exit vehicle identification data in the fused vehicle identification data.

[0077] The preset constraints include time constraints and space constraints. Among them, the time constraint includes that the collection time of vehicle identification data and traffic medium data is within the time error range, and the space constraint includes that the vehicle identification data and traffic medium data are collected at the same identification point. Since the vehicle identification device processes the traffic data into vehicle identification data immediately after collecting it, the collection time of the vehicle identification data can be considered to be equal to the time when the vehicle identification device collects the traffic data.

[0078] In one embodiment, the preset constraint condition may further include a license plate constraint condition. When matching the entry traffic medium data that satisfies the preset constraint condition with the entry vehicle identification data according to the exit vehicle identification data in the fused vehicle identification data, firstly, all the entry traffic medium data that satisfies the time constraint condition and the space constraint condition with the entry vehicle identification data are matched as the first matching candidate set, and then, according to the license plate constraint condition, the exit traffic medium data that satisfies the license plate constraint condition with the entry vehicle identification data is matched from the first matching candidate set as the entry traffic medium data that satisfies the preset constraint condition with the entry license plate identification data.

[0079] Similarly, when matching the exit vehicle identification data in the fused vehicle identification data to find the exit traffic media data that meets the preset constraints with the exit vehicle identification data, first match all the exit traffic media data that meet the time constraints and space constraints with the exit vehicle identification data as the first matching candidate set, and then match the exit traffic media data that meet the license plate constraints with the exit vehicle identification data from the second matching candidate set based on the license plate constraints as the exit traffic media data that meet the preset constraints with the exit license plate recognition data.

[0080] Among them, the license plate constraint condition includes that the similarity of the license plate data is greater than or equal to the first similarity threshold. Further, the license plate constraint condition may include that the license plate data is consistent, that is, the first similarity threshold is 100%. When the entry passage medium data that meets the license plate constraint condition with the entry vehicle identification data is matched from the first matching candidate set according to the license plate constraint condition, the entry vehicle identification data is firstly accurately matched with the entry passage medium data in the first matching candidate set, and the accurate matching is to determine whether there is entry passage medium data that is consistent with the license plate data of the entry vehicle identification data in the first matching candidate set. If so, the entry passage medium data is used as the exit passage medium data that meets the preset constraint condition with the exit license plate identification data. If not, the entry vehicle identification data is further fuzzy matched with the entry passage medium data in the first matching candidate set, and the fuzzy matching is to determine whether there is entry passage medium data in the first matching candidate set that has a similarity with the license plate data of the entry vehicle identification data that is greater than or equal to the first similarity threshold. If so, the entry passage medium data is used as the exit passage medium data that meets the preset constraint condition with the exit license plate identification data.

[0081] In the above embodiment, with time, location, and license plate number as constraints, the traffic medium data of the same passing vehicle collected at the same identification point in the same time period can be screened out to ensure that the data in the fused data set belongs to the same passing vehicle, ensure the accuracy of the fused data set, and further ensure the accuracy of the vehicle abnormal behavior analysis.

[0082] In one embodiment, the vehicle identification data includes vehicle model data, axle data and license plate data, the passing medium data includes medium vehicle model data, medium axle data and medium license plate data, and comparing the data difference of the target passing vehicle at the entrance and exit according to the fusion data set of the target passing vehicle to identify the abnormal behavior of the target passing vehicle includes:

[0083] If the entrance vehicle model data is inconsistent with the entrance medium vehicle model data, or the exit vehicle model data is inconsistent with the exit medium vehicle model data, it is determined that the vehicle model abnormal behavior of the target passing vehicle is identified in the service area; if the entrance axle data is inconsistent with the entrance medium axle data, or the exit axle data is inconsistent with the exit medium axle data, it is determined that the axle abnormal behavior of the target passing vehicle is identified in the service area; if the entrance license plate data is inconsistent with the entrance medium license plate data, or the exit license plate data is inconsistent with the exit medium license plate data, it is determined that the license plate abnormal behavior of the target passing vehicle is identified in the service area.

[0084] Since the fused data set contains both the vehicle identification data and the traffic medium data of the same passing vehicle at the entry identification point and the exit identification point, the abnormal behavior of the target passing vehicle can be identified by comparing the vehicle identification data and the traffic medium data at the same identification point.

[0085] The vehicle identification data includes vehicle model data, axle data and license plate data, and the corresponding entry vehicle identification data includes entry vehicle model data, entry axle data and entry license plate data, and the exit vehicle identification data includes exit vehicle model data, exit axle data and exit license plate data. The traffic medium data includes medium vehicle model data, medium axle data and medium license plate data, and the corresponding entry traffic medium data includes entry medium vehicle model data, entry medium axle data and entry medium license plate data, and the exit traffic medium data includes exit medium vehicle model data, exit medium axle data and exit medium license plate data.

[0086] Optionally, the license plate data includes the license plate number and the license plate color, and the medium license plate data includes the medium license plate number and the medium license plate color. The license plate data and the medium license plate data are consistent when the license plate number and the medium license plate number are consistent and the license plate color and the medium license plate color are consistent. The license plate number and the medium license plate number are inconsistent or the license plate color and the medium license plate color are inconsistent, and both can be determined as the license plate data and the medium license plate data are inconsistent.

[0087] In one embodiment, a verification mark of the target passing vehicle can be generated according to the recognition result of the target passing vehicle. Each passing vehicle is taken as a target passing vehicle. If the vehicle model data of the target passing vehicle at the same recognition point is inconsistent with the medium vehicle model data, a verification mark of "vehicle model abnormality" is generated and attached to the target passing vehicle; if the axle data of the target passing vehicle at the same recognition point is inconsistent with the medium axle data, a verification mark of "axle abnormality" is generated and attached to the target passing vehicle; if the license plate data of the target passing vehicle at the same recognition point is inconsistent with the medium license plate data, a verification mark of "license plate abnormality" is generated and attached to the target passing vehicle; if the number of passing medium data matched by the vehicle recognition data in the fusion data set of the target passing vehicle is not 1 (such as 0 or greater than 1), a verification mark of "card signature abnormality" is generated and attached to the target passing vehicle.

[0088] Furthermore, the above verification marks can be regarded as large-category verification marks. By further analyzing the abnormal behavior, more detailed sub-category verification marks can be generated and attached to the corresponding target passing vehicles. Sub-category verification marks can include "large vehicle with small mark", "truck passenger mark", "one vehicle with multiple marks", etc.

[0089] For example, if the model data of the target passing vehicle is inconsistent with the medium model data at the same identification point, the model data is compared with the medium model data. If the standard volume of the model in the model data is larger than the standard volume of the model in the medium model data, a "large vehicle with small label" verification mark is generated and attached to the corresponding target passing vehicle to mark the abnormal behavior that the target passing vehicle is actually a large vehicle but is recorded as a small vehicle in the passing medium. If the model data of the target passing vehicle is inconsistent with the medium model data at the same identification point, a verification mark can also be generated based on the specific model in the model data and the medium model data. For example, when the model data is a truck and the medium model data is a bus, a "truck with passenger label" verification mark can be generated and attached to the corresponding target passing vehicle to mark the abnormal behavior that the target passing vehicle is actually a truck but is recorded as a bus in the passing medium.

[0090] The passing medium data matched to the vehicle identification data in the fused data set of the target passing vehicle refers to the valid passing medium data existing in the fused data set.

[0091] If the number of pass medium data matched by the vehicle identification data in the fusion data set of the target passing vehicle is 0 (i.e., there is vehicle identification data in the fusion data set that does not match the pass medium data), a "vehicle without signature" verification mark is generated and attached to the target passing vehicle to mark the abnormal behavior that the target passing vehicle is not equipped with a pass medium and may evade tolls. If the number of pass medium data matched by the vehicle identification data in the fusion data set of the target passing vehicle is greater than 1 (i.e., there is vehicle identification data in the fusion data set that matches more than one set of pass medium data), a "one vehicle multiple signatures" verification mark is generated and attached to the target passing vehicle to mark the abnormal behavior that the target passing vehicle is equipped with more than one pass medium.

[0092] The various passing medium data of the passing vehicles recorded in the passing medium are closely related to the payment of the passing vehicles. By comparing the vehicle identification data and the passing medium data, the above embodiment can verify the various recorded and stored data through the real-time identification data, thereby identifying a series of abnormal behaviors that may exist in the passing vehicles and ensuring the accuracy of highway toll payment.

[0093] In one embodiment, the vehicle identification data includes vehicle model data, axle data and license plate data, and the passing medium data includes a medium identification. Comparing the data difference of the target passing vehicle at the entrance and exit according to the fused data set of the target passing vehicle to identify the abnormal behavior of the target passing vehicle includes:

[0094] If the exit vehicle model data and the entrance vehicle model data of the target passing vehicle are inconsistent, it is confirmed that the target passing vehicle has changed its vehicle model in the service area; if the exit axle data and the entrance axle data of the target passing vehicle are inconsistent, it is confirmed that the target passing vehicle has changed its axle in the service area; if the exit license plate data and the entrance license plate data of the target passing vehicle are inconsistent, it is confirmed that the target passing vehicle has changed its license plate in the service area; if the exit media identification and the entrance media identification of the target passing vehicle are inconsistent, it is confirmed that the target passing vehicle has changed its card signature in the service area; if the fused data set of the target passing vehicle contains passing media data with different media identifications, it is confirmed that the target passing vehicle has abnormal signature-free behavior in the service area.

[0095] Optionally, the license plate data includes a license plate number and a license plate color. The inconsistency between the export license plate data and the import license plate data includes that at least one of the license plate number and the license plate color in the export data and the import license plate data is inconsistent. Only when the license plate number and the license plate color in the export license plate data and the import license plate data are consistent, it is determined that the export license plate data is consistent with the import license plate data.

[0096] Passing vehicles may perform one or more abnormal behaviors in the service area. By comparing the vehicle identification data of each type, it can be determined whether the passing vehicle has the abnormal behavior corresponding to that type.

[0097] In one embodiment, the vehicle identification data includes vehicle model data and license plate data, the passing medium data includes medium vehicle model data, medium license plate data and medium identification, and comparing the data difference of the target passing vehicle at the entrance and exit according to the fusion data set of the target passing vehicle to identify the abnormal behavior of the target passing vehicle includes:

[0098] If the vehicle type in the vehicle type data is larger than the vehicle type in the medium vehicle type data at the same identification point, it is determined that the abnormal behavior of the target vehicle being a large vehicle with a small label is identified; or if the vehicle type in the vehicle type data is a truck and the vehicle type in the medium vehicle type data at the same identification point is a passenger car, it is determined that the abnormal behavior of the target vehicle being a truck with a passenger label is identified; or if the license plate data and the medium license plate data at the same identification point have different license plate numbers or license plate colors, it is determined that the abnormal behavior of the target vehicle being a license plate that does not match is identified; or if the fused data set contains vehicle identification data that is not matched to the passing medium data, it is determined that the abnormal behavior of the target vehicle being a vehicle without a signature is identified; or if the fused data set contains vehicle identification data that matches more than one set of passing medium data, it is determined that the abnormal behavior of the target vehicle being a vehicle with multiple signatures is identified; or if the exit medium identification and the entrance medium identification of the target vehicle are inconsistent, it is determined that the abnormal behavior of the target vehicle being a replaced card signature is identified.

[0099] The vehicle model data may include each vehicle model and its size and specific parameters. Vehicle models of the same category have a preset vehicle model size order. Each vehicle model and its size, specific parameters, etc. can refer to the provisions of JT / T489-2019 "Vehicle Model Classification for Toll Road Vehicle Tolls", please refer to Table 1 and Table 2.

[0100] Table 1

[0101]

[0102] Table 2

[0103]

[0104] Among them, the bus types include Class 1 bus, Class 2 bus, Class 3 bus and Class 4 bus. According to the preset bus size order, the bus sizes are as follows: Class 1 bus < Class 2 bus < Class 3 bus < Class 4 bus. From Class 1 bus to Class 4 bus, the bus size increases, and the length and the number of passengers increase.

[0105] Among them, the truck categories include Class 1 trucks, Class 2 trucks, Class 3 trucks, Class 4 trucks, Class 5 trucks and Class 6 trucks. According to the preset truck size order, the truck sizes are as follows: Class 1 trucks < Class 2 trucks < Class 3 trucks < Class 4 trucks < Class 5 trucks < Class 6 trucks. From Class 1 trucks to Class 6 trucks, the truck models increase in size, and the number of axles, vehicle length and maximum allowable gross weight increase in size.

[0106] If the vehicle type in the vehicle type data and the vehicle type in the medium vehicle type data of the same identification point are passenger vehicle models, the size relationship between the passenger vehicle model in the vehicle type data and the passenger vehicle model in the medium vehicle type data of the same identification point can be determined according to the preset passenger vehicle model size sequence; if the vehicle type in the vehicle type data and the vehicle type in the medium vehicle type data of the same identification point are truck models, the size relationship between the truck model in the vehicle type data and the truck model in the medium vehicle type data of the same identification point can be determined according to the preset truck model size sequence. In one embodiment, a verification mark of a target passing vehicle can be generated according to the recognition result of the target passing vehicle. For example, each passing vehicle is taken as a target passing vehicle. If the abnormal behavior of a large vehicle with a small label is identified as the target passing vehicle, a verification mark of "large vehicle with small label" is generated and attached to the target passing vehicle; if the abnormal behavior of a truck and passenger label is identified as the target passing vehicle, a verification mark of "truck and passenger label" is generated and attached to the target passing vehicle; if the abnormal behavior of the target passing vehicle's license plate not matching is identified, a verification mark of "license plate not matching" is generated and attached to the target passing vehicle; if the abnormal behavior of the target passing vehicle's vehicle without a signature is identified, a verification mark of "vehicle without signature" is generated and attached to the target passing vehicle; if the abnormal behavior of the target passing vehicle's vehicle with multiple signatures is identified, a verification mark of "one vehicle with multiple signatures" is generated and attached to the target passing vehicle; if the abnormal behavior of the target passing vehicle's card signature being replaced is identified, a verification mark of "card signature replaced" is generated and attached to the target passing vehicle.

[0107] Optionally, more marks may be added to passing vehicles by setting other verification methods.

[0108] It is understandable that the comparison of the vehicle identification data and the passing medium data of the same identification point, the comparison of the entry vehicle identification data and the exit vehicle identification data, and the comparison of the entry passing medium data and the exit passing medium data can be performed in parallel. For abnormal behavior identified by any comparison scheme, a corresponding verification mark can be generated and attached to the corresponding target passing vehicle.

[0109] A highway inspection result set is generated based on the inspection marks of each passing vehicle, and the inspection result set is reported to the highway management terminal to facilitate management by relevant personnel.

[0110] The present application also provides a vehicle abnormality identification system, see Figure 2. The vehicle abnormality identification and verification system includes a vehicle type identification device, an ETC roadside unit antenna device and a server arranged at the entrance and exit of the service area, wherein the server uses the vehicle abnormality analysis method provided in the present application to provide abnormal vehicle audit analysis services. The specific embodiment of the vehicle abnormality identification system is as follows:

[0111] 1. Equipment Installation

[0112] 1. Vehicle type identification equipment

[0113] As shown in Table 3, pole-type vehicle type recognition equipment is installed at the entrance and exit ramps to capture the front, side and rear images of vehicles entering and leaving the service area; and to analyze the captured images, extract multi-dimensional features of the vehicle, and output information such as license plate and vehicle type.

[0114] Table 3

[0115]

[0116] 2. ETC roadside unit antenna equipment

[0117] As shown in Table 4, ETC roadside unit antenna equipment is installed at the entrance and exit ramps to read the ETC pass medium data of vehicles entering and leaving the service area, and output information such as the medium license plate, medium vehicle model, medium axle, vehicle type, and medium number.

[0118] Table 4

[0119]

[0120] The installation positions of the devices at the entrance and exit ramps can be seen in Figure 3. Each entrance and exit of each service area is equipped with an identification point, and each identification point is equipped with a vehicle type identification device and an ETC roadside unit antenna device.

[0121] 2. Network topology

[0122] The network topology is shown in Figure 4, where the service area network of the highway is an intranet, and the vehicle type recognition device and the ETC roadside unit antenna device are used as front-end devices, which are connected to the server in the service area computer room through a wired network. The server uses the vehicle anomaly recognition method provided in this application to provide abnormal vehicle audit and analysis services. The front-end device and the server use the HTTP protocol as the communication protocol. The system management terminal (such as a PC) needs to be in the same network as the server, and the user uses the system management terminal to access the abnormal vehicle audit and analysis service UI interface to operate and view data.

[0123] 3. Abnormal Vehicle Audit and Analysis Service

[0124] The server uses the vehicle abnormality identification method provided by this application to provide abnormal vehicle audit analysis services. The server can be stored in a computer room in the service area. The abnormal vehicle audit analysis services provided by the server include:

[0125] 1. Data aggregation

[0126] All data from the vehicle type recognition devices and ETC roadside unit antenna devices installed at the entrance and exit recognition points of each service area are transmitted through the switch and collected on the server for storage.

[0127] 2. Data Fusion

[0128] The server obtains the vehicle identification data and the traffic medium data of the passing vehicles collected by the identification point, and uses the steps in the vehicle abnormality identification method provided in the embodiment of the present application to fuse the vehicle identification data and the traffic medium data of the same passing vehicle to obtain a fused data set of each passing vehicle, which can be referred to at the same time Figure 5 .

[0129] 3. Data Analysis

[0130] Please continue reading Figure 5 The server uses the steps in the vehicle anomaly identification method provided in the embodiment of the present application to compare the data differences of the passing vehicles at the entrance and exit according to the fusion data set of the target passing vehicles to identify the abnormal behavior of the target passing vehicles.

[0131] Among them, the entry vehicle identification data is obtained by the vehicle type identification device set at the entrance of the service area, the exit vehicle identification data is obtained by the vehicle type identification device set at the exit of the service area, the entry ETC traffic medium data is obtained by the ETC roadside unit antenna device at the entrance of the service area, and the exit ETC traffic medium data is obtained by the ETC roadside unit antenna device at the exit of the service area. For the obtained entry vehicle identification data and exit vehicle identification data, if both the entry license plate recognition data and the exit vehicle identification data contain license plate data (i.e., license plate-carrying vehicles), it is determined whether the entry vehicle identification data and the exit vehicle identification data meet the license plate constraint conditions, that is, the entry vehicle identification data and the exit vehicle identification data are subjected to license plate matching and license plate fuzzy matching. If the license plates of the two match, the entry vehicle identification data and the exit vehicle identification data are determined as matching vehicle identification data. If the license plates of the two do not match, the image AI algorithm is further used to determine the similarity of the vehicle features of at least two vehicle identification data, and then the matching entry vehicle identification data and exit vehicle identification data are determined. The matching entry vehicle identification data and exit vehicle identification data are used as fused vehicle identification data.

[0132] The fused vehicle identification data is further matched with the entry ETC traffic medium data and the exit ETC traffic medium data, including time-space matching and license plate number matching. Among them, according to the entry vehicle identification data in the fused vehicle identification data, time-space matching is performed with each entry ETC traffic medium data, and all entry traffic medium data that meet the time constraint and space constraint conditions with the entry vehicle identification data are matched as the first matching candidate set. Then, according to the license plate constraint condition, license plate matching is performed with the entry ETC traffic medium data in the first matching candidate set, and entry traffic medium data that is consistent with the license plate data of the entry vehicle identification data is matched from the first matching candidate set. If the license plate matching does not match a result, fuzzy license plate matching is performed, and entry traffic medium data whose similarity with the license plate data of the entry vehicle identification data is greater than or equal to the first similarity threshold is matched from the first matching candidate set.

[0133] According to the exit vehicle identification data in the fused vehicle identification data, time-space matching is performed with each exit ETC traffic medium data, and all exit traffic medium data that meet the time constraint and space constraint conditions with the exit vehicle identification data are matched as the first matching candidate set. Then, according to the license plate constraint condition, license plate matching is performed with the exit ETC traffic medium data in the first matching candidate set, and the exit traffic medium data that is consistent with the license plate data of the exit vehicle identification data is matched from the first matching candidate set. If the license plate matching does not match a result, fuzzy license plate matching is performed, and the exit traffic medium data whose similarity with the license plate data of the exit vehicle identification data is greater than or equal to the first similarity threshold is matched from the first matching candidate set.

[0134] According to the fused vehicle identification data and the matched entry and exit media data, a fused data set of the target passing vehicle can be obtained. According to the fused data set, it is possible to further analyze whether the target passing vehicle has abnormal behavior. Optionally, if the entry and exit media data or the exit media data is not matched, a "vehicle without signature" verification mark can be generated and attached to the target passing vehicle.

[0135] According to the fusion data set of the target passing vehicle, identify whether the vehicle type of the vehicle type data of the target passing vehicle at the same identification point is consistent with the vehicle type of the medium vehicle type data. If they are inconsistent, such as the vehicle type of the vehicle type data is a truck, and the vehicle type of the medium vehicle type data is a bus, then generate a "truck passenger mark" verification mark and attach it to the target passing vehicle. If the vehicle types are consistent, such as both are trucks or both are buses, further identify whether the vehicle size of the vehicle type data is consistent with the vehicle size of the medium vehicle type data. If the vehicle size is inconsistent, such as the vehicle type data is truck type 6, and the medium vehicle type data is truck type 3, then generate a "large vehicle small mark" verification mark and attach it to the target passing vehicle.

[0136] When the target passing vehicle is a licensed vehicle, if the license plate data and the medium license plate data of the same identification point in the fusion data set of the target passing vehicle have the same license plate number but different license plate colors, or the license plate numbers are different and the difference in license plate number characters exceeds a certain range, a "license plate does not match" verification mark is generated and attached to the target passing vehicle.

[0137] If there are more than two valid ETC pass data with different media numbers in the fused data set of the target vehicle, a "one vehicle, multiple signatures" verification mark is generated and attached to the target vehicle. If both the entry ETC pass data and the exit ETC pass media data in the fused data set are valid but the media numbers are inconsistent, a "change card signature" verification mark is generated and attached to the target vehicle.

[0138] The analyzed data, such as the verification marks of each target passing vehicle, can be saved in the database, and file data such as pictures can be persisted in the server disk.

[0139] The details of the above data fusion and data analysis can be found in the description of the embodiment of the above vehicle abnormality identification method, which will not be repeated here.

[0140] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0141] Based on the same inventive concept, the embodiment of the present application also provides a vehicle abnormality identification device for implementing the vehicle abnormality identification method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more vehicle abnormality identification device embodiments provided below can refer to the limitations of the vehicle abnormality identification method above, and will not be repeated here.

[0142] In an exemplary embodiment, Figure 6 As shown, a vehicle abnormality recognition device is provided, including: an acquisition module 701, a fusion module 702 and a recognition module 703, wherein:

[0143] The acquisition module 701 is used to acquire the vehicle identification data and the passing medium data of the passing vehicle collected by the identification point, wherein the identification point is set at the entrance and exit of the service area of ​​the highway, and the identification point is equipped with a vehicle identification device and a medium reading device, the vehicle identification device is used to collect the passing data of the passing vehicle and generate the vehicle identification data of the passing vehicle according to the collected passing data, and the medium reading device is used to collect the passing medium data of the passing vehicle;

[0144] A fusion module 702 is used to fuse the vehicle identification data and the passing medium data of the same passing vehicle to obtain a fused data set of each passing vehicle;

[0145] The fusion module 703 is used to compare the data difference of the target passing vehicle at the entrance and exit according to the fusion data set of the target passing vehicle to identify the abnormal behavior of the target passing vehicle.

[0146] In one embodiment, when the vehicle identification data and the passing medium data of the same passing vehicle are fused to obtain a fused data set of each passing vehicle, the fusion module 702 is further used to:

[0147] The vehicle identification data of the same passing vehicles are determined by matching, and the vehicle identification data of the same passing vehicles are fused to obtain fused vehicle identification data of the passing vehicles;

[0148] The passing medium data of the same passing vehicles are matched according to the fused vehicle identification data, and the passing medium data and the fused vehicle identification data that meet the preset constraints are fused to obtain a fused data set of the passing vehicles.

[0149] In one embodiment, when determining the vehicle identification data of the same passing vehicle through matching, the fusion module 702 is further configured to:

[0150] If at least two vehicle identification data include license plate data, and the similarity of the license plate data included in the at least two vehicle identification data is greater than or equal to a first similarity threshold, then the at least two vehicle identification data are determined to be vehicle identification data of the same passing vehicle;

[0151] If at least two vehicle identification data do not contain license plate data, or the similarity of the contained license plate data is less than a first similarity threshold, vehicle features of the at least two vehicle identification data are obtained; if the similarity of the vehicle features of the at least two vehicle identification data is greater than or equal to a second similarity threshold, the at least two vehicle identification data are determined to be vehicle identification data of the same passing vehicle.

[0152] In one embodiment, the vehicle identification data includes entry vehicle identification data and entry traffic medium data collected at an entry identification point, and exit vehicle identification data and exit traffic medium data collected at an exit identification point. When the traffic medium data and the fused vehicle identification data satisfying the preset constraint conditions are fused to obtain a fused data set of passing vehicles, the fusion module 702 is further used to:

[0153] According to the entrance vehicle identification data in the fused vehicle identification data, the entrance traffic medium data that satisfies the preset constraint conditions with the entrance vehicle identification data is matched;

[0154] According to the exit vehicle identification data in the fused vehicle identification data, the exit traffic medium data that satisfies the preset constraint conditions with the exit vehicle identification data is matched;

[0155] The matched entrance traffic medium data, exit traffic medium data and fused vehicle identification data of the passing vehicles are fused to obtain a fused data set of the passing vehicles.

[0156] In one embodiment, the preset constraints include at least one of a time constraint and a space constraint, wherein the time constraint includes that the collection time of the vehicle identification data and the traffic medium data is within a time error range, and the space constraint includes that the vehicle identification data and the traffic medium data are collected at the same identification point.

[0157] In one embodiment, the vehicle identification data includes vehicle model data and license plate data, and the passing medium data includes medium vehicle model data, medium license plate data, and medium identification. When comparing the data difference of the target passing vehicle at the entrance and exit according to the fused data set of the target passing vehicle to identify the abnormal behavior of the target passing vehicle, the identification module 703 is further used to:

[0158] If the vehicle type in the vehicle type data is larger than the vehicle type in the medium vehicle type data of the same identification point, it is determined that the abnormal behavior of the target vehicle with a large vehicle and a small logo is identified; or

[0159] If the vehicle type in the vehicle type data is a truck, and the vehicle type in the medium vehicle type data of the same identification point is a passenger car, then it is determined that the abnormal behavior of the truck passenger logo of the target passing vehicle is identified; or

[0160] If the license plate data and the medium license plate data of the same identification point have different license plate numbers or license plate colors, it is determined that the identification of the target passing vehicle has been detected as an abnormal behavior in which the license plate number does not match; or

[0161] If the fused data set contains vehicle identification data that is not matched to the passing medium data, it is determined that the target passing vehicle has been identified as having abnormal behavior of not having a vehicle signature; or

[0162] If the fused data set contains vehicle identification data that matches more than one set of traffic medium data, it is determined that an abnormal behavior of multiple signatures for one target traffic vehicle is identified; or

[0163] If the exit medium identification and the entry medium identification of the target passing vehicle are inconsistent, it is determined that an abnormal behavior of replacing the card signature of the target passing vehicle is identified.

[0164] The above-mentioned vehicle abnormality identification device, the acquisition module 701 acquires the vehicle identification data and the passing medium data of the passing vehicle collected by the identification point, wherein the identification point is set at the entrance and exit of the service area of ​​the highway, and the vehicle identification device and the medium reading device are installed at the identification point, the vehicle identification device is used to collect the passing data of the passing vehicle and generate the vehicle identification data of the passing vehicle according to the collected passing data, and the medium reading device is used to collect the passing medium data of the passing vehicle; the fusion module 702 fuses the vehicle identification data and the passing medium data of the same passing vehicle to obtain the fused data set of each passing vehicle; the identification module 703 compares the data difference of the target passing vehicle at the entrance and exit according to the fused data set of the target passing vehicle to identify the abnormal behavior of the target passing vehicle. By installing vehicle identification equipment and media reading equipment at the entrance of the service area, the vehicle identification data and the passing medium data of each passing vehicle entering the service area are obtained; by installing vehicle identification equipment and media reading equipment at the exit of the service area, the vehicle identification data and the passing medium data of each passing vehicle leaving the service area are obtained. A fused data set of the passing vehicle is generated separately based on the data of the same passing vehicle. The data differences of the passing vehicles entering and leaving the service area are analyzed in combination with the fused data set, and the abnormal behavior of the passing vehicles in the service area is automatically identified, thereby improving the screening efficiency of abnormal behavior of vehicles in the service area.

[0165] Each module in the above-mentioned vehicle abnormality identification device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0166] Terms such as "component", "module", and "system" are intended to refer to a computer-related entity, which can be hardware, a combination of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable code, a thread of execution, a program, and / or a computer. As an illustration, both a running program running on a server and a server can be a component. One or more components can reside in a process and / or a thread of execution, and a component can be located in one computer and / or distributed between two or more computers.

[0167] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG7. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile computer-readable storage medium and an internal memory. The non-volatile computer-readable storage medium stores an operating system, a computer-readable instruction and a database. The internal memory provides an environment for the operation of the operating system and the computer-readable instructions in the non-volatile computer-readable storage medium. The database of the computer device is used to store the traffic data of passing vehicles, vehicle identification data, traffic medium data, fusion data sets, abnormal behavior recognition results, etc. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer-readable instruction is executed by the processor, a vehicle abnormality recognition method is implemented.

[0168] In an exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be shown in FIG8. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, the memory, and the input / output interface are connected via a system bus, and the communication interface, the display unit, and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile computer-readable storage medium and an internal memory. The non-volatile computer-readable storage medium stores an operating system and computer-readable instructions. The internal memory provides an environment for the operation of the operating system and the computer-readable instructions in the non-volatile computer-readable storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer-readable instructions are executed by the processor, a vehicle abnormality identification method is implemented. The display unit of the computer device is used to form a visually visible picture, which may be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0169] Those skilled in the art will understand that the structures shown in FIGS. 7 and 8 are merely block diagrams of partial structures related to the scheme of the present application, and do not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device may include more or fewer components than those shown in the figures, or combine certain components, or have a different arrangement of components.

[0170] In one embodiment, a computer device is further provided, including a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps in the above-mentioned method embodiments when executing the computer-readable instructions.

[0171] In one embodiment, a computer-readable storage medium is provided, which stores computer-readable instructions. When the computer-readable instructions are executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0172] In one embodiment, a computer program product is provided, the computer program product comprising computer-readable instructions, the computer-readable instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer-readable instructions from the computer-readable storage medium, and the processor executes the computer-readable instructions, so that the computer device performs the steps in the above-mentioned method embodiments.

[0173] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a non-volatile computer-readable storage medium. When the computer-readable instructions are executed, they can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0174] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0175] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A vehicle abnormality identification method, characterized in that: include: Acquiring vehicle identification data and passing medium data of a passing vehicle collected at an identification point, wherein the identification point is set at the entrance and exit of a service area of ​​a highway, and a vehicle identification device and a medium reading device are installed at the identification point, wherein the vehicle identification device is used to collect the passing data of the passing vehicle and generate the vehicle identification data of the passing vehicle according to the collected passing data, and the medium reading device is used to collect the passing medium data of the passing vehicle; The vehicle identification data and the passing medium data of the same passing vehicle are fused to obtain a fused data set of each passing vehicle; The data difference of the target passing vehicle at the entrance and the exit is compared according to the fused data set of the target passing vehicle to identify abnormal behavior of the target passing vehicle.

2. The method according to claim 1, characterized in that The vehicle identification data and the passing medium data of the same passing vehicle are fused to obtain a fused data set of each passing vehicle, including: The vehicle identification data of the same passing vehicles are determined by matching, and the vehicle identification data of the same passing vehicles are fused to obtain fused vehicle identification data of the passing vehicles; The passing medium data of the same passing vehicles are matched according to the fused vehicle identification data, and the passing medium data and the fused vehicle identification data that meet the preset constraints are fused to obtain a fused data set of the passing vehicles.

3. The method according to claim 2, characterized in that The vehicle identification data of the same passing vehicles determined by matching includes: If at least two vehicle identification data include license plate data, and the similarity of the license plate data included in the at least two vehicle identification data is greater than or equal to a first similarity threshold, the at least two vehicle identification data are determined to be vehicle identification data of the same passing vehicle; If at least two vehicle identification data do not contain license plate data, or the similarity of the contained license plate data is less than a first similarity threshold, the vehicle characteristics of the at least two vehicle identification data are obtained; if the similarity of the vehicle characteristics of the at least two vehicle identification data is greater than or equal to a second similarity threshold, the at least two vehicle identification data are determined to be vehicle identification data of the same passing vehicle.

4. The method according to claim 2, characterized in that: The vehicle identification data includes the entry vehicle identification data and the entry traffic medium data collected at the entry identification point, and the exit vehicle identification data and the exit traffic medium data collected at the exit identification point. The traffic medium data and the fused vehicle identification data satisfying the preset constraint conditions are fused to obtain a fused data set of passing vehicles, including: According to the entrance vehicle identification data in the fused vehicle identification data, matching the entrance traffic medium data that satisfies the preset constraint condition with the entrance vehicle identification data; According to the exit vehicle identification data in the fused vehicle identification data, matching the exit traffic medium data that satisfies the preset constraint condition with the exit vehicle identification data; The matched entrance traffic medium data, exit traffic medium data and fused vehicle identification data of the passing vehicles are fused to obtain a fused data set of the passing vehicles.

5. The method according to claim 4, characterized in that The preset constraints include time constraints and space constraints, wherein the time constraints include that the collection time of vehicle identification data and traffic medium data is within a time error range, and the space constraints include that the vehicle identification data and traffic medium data are collected at the same identification point.

6. The method according to claim 4, characterized in that The vehicle identification data includes vehicle model data and license plate data, the passing medium data includes medium vehicle model data, medium license plate data and medium identification, and the comparing the data difference of the target passing vehicle at the entrance and the exit according to the fusion data set of the target passing vehicle to identify the abnormal behavior of the target passing vehicle includes: If the vehicle type in the vehicle type data is larger than the vehicle type in the medium vehicle type data of the same identification point, it is determined that the abnormal behavior of the target vehicle with a large vehicle and a small logo is identified; or If the vehicle type in the vehicle type data is a truck, and the vehicle type in the medium vehicle type data of the same identification point is a passenger car, then it is determined that the abnormal behavior of the truck passenger logo of the target passing vehicle is identified; or If the license plate data and the medium license plate data of the same identification point have different license plate numbers or license plate colors, it is determined that the identification of the target passing vehicle has been detected as an abnormal behavior in which the license plate number does not match; or If the fused data set contains vehicle identification data that is not matched to the passing medium data, it is determined that the target passing vehicle has been identified as having an abnormal behavior of not having a vehicle signature; or If the fused data set contains vehicle identification data that matches more than one set of traffic medium data, it is determined that an abnormal behavior of multiple signatures for one target traffic vehicle is identified; or If the exit medium identification and the entry medium identification of the target passing vehicle are inconsistent, it is determined that an abnormal behavior of replacing the card signature of the target passing vehicle is identified.

7. A vehicle abnormality identification device, characterized in that: include: an acquisition module, used to acquire vehicle identification data and passing medium data of a passing vehicle collected at an identification point, wherein the identification point is set at the entrance and exit of a service area of ​​a highway, and a vehicle identification device and a medium reading device are installed at the identification point, the vehicle identification device is used to collect the passing data of the passing vehicle and generate the vehicle identification data of the passing vehicle according to the collected passing data, and the medium reading device is used to collect the passing medium data of the passing vehicle; A fusion module is used to fuse the vehicle identification data and the passing medium data of the same passing vehicle to obtain a fused data set of each passing vehicle; The identification module is used to compare the data difference of the target passing vehicle at the entrance and the exit according to the fused data set of the target passing vehicle, so as to identify the abnormal behavior of the target passing vehicle in the service area.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images