Abnormal vehicle identification method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to an abnormal vehicle identification method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring a target vehicle image in a target lane and a target electronic tag signal returned by electronic tag equipment in a target vehicle; performing license plate recognition on the target vehicle image to obtain a recognized license plate and license plate coordinates, and performing vehicle type recognition on the target vehicle image to obtain a recognized vehicle type and vehicle coordinates; determining a device coordinate, a real license plate and a real vehicle type corresponding to the electronic tag device based on the target electronic tag signal; when the equipment coordinates are matched with the license plate coordinates and the vehicle coordinates, taking the equipment coordinates as reference coordinates of the target vehicle; and when the reference coordinates are in the vehicle detection range, abnormal vehicle identification is carried out on the target vehicle based on the coordinate number of the reference coordinates, the real license plate, the identified license plate, the real vehicle type and the identified vehicle type to obtain an abnormal vehicle identification result. By adopting the method, the abnormal vehicle identification accuracy can be improved.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to an abnormal vehicle identification method, device, computer equipment, computer-readable storage medium and computer program product. Background Art

[0002] With the adjustment of national policies, in order to improve the efficiency of highway traffic, ETC unmanned toll lanes have become popular. However, they also face considerable challenges. Since the ETC unmanned toll lanes actually conduct transactions with the OBU (on-board unit) equipment installed on the vehicle, and the OBU equipment is easily disassembled and installed privately, it has spawned many malicious evasion behaviors, such as the license plate number hung on the vehicle is inconsistent with the OBU information carried, and the same vehicle carries multiple different OBUs. Traditional ETC equipment cannot identify such situations, resulting in low accuracy in identifying abnormal vehicles. Summary of the invention

[0003] Based on this, it is necessary to provide an abnormal vehicle identification method, device, computer equipment, computer-readable storage medium and computer program product that can improve the accuracy of abnormal vehicle identification in response to the above technical problems.

[0004] In a first aspect, the present application provides a method for identifying an abnormal vehicle, comprising:

[0005] Acquire a target vehicle image of a target vehicle in a target lane and a target electronic tag signal returned by an electronic tag device in the target vehicle;

[0006] Perform license plate recognition on the target vehicle image to obtain the recognized license plate and license plate coordinates, and perform vehicle model recognition on the target vehicle image to obtain the recognized vehicle model and vehicle coordinates;

[0007] Determine the device coordinates, real license plate and real vehicle model corresponding to the electronic tag device based on the target electronic tag signal;

[0008] When the device coordinates are matched with the license plate coordinates and vehicle coordinates, the device coordinates are used as the reference coordinates of the target vehicle;

[0009] When the reference coordinates are within the vehicle detection range, the target vehicle is identified as an abnormal vehicle based on the coordinate quantity of the reference coordinates, the real license plate, the recognized license plate, the real vehicle model and the recognized vehicle model to obtain an abnormal vehicle identification result.

[0010] In a second aspect, the present application also provides an abnormal vehicle identification device, comprising:

[0011] An acquisition module, used to acquire a target vehicle image of a target vehicle in a target lane and a target electronic tag signal returned by an electronic tag device in the target vehicle;

[0012] The image recognition module is used to perform license plate recognition on the target vehicle image to obtain the recognized license plate and license plate coordinates, and to perform vehicle model recognition on the target vehicle image to obtain the recognized vehicle model and vehicle coordinates;

[0013] A signal processing module, used to determine the device coordinates, real license plate and real vehicle model corresponding to the electronic tag device based on the target electronic tag signal;

[0014] A coordinate matching module is used to use the device coordinates as the reference coordinates of the target vehicle when matching the device coordinates with the license plate coordinates and the vehicle coordinates;

[0015] The recognition result module is used to identify the target vehicle as an abnormal vehicle based on the coordinate quantity of the reference coordinate, the real license plate, the recognized license plate, the real vehicle model and the recognized vehicle model when the reference coordinate is within the vehicle detection range, and obtain the abnormal vehicle recognition result.

[0016] 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:

[0017] Acquire a target vehicle image of a target vehicle in a target lane and a target electronic tag signal returned by an electronic tag device in the target vehicle;

[0018] Perform license plate recognition on the target vehicle image to obtain the recognized license plate and license plate coordinates, and perform vehicle model recognition on the target vehicle image to obtain the recognized vehicle model and vehicle coordinates;

[0019] Determine the device coordinates, real license plate and real vehicle model corresponding to the electronic tag device based on the target electronic tag signal;

[0020] When the device coordinates are matched with the license plate coordinates and vehicle coordinates, the device coordinates are used as the reference coordinates of the target vehicle;

[0021] When the reference coordinates are within the vehicle detection range, the target vehicle is identified as an abnormal vehicle based on the coordinate quantity of the reference coordinates, the real license plate, the recognized license plate, the real vehicle model and the recognized vehicle model to obtain an abnormal vehicle identification result.

[0022] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0023] Acquire a target vehicle image of a target vehicle in a target lane and a target electronic tag signal returned by an electronic tag device in the target vehicle;

[0024] Perform license plate recognition on the target vehicle image to obtain the recognized license plate and license plate coordinates, and perform vehicle model recognition on the target vehicle image to obtain the recognized vehicle model and vehicle coordinates;

[0025] Determine the device coordinates, real license plate and real vehicle model corresponding to the electronic tag device based on the target electronic tag signal;

[0026] When the device coordinates are matched with the license plate coordinates and vehicle coordinates, the device coordinates are used as the reference coordinates of the target vehicle;

[0027] When the reference coordinates are within the vehicle detection range, the target vehicle is identified as an abnormal vehicle based on the coordinate quantity of the reference coordinates, the real license plate, the recognized license plate, the real vehicle model and the recognized vehicle model to obtain an abnormal vehicle identification result.

[0028] 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:

[0029] Acquire a target vehicle image of a target vehicle in a target lane and a target electronic tag signal returned by an electronic tag device in the target vehicle;

[0030] Perform license plate recognition on the target vehicle image to obtain the recognized license plate and license plate coordinates, and perform vehicle model recognition on the target vehicle image to obtain the recognized vehicle model and vehicle coordinates;

[0031] Determine the device coordinates, real license plate and real vehicle model corresponding to the electronic tag device based on the target electronic tag signal;

[0032] When the device coordinates are matched with the license plate coordinates and vehicle coordinates, the device coordinates are used as the reference coordinates of the target vehicle;

[0033] When the reference coordinates are within the vehicle detection range, the target vehicle is identified as an abnormal vehicle based on the coordinate quantity of the reference coordinates, the real license plate, the recognized license plate, the real vehicle model and the recognized vehicle model to obtain an abnormal vehicle identification result.

[0034] The above-mentioned abnormal vehicle identification method, device, computer equipment, computer-readable storage medium and computer program product perform license plate recognition and vehicle recognition on the target vehicle image collected by the target lane to obtain the identified license plate, license plate coordinates, identified vehicle and vehicle coordinates, and then determine the device coordinates, real license plate and real vehicle model of the electronic tag device according to the target electronic tag signal returned by the electronic tag device in the target vehicle, match the device coordinates, license plate coordinates and vehicle coordinates, and can identify whether the electronic tag device to which the device coordinates belong is located on the same target vehicle, thereby realizing the accuracy verification of the electronic tag device in the target vehicle. When the device coordinates, license plate coordinates and vehicle coordinates match, the device coordinates are used as the reference coordinates of the target vehicle, thereby ensuring the recognition accuracy of the device electronic tag in the target vehicle; then, when the reference coordinates are within the vehicle detection range, the target vehicle is identified as an abnormal vehicle according to the coordinate number of the reference coordinates, the real license plate, the identified license plate, the real vehicle model and the identified vehicle model, so that the electronic tag in the target vehicle can be verified while the license plate and vehicle model of the target vehicle are verified, thereby further improving the accuracy of abnormal vehicle identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] 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.

[0036] Figure 1 A diagram showing an application environment of an abnormal vehicle identification method in an embodiment;

[0037] Figure 2 A schematic diagram of a flow chart of an abnormal vehicle identification method in one embodiment;

[0038] Figure 3 A schematic diagram of a flow chart of an abnormal vehicle identification step in one embodiment;

[0039] Figure 4 A schematic diagram of calculating the three-dimensional coordinates of a license plate in one embodiment;

[0040] Figure 5 A schematic diagram of a vehicle data collection device in one embodiment;

[0041] Figure 6 A schematic diagram of an abnormal vehicle identification process in one embodiment;

[0042] Figure 7 is a structural block diagram of an abnormal vehicle identification device in one embodiment;

[0043] Figure 8 is an internal structure diagram of a computer device in another embodiment;

[0044] Fig. 9 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the present application more clearly understood, 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 to limit the present application.

[0046] The abnormal vehicle identification method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. In an exemplary embodiment, the terminal 102 obtains the target vehicle image of the target vehicle in the target lane and the target electronic tag signal returned by the electronic tag device in the target vehicle; the terminal 102 performs license plate recognition on the target vehicle image to obtain the identified license plate and license plate coordinates, and performs vehicle model recognition on the target vehicle image to obtain the identified vehicle model and vehicle coordinates; the terminal 102 determines the device coordinates, real license plate and real vehicle model corresponding to the electronic tag device based on the target electronic tag signal; when the device coordinates match the license plate coordinates and vehicle coordinates, the terminal 102 uses the device coordinates as the reference coordinates of the target vehicle; when the reference coordinates are within the vehicle detection range, the terminal 102 performs abnormal vehicle recognition on the target vehicle based on the coordinate quantity of the reference coordinates, the real license plate, the identified license plate, the real vehicle model and the identified vehicle model, and obtains the abnormal vehicle recognition result; the terminal 102 can send the target vehicle image and the abnormal vehicle recognition result to the server 104 for storage. The terminal 102 may be, but is not limited to, various personal computers, laptop computers, etc. The server 104 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0047] In an exemplary embodiment, Figure 2 As shown, a method for identifying abnormal vehicles is provided, and the method is applied to Figure 1 The server in the example is used for explanation, so that it is understood that the method can also be applied to the server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0048] Step 202: Acquire a target vehicle image of a target vehicle in a target lane and a target electronic tag signal returned by an electronic tag device in the target vehicle.

[0049] The target lane is the lane where the vehicle whose vehicle image needs to be collected is traveling, and can be a lane in the abnormal vehicle identification area of ​​the highway. The abnormal vehicle identification area is an area used to detect vehicles and identify whether the vehicle is an abnormal vehicle, such as a lane in the toll execution area of ​​a toll station on a highway. The target vehicle image refers to an image of the target vehicle in the target lane. The electronic tag device refers to a microwave device mounted on the vehicle that can communicate via microwaves and is used to provide real vehicle information. The target electronic tag signal refers to the signal returned by the electronic tag device in the target vehicle in response to the communication signal.

[0050] Exemplarily, the target vehicle is traveling on any lane of a highway. When it travels into an abnormal vehicle identification area, the lane in which the target vehicle is traveling within the abnormal vehicle identification area is used as the target lane. Then, an image acquisition device deployed in the abnormal vehicle identification area is used to acquire an image of the target vehicle in the target lane to obtain an image of the target vehicle.

[0051] Radio frequency transceivers are also deployed in the abnormal vehicle identification area. The radio frequency transceivers are used to communicate with the electronic tag devices installed on the vehicles in the target lane to obtain relevant vehicle information of the vehicles. Among them, the acquisition frequency of the image acquisition device is the same as the radio frequency signal transmission frequency of the radio frequency transceiver. When the target vehicle drives into the abnormal vehicle identification area, the radio frequency transceiver deployed in the abnormal vehicle identification area synchronously sends radio frequency communication signals to the target lane, and receives the target electronic tag signal returned by the electronic tag device in the target vehicle in response to the radio frequency communication signal.

[0052] The terminal obtains the target vehicle image of the current frame through the image acquisition device. The target vehicle image is the target vehicle image corresponding to the target vehicle on the target lane in the abnormal vehicle identification area, and obtains the target electronic tag signal at the same time when the target vehicle image is acquired through the radio frequency transceiver device. The target electronic tag signal is the signal returned by the electronic tag device loaded on the target vehicle on the target lane.

[0053] Step 204, performing license plate recognition on the target vehicle image to obtain the recognized license plate and license plate coordinates, performing vehicle type recognition on the target vehicle image to obtain the recognized vehicle type and vehicle coordinates.

[0054] Among them, license plate recognition refers to the process of identifying the license plate content and license plate coordinates on the target vehicle. License plate recognition refers to the license plate content obtained by license plate recognition. License plate coordinates refer to the three-dimensional spatial coordinates of the license plate in the world coordinate system. Vehicle model recognition refers to the process of identifying the appearance outline and vehicle coordinates of the target vehicle. Vehicle model recognition refers to the vehicle model features obtained by vehicle model recognition. Vehicle coordinates refer to the three-dimensional spatial coordinates of the vehicle in the world coordinate system.

[0055] Exemplarily, the terminal is also deployed with a license plate recognition model and a vehicle recognition model. The license plate recognition model is a model pre-trained using license plate sample data, and the vehicle recognition model is a model pre-trained using vehicle appearance features as sample data.

[0056] After the terminal obtains the target vehicle image corresponding to the target vehicle, the target vehicle image is input into the license plate recognition model and the vehicle recognition model for recognition. The license plate recognition model outputs the recognition license plate corresponding to the target vehicle image and the two-dimensional coordinates corresponding to the center point of the license plate area in the target vehicle image (which can be expressed as the license plate two-dimensional image coordinates), and the two-dimensional image coordinates of the license plate are converted to the coordinate system to obtain the three-dimensional space coordinates of the center point of the license plate in three-dimensional space, that is, the license plate coordinates; the vehicle recognition model outputs the model features of the target vehicle in the target vehicle image (model features such as small cars, medium-sized cars, etc.) and the two-dimensional coordinates corresponding to the center point of the vehicle area in the target vehicle image (which can be expressed as the vehicle two-dimensional image coordinates), and the vehicle area can refer to the front area, and the two-dimensional image coordinates of the vehicle are converted to the coordinate system to obtain the three-dimensional space coordinates of the center point of the vehicle area in three-dimensional space, that is, the vehicle coordinates.

[0057] Step 206: Determine the device coordinates, real license plate number and real vehicle model corresponding to the electronic tag device based on the target electronic tag signal.

[0058] The device coordinates refer to the three-dimensional space coordinates of the electronic tag device in the world coordinate system. The real license plate refers to the license plate in the vehicle information bound to the electronic tag device. The real vehicle model refers to the vehicle model in the vehicle information bound to the electronic tag device.

[0059] Exemplarily, at least two RF transceivers are deployed in the abnormal vehicle identification area to receive the target electronic tag signal returned by the electronic tag device for each RF transceiver, and the target electronic tag signal is parsed to obtain the real license plate and real vehicle model corresponding to the electronic tag device.

[0060] The response time of the target electronic tag signal is obtained, that is, the waiting time before the RF transceiver receives the target electronic tag signal. The straight-line distance of the electronic tag device relative to each RF transceiver device is calculated based on the response time and signal speed of the target electronic tag signal. Then, the device position of each RF transceiver device is obtained, such as the device height of the RF transceiver device from the ground. According to the device position and the straight-line distance of the electronic tag device relative to each RF transceiver device, the relative coordinates of the electronic tag device relative to each RF transceiver device are calculated. Then, the relative positions of each RF transceiver device are obtained. According to the relative positions of each RF transceiver device, the relative coordinates of the electronic tag device relative to each RF transceiver device are converted into coordinate systems to obtain the three-dimensional space coordinates of the electronic tag device in the world coordinate system, that is, the device coordinates.

[0061] Step 208: When the device coordinates match the license plate coordinates and the vehicle coordinates, the device coordinates are used as reference coordinates of the target vehicle.

[0062] The reference coordinates are used to detect whether the vehicle is within the vehicle detection range.

[0063] Exemplarily, the terminal matches the currently calculated device coordinates with the license plate coordinates and the vehicle coordinates. When the device coordinates match the license plate coordinates and the vehicle coordinates, it is determined that the electronic tag device corresponding to the device coordinates is placed on the target vehicle corresponding to the license plate coordinates and the vehicle coordinates, and the device coordinates are used as the reference coordinates of the target vehicle. When there are multiple device coordinates that match the license plate coordinates and the vehicle coordinates, the average coordinates of each device coordinate are calculated and the average coordinates are used as the reference coordinates of the target vehicle.

[0064] In an exemplary embodiment, when the target vehicle is not equipped with a license plate, the license plate and license plate coordinates cannot be recognized for the target vehicle image, but the vehicle model and vehicle coordinates can be recognized for the target vehicle image, then the vehicle coordinates are matched with the device coordinates, and when the device coordinates match the vehicle coordinates, the device coordinates are used as the reference coordinates of the target vehicle.

[0065] Step 210, when the reference coordinates are within the vehicle detection range, based on the coordinate quantity of the reference coordinates, the real license plate, the recognized license plate, the real vehicle model and the recognized vehicle model, an abnormal vehicle recognition result is obtained for the target vehicle.

[0066] The vehicle detection range refers to the detection range in the abnormal vehicle identification area where the vehicle is judged to be abnormal. The number of coordinates refers to the number of device coordinates that match the same license plate coordinates and the same vehicle coordinates. Since the device coordinates are calculated based on the target electronic tag signal returned by the electronic tag device, the electronic tag device, the target electronic tag signal and the device coordinates correspond one to one, and the number of device coordinates can reflect the number of electronic tag devices on the same vehicle.

[0067] Exemplarily, the abnormal vehicle identification area also includes a vehicle detection range, which may be a vehicle detection coordinate pre-set in the abnormal vehicle identification area. The terminal may calculate the reference coordinates of the target vehicle in real time, and when it is detected that the reference coordinates are in the vehicle detection range, such as when the distance between the reference coordinates and the vehicle detection coordinates is less than a distance threshold, it is determined that the target vehicle meets the detection condition, and the terminal compares the real license plate and the real vehicle model with the identified license plate and the identified vehicle model, respectively, and determines the abnormal vehicle identification result of the target vehicle according to the comparison result and the number of coordinates of the reference coordinates, such as whether it is a normal vehicle, an abnormal vehicle, etc.

[0068] In the above abnormal vehicle identification method, the target vehicle image collected in the target lane is subjected to license plate recognition and vehicle recognition to obtain the identified license plate, license plate coordinates, identified vehicle and vehicle coordinates, and then the device coordinates, real license plate and real vehicle model of the electronic tag device are determined according to the target electronic tag signal returned by the electronic tag device in the target vehicle, and the device coordinates, license plate coordinates and vehicle coordinates are matched to identify whether the electronic tag device to which the device coordinates belong is located on the same target vehicle, thereby realizing the accuracy verification of the electronic tag device in the target vehicle, and then when the device coordinates, license plate coordinates and vehicle coordinates are matched, the device coordinates are used as the reference coordinates of the target vehicle to ensure the recognition accuracy of the device electronic tag in the target vehicle; then when the reference coordinates are within the vehicle detection range, the target vehicle is subjected to abnormal vehicle identification according to the coordinate quantity of the reference coordinates, the real license plate, the identified license plate, the real vehicle model and the identified vehicle model, so that the electronic tag in the target vehicle can be verified while the license plate and vehicle model of the target vehicle are verified, thereby further improving the accuracy of abnormal vehicle identification.

[0069] In an exemplary embodiment, Figure 3 As shown, step 204, performing license plate recognition on the target vehicle image to obtain the recognized license plate and license plate coordinates, includes:

[0070] Step 302: Input the target vehicle image into the license plate recognition model, and output the recognized license plate and the two-dimensional image coordinates of the license plate corresponding to the target vehicle.

[0071] Step 304: Acquire the device acquisition angle of the image acquisition device corresponding to the target vehicle image.

[0072] Step 306: based on the device acquisition angle, convert the two-dimensional image coordinates of the license plate into three-dimensional space coordinates of the license plate to obtain the coordinates of the license plate.

[0073] Among them, the device acquisition angle includes the horizontal field of view angle and the vertical field of view angle of the image acquisition device. The preset license plate height refers to the preset physical license plate height. The two-dimensional image coordinates of the license plate refer to the two-dimensional coordinates corresponding to the center point of the license plate area in the target vehicle image. The three-dimensional spatial coordinates of the license plate refer to the three-dimensional coordinates of the license plate in the three-dimensional space, which can be specifically the three-dimensional coordinates of the center point of the license plate in the coordinate system with the image acquisition device as the origin, including the horizontal coordinate and vertical coordinate of the center point of the license plate in the coordinate system of the image acquisition device.

[0074] Exemplarily, the terminal inputs the target vehicle image into the license plate recognition model, obtains the recognized license plate and the license plate two-dimensional image coordinates output by the license plate recognition model, then obtains the device acquisition angle and device installation height of the image acquisition device corresponding to the target vehicle image, and converts the license plate two-dimensional image coordinates into the license plate three-dimensional space coordinates based on the device acquisition angle and the device installation height to obtain the license plate coordinates.

[0075] In an exemplary embodiment, Figure 4 As shown, a schematic diagram of calculating the three-dimensional spatial coordinates of a license plate is provided. Figure 4 -a represents a schematic diagram of calculating the vertical coordinate in the three-dimensional space coordinates of the license plate, and Figure 4 -b represents a schematic diagram of calculating the horizontal coordinate in the three-dimensional space coordinates of the license plate.

[0076] like Figure 4 -a, the device acquisition angle includes the vertical field of view angle of the image acquisition device (referred to as the camera) and the pitch angle c. The camera height is H and the image height is h. According to the imaging relationship, the distance from the position of the license plate imaging point in the target vehicle image to the bottom of the target vehicle image is ( The angle between the vertical coordinate of the license plate 2D image and the vertical field of view of the camera There is a proportional relationship between them, as shown in formula (1):

[0077] (1)

[0078] Where d represents the longitudinal reference angle involved in the intermediate calculation, which is used to calculate the inclination angle b of the license plate relative to the camera. The calculation of the inclination angle b of the license plate relative to the camera is shown in formula (2). After obtaining the inclination angle b of the license plate relative to the camera, the longitudinal coordinate of the license plate in the three-dimensional space from the camera is calculated according to formula (3): .

[0079] (2)

[0080] (3)

[0081] Specifically, the terminal uses the image height h and the vertical field of view angle of the camera to , the distance from the position of the license plate imaging point in the target vehicle image to the bottom of the target vehicle image The proportional relationship between them is used to calculate the longitudinal reference angle d according to formula (1); then, according to the longitudinal reference angle d, the pitch angle c and the vertical field of view angle of the camera According to the geometric relationship between the license plate and the camera, the inclination angle b of the license plate relative to the camera is calculated according to formula (2); according to the inclination angle b of the license plate relative to the camera and the inclination angle b of the license plate relative to the camera, the longitudinal distance of the license plate from the camera in the three-dimensional space is calculated according to formula (3), that is, the longitudinal coordinate in the three-dimensional space coordinates of the license plate .

[0082] like Figure 4 -b shows that the device acquisition angle includes the horizontal field of view angle of the image acquisition device (referred to as the camera) , the image width of the target vehicle image is w. According to the imaging relationship, the distance from the position of the license plate imaging point in the target vehicle image to the center of the target vehicle image is ( The angle between the horizontal coordinate in the two-dimensional image coordinates of the license plate and the image center coordinates and the camera's flat field of view angle There is a proportional relationship between them, as shown in formula (4):

[0083] (4)

[0084] Where e represents the lateral reference angle involved in the intermediate calculation. After obtaining the lateral reference angle e, the horizontal coordinate of the license plate in the 3D space at the lateral distance from the camera is calculated according to formula (5): .

[0085] (5)

[0086] Specifically, the terminal calculates the image width w and the camera's horizontal field of view angle. , the distance from the position of the license plate imaging point in the target vehicle image to the center of the target vehicle image The proportional relationship between them is used to calculate the lateral reference angle e according to formula (4); then, according to the lateral reference angle e and the ordinate in the three-dimensional coordinates of the license plate, , according to formula (5), the tangent calculation is performed to obtain the lateral distance of the license plate from the camera in the three-dimensional space, that is, the horizontal coordinate of the license plate in the three-dimensional space coordinates , get the three-dimensional space coordinates of the license plate ( , ).

[0087] In an exemplary embodiment, the terminal inputs the target vehicle image into the vehicle recognition model, obtains the identified vehicle model and the two-dimensional image coordinates of the vehicle output by the vehicle recognition model, and the two-dimensional image coordinates of the vehicle refer to the two-dimensional coordinates of the center point of the vehicle area in the target vehicle image. Then, the device acquisition angle and the device installation height of the image acquisition device corresponding to the target vehicle image are obtained, and the two-dimensional image coordinates of the vehicle are converted into the three-dimensional space coordinates of the vehicle according to the device acquisition angle and the device installation height to obtain the license plate coordinates. The three-dimensional space coordinates of the vehicle refer to the three-dimensional coordinates of the center point of the front of the vehicle in the three-dimensional space, and specifically can be the three-dimensional coordinates of the center point of the front of the vehicle in the coordinate system with the image acquisition device as the origin, including the horizontal coordinate and the vertical coordinate of the vehicle in the coordinate system of the image acquisition device. Among them, the calculation of the horizontal coordinate and the vertical coordinate of the vehicle in the coordinate system of the image acquisition device can refer to the calculation process of the horizontal coordinate and the vertical coordinate of the license plate in the coordinate system of the image acquisition device in the above formulas (1)-(5).

[0088] In this embodiment, the accuracy of license plate recognition and vehicle recognition is ensured by using the pre-trained license plate recognition model and vehicle recognition model outputs to recognize the license plate and the vehicle.

[0089] In an exemplary embodiment, the abnormal vehicle identification method further includes:

[0090] Obtain a vehicle tracking sequence corresponding to the target lane, and obtain a candidate vehicle information sequence corresponding to the target vehicle based on the vehicle tracking sequence;

[0091] Compare the recognized license plate with the last recognized license plate in the candidate vehicle information sequence, and if the comparison is successful, add the recognized license plate and the license plate coordinates to the last recognized license plate;

[0092] The identified vehicle model is matched with the last identified vehicle model in the candidate vehicle information sequence. When the match is successful, the identified vehicle model and vehicle coordinates are added to the last identified vehicle model, and the candidate vehicle information sequence is determined as the target vehicle information sequence corresponding to the target vehicle; the target vehicle information sequence is used to identify the target vehicle as an abnormal vehicle.

[0093] The vehicle tracking sequence is used to store the vehicle information collected at each time for each vehicle in the target lane. The vehicle tracking sequence may include vehicle information sequences corresponding to multiple vehicles on the same lane. The vehicle information sequence is a sequence that stores the vehicle information collected at each time for the same vehicle. The vehicle information includes the identification license plate, license plate coordinates, identification vehicle model, vehicle coordinates and device coordinates of each vehicle. The target vehicle information sequence refers to the vehicle information sequence corresponding to the target vehicle.

[0094] Exemplarily, after the terminal recognizes the target vehicle's license plate and vehicle model from the target vehicle image, it obtains the vehicle tracking sequence corresponding to the target lane. The vehicle tracking sequence includes vehicle information sequences corresponding to multiple vehicles, and the order of the vehicle information sequences corresponding to the vehicles is consistent with the order of the vehicles to which the vehicle information sequences belong entering the abnormal vehicle identification area. The vehicle information sequence also includes a license plate sequence and a vehicle model sequence. The license plate sequence is used to store each license plate and each license plate coordinate of the same vehicle, and the vehicle model sequence is used to store each license plate and each vehicle coordinate of the same vehicle.

[0095] The most recently generated vehicle information sequence in the vehicle tracking sequence can be used as the candidate vehicle information sequence corresponding to the target vehicle image. At this time, it is also necessary to perform license plate verification and vehicle model verification on the candidate vehicle information sequence based on the identified license plate and identified vehicle model obtained from the target vehicle image. Through license plate verification and vehicle model verification, it is determined whether the target vehicle in the target vehicle image is the same vehicle as the vehicle to which the candidate vehicle information sequence belongs.

[0096] The terminal obtains a candidate vehicle information sequence from the vehicle tracking sequence. The candidate vehicle information sequence also includes a candidate identification license plate sequence and a candidate identification vehicle model sequence. The terminal compares the identification license plate corresponding to the target vehicle image with the previous identification license plate in the candidate identification license plate sequence, which may be a character comparison. When the comparison is successful, the identification license plate and the license plate coordinates are added after the previous identification license plate. Then the identification vehicle model corresponding to the target vehicle image is matched with the previous identification vehicle model in the candidate identification vehicle model sequence, which may be a feature matching. When the match is successful, the identification vehicle model and the vehicle coordinates are added after the previous identification vehicle model. After the license plate verification and vehicle model verification of the candidate vehicle information sequence are successful, the terminal determines that the candidate vehicle information sequence is the target vehicle model information sequence corresponding to the target vehicle, including the target identification license plate sequence and the target identification vehicle model sequence corresponding to the target vehicle. The target vehicle information sequence is used to identify abnormal vehicles for the target vehicle.

[0097] In this embodiment, by performing license plate verification and vehicle model verification on the vehicle information sequence, it is prevented that the vehicle information sequence of any vehicle does not contain vehicle information of other vehicles, thereby ensuring the accuracy of vehicle information in each vehicle information sequence of the vehicle tracking sequence.

[0098] In an exemplary embodiment, the target vehicle information sequence also includes a reference coordinate sequence. After the terminal calculates the device coordinates based on the target electronic tag signal obtained at the current moment, it obtains the license plate coordinates and vehicle coordinates obtained by the target vehicle image recognition collected at the same moment in the license plate recognition sequence and vehicle model recognition sequence of the target vehicle information sequence, respectively. The device coordinates are matched with the license plate coordinates and vehicle coordinates. If the match is successful, the device coordinates are used as reference coordinates and added to the reference coordinate sequence of the target vehicle information sequence; if there is no match, the device coordinates are discarded.

[0099] In an exemplary embodiment, in the license plate comparison of the candidate recognition license plate sequence, invalid recognition license plates can be determined according to the number of failed comparisons of the recognition license plates, and the recognition license plate sequence containing the invalid recognition license plates can be deleted.

[0100] The recognized license plate obtained by the target vehicle image recognition is used as the current recognized license plate. If the current recognized license plate corresponding to the target vehicle image fails to match the previous recognized license plate in the candidate recognized license plate sequence of the candidate vehicle information sequence, the number of failed comparisons of the current recognized license plate and the previous recognized license plate is updated respectively. When the number of failed comparisons of the updated current recognized license plate and the previous recognized license plate are both 1, it means that the current comparison failure is the first comparison failure of the current recognized license plate and the previous recognized license plate, and the current recognized license plate that fails to match is used as the difference recognized license plate. Then, a new updated vehicle information sequence is created in the vehicle tracking sequence, as well as an updated recognized license plate sequence and an updated recognized vehicle sequence in the newly created updated vehicle information sequence, and the difference recognized license plate and the corresponding vehicle coordinates are added to the updated recognized license plate sequence. If the recognized vehicle type obtained by the target vehicle image recognition successfully matches the previous recognized vehicle type in the candidate recognized vehicle type sequence of the candidate vehicle information sequence, the recognized vehicle type and vehicle coordinates obtained by the target vehicle image recognition are added to the updated recognized vehicle sequence; if the match fails, the recognized vehicle type and the corresponding vehicle coordinates are discarded.

[0101] After obtaining the next recognized license plate, the terminal uses the updated vehicle information sequence as a new candidate vehicle information sequence, and the new candidate vehicle information sequence includes the updated recognized license plate sequence. The next recognized license plate is compared with the difference recognized license plate in the updated recognized license plate sequence. If the comparison is successful, the next recognized license plate and the corresponding license plate coordinates are added to the difference recognized license plate, and the new candidate vehicle information is determined as the target vehicle information sequence corresponding to the target vehicle, and the target vehicle information sequence corresponding to the target vehicle may include multiple; if the comparison fails, the number of comparison failures of the difference recognized license plate and the next recognized license plate is updated. At this time, the number of comparison failures of the updated difference recognized license plate is 2 and the number of comparison failures of the next recognized license plate is 1. When the number of comparison failures of the difference recognized license plate is greater than 1, the difference recognized license plate is determined to be an invalid recognized license plate, and the new candidate vehicle information sequence is deleted. Then the next recognized license plate is used as a new difference recognized license plate, and the step of creating a new updated vehicle information sequence in the vehicle tracking sequence is returned to be executed.

[0102] In an exemplary embodiment, an image acquisition device and a radio frequency transceiver are installed on the target lane; step 202, obtaining a target vehicle image of a target vehicle in the target lane and a target electronic tag signal returned by an electronic tag device in the target vehicle, includes:

[0103] Based on the image acquisition frequency, when the image of the target vehicle corresponding to the target vehicle is collected within the specified range of the target lane at the current acquisition moment, the radio frequency transceiver device is synchronously triggered to send a radio frequency communication signal within the specified range, and receive the target electronic tag signal returned by the electronic tag device in the target vehicle within the specified range.

[0104] The designated range refers to the area covered by the target lane in the abnormal vehicle identification area. The abnormal vehicle identification area is larger than the designated area of ​​the target lane and may include designated areas of multiple lanes.

[0105] Exemplarily, the image acquisition device has the same image acquisition frequency as the signal transmission frequency of the radio frequency transceiver device. The acquisition range of the image acquisition device is the specified range of the target lane, and the signal transmission and reception range of the radio frequency transceiver device is the abnormal vehicle identification area. The image acquisition device acquires the original area image of the specified range of the target lane at the current moment, extracts the target vehicle image corresponding to the target vehicle from the original area image, and synchronously triggers the radio frequency transceiver device to send a radio frequency communication signal to the abnormal vehicle identification area, receives each electronic tag signal returned in the abnormal vehicle identification area, and receives the device coordinates of each electronic tag signal. Then, the electronic tag signal whose device coordinates are within the specified range of the target lane is determined as the target electronic tag signal returned by the electronic tag device in the target vehicle within the specified range.

[0106] In an exemplary embodiment, the terminal obtains the original area image of the current frame (nth frame) and the original area image of the previous frame (n-1th frame), calculates the grayscale differences fn(x, y) and fn-i(x, y) of the corresponding pixels of the original area images of the nth frame and the n-1th frame, subtracts the grayscale values ​​of the corresponding pixels of the original area images of the nth frame and the n-1th frame, and takes their absolute value Dn(x, y)=lfn(x, y)-fn-1(x, y) to obtain a differential image D.

[0107] The difference image D is binarized by setting a threshold value T. If Dn(x,y) >T, the grayscale Ln(x,y) = 1. If Dn(x,y) ≤T, the grayscale value Ln(x,y) = 0, and a binary image L is obtained. The points with a grayscale value of 1 in the binary image L are taken as foreground (moving object) points, and the points with a grayscale value of 0 are taken as background points. The foreground image is extracted from the binary image L according to the foreground points, and the vehicle area image Rn(x,y,w,h) is obtained, that is, the target vehicle image.

[0108] In this embodiment, the original region image is processed to obtain a binary image, and the foreground image is extracted from the binary image to obtain the target vehicle image, thereby ensuring the accuracy of the target vehicle image.

[0109] In an exemplary embodiment, step 210, based on the coordinate quantity of the reference coordinate, the real license plate, the recognized license plate, the real vehicle model and the recognized vehicle model, performs abnormal vehicle recognition on the target vehicle to obtain an abnormal vehicle recognition result, including:

[0110] When the number of coordinates is one and the recognized license plate is consistent with the real license plate, and the recognized vehicle model is consistent with the real vehicle model, the abnormal vehicle recognition result of the target vehicle is determined to be a normal vehicle;

[0111] Otherwise, the abnormal vehicle identification result of the target vehicle is determined to be an abnormal vehicle.

[0112] Exemplarily, when the terminal detects that the reference coordinates of the current target vehicle are within the vehicle detection range in the reference coordinate sequence of the target vehicle information sequence corresponding to the target vehicle, the abnormal vehicle detection process for the target vehicle is triggered.

[0113] The terminal detects the number of coordinates of the reference coordinates at the current moment in the reference coordinate sequence, and determines whether the number of coordinates is 1. If not, the abnormal vehicle identification result of the target vehicle is determined to be an abnormal vehicle, and the abnormal category of the target vehicle is an abnormal number of electronic tag devices. For example, when the number of coordinates is greater than 1, it means that there are multiple electronic tag devices in the target vehicle; when the number of coordinates is equal to 0, it means that there is no electronic tag device in the target vehicle. If so, it is determined whether the identified license plate is consistent with the real license plate. If not, it is determined that the abnormal vehicle identification result of the target vehicle is an abnormal vehicle, and the abnormal category of the target vehicle is a license plate abnormality. If consistent, it is determined whether the identified model is consistent with the real model; if not, it is determined that the abnormal vehicle identification result of the target vehicle is an abnormal vehicle, and the abnormal category of the target vehicle is a model abnormality. If consistent, it is determined that the abnormal vehicle identification result of the target vehicle is a normal vehicle.

[0114] In this embodiment, the abnormal vehicle identification result is determined by the number of coordinates, the recognized license plate and the recognized vehicle model, so that multi-dimensional abnormal vehicle judgment can be achieved. Furthermore, by judging the number of coordinates, the situation where multiple electronic tag devices are carried on the same vehicle can be effectively judged, thereby improving the accuracy of abnormal vehicle identification.

[0115] In an exemplary embodiment, the abnormal vehicle identification method further includes:

[0116] When the target vehicle is a normal vehicle, the payment operation is performed based on the user account information in the electronic tag signal, and when the payment is successful, the interception device is controlled to release the target vehicle;

[0117] When the target vehicle is an abnormal vehicle, the interception device is controlled to intercept the target vehicle.

[0118] For example, when the terminal detects that the target vehicle is a normal vehicle, it generates a payment request based on the user account information carried by the electronic tag information, and sends the payment request to the corresponding server. The server performs a payment operation on the user account information in response to the payment request. When the payment is successful, a payment success notification is sent to the terminal. After receiving the payment success notification, the terminal controls the interception device to release the target vehicle. When the terminal detects that the target vehicle is an abnormal vehicle, it controls the interception device to intercept the target vehicle and generates an abnormal vehicle alarm.

[0119] In an exemplary embodiment, Figure 5As shown, a schematic diagram of a vehicle data acquisition device is provided, including an installation elevation diagram and an installation foundation diagram of the vehicle data acquisition device. The target lane may be an ETC toll lane, and the image acquisition device may be a camera. The camera is installed directly above the ETC toll lane at a height of 6 meters, and continuously acquires images with a frame rate of more than 25fps. The radio frequency transceiver device may be an ETC roadside unit antenna. The integrated display and anti-collision column area are the toll execution area, and the automatic barrier is an interception device.

[0120] The vehicle travels from left to right. When the vehicle reaches the position 25 meters to the left of the ETC roadside unit antenna, the vehicle enters the abnormal vehicle identification area. The camera continuously collects multiple frames of vehicle images, and the ETC roadside unit antenna sends a radio frequency communication signal to the vehicle. For any frame of the vehicle image, the identification license plate, vehicle coordinates, identification model and vehicle coordinates are obtained and added to the corresponding sequence respectively. For the electronic tag signal received by the ETC roadside unit antenna, the reference coordinates are determined and added to the corresponding reference coordinate sequence. When the vehicle is determined to have reached the position 8 meters to the left of the ETC roadside unit antenna according to the reference coordinates, the vehicle is identified as an abnormal vehicle. When the vehicle is a normal vehicle and the payment is successful, the automatic barrier is controlled to release the vehicle; when the vehicle is an abnormal vehicle or the payment fails, the automatic barrier is controlled to release the vehicle.

[0121] In an exemplary embodiment, Figure 6 As shown, a schematic diagram of an abnormal vehicle identification process is provided. Specifically, the following steps are included:

[0122] The vehicle data acquisition device is installed directly above the toll lane. When a vehicle passes, the front image data of each vehicle in the toll lane is continuously collected according to the acquisition frequency, and the foreground image of the moving vehicle is extracted respectively to obtain the target vehicle image sequence M in the vehicle area and cache it.

[0123] The target vehicle image sequence M is processed one by one as follows: the first step is to normalize the target vehicle image. The second step is to use the pre-trained license plate recognition model to detect and recognize the vehicle license plate of the target vehicle image to obtain the license plate information (recognize the license plate) and the image center point coordinate information of the license plate (license plate two-dimensional image coordinates). Using the known equipment installation height H, the estimated vehicle height H1, and the horizontal and vertical field of view angles of the camera (equipment acquisition angle), the three-dimensional coordinates of the license plate relative to the camera (license plate coordinates) are calculated to obtain the vehicle license plate sequence L (recognize the license plate sequence) containing the license plate coordinates.

[0124] The target vehicle image sequence M is processed one by one as follows: the first step is to normalize the target vehicle image. The second step is to use the pre-trained vehicle feature extraction model (vehicle type recognition model) to extract vehicle feature information (recognize the vehicle type) and the image center point coordinate information of the vehicle (vehicle two-dimensional image coordinates) from the target vehicle image. The known device installation height H, the estimated vehicle height H1, and the horizontal and vertical field of view angles of the camera (device acquisition angle) are used to calculate the three-dimensional coordinates of the vehicle relative to the camera (vehicle coordinates) to obtain the vehicle feature information sequence T (recognize the vehicle type sequence) containing the vehicle coordinates.

[0125] Through the RF transceiver unit of the RF transceiver device, RF communication is carried out on the toll lane in real time to read the OBU information of the vehicle in the toll lane (target electronic tag signal), and the coordinate information of the OBU (device coordinates) is obtained synchronously through the RF positioning unit in the RF transceiver device to generate a RF OBU vehicle information sequence S (reference coordinate sequence) containing the real license plate and positioning coordinate information (device coordinates matching the license plate coordinates and vehicle coordinates).

[0126] The video data vehicle feature information sequence T, the video vehicle license plate sequence L and the radio frequency OBU vehicle information sequence S are fused to generate a vehicle tracking sequence P (including license plate information and coordinate information, vehicle feature data, vehicle OBU information and coordinate information), including:

[0127] Compare the license plate information in the vehicle license plate sequence L with the previous license plate information in the vehicle tracking sequence P one by one. If the license plate information is the same, merge the current vehicle license plate sequence Ln into the current vehicle tracking sequence Pn, and update Pn with the license plate information and coordinate information of Ln; if there is no match between Ln and sequence P, increase the new sequence number m of P, and update Pm with the license plate information and coordinate information of Ln;

[0128] The vehicle feature information in the vehicle feature information sequence T is compared with the previous vehicle feature information in the vehicle tracking sequence P one by one, and the cosine distance S between the two features is calculated. If S is less than the set threshold Ss, the current vehicle feature information sequence Tn is merged into the current vehicle tracking sequence Pn, and the vehicle feature information and coordinate information of Tn are updated to Pn; if Tn has no matching result with the sequence P, a new sequence number Pm of P is added, and the vehicle feature information and coordinate information of Tn are updated to Pm;

[0129] The coordinate information of the OBU in the RF OBU vehicle information sequence S is compared with the vehicle tracking sequence P one by one, and the distance Q between the two coordinates is calculated. If it is less than the set threshold Qs, the current RF OBU vehicle information sequence Sn is merged into the current vehicle tracking sequence Pn, and the vehicle OBU information and coordinate information of Sn are updated to Pn; if Sn has no matching result with the sequence P, it is considered to be invalid RF information and is discarded.

[0130] Traverse the vehicle tracking sequence P, calculate the distance Q between the vehicle coordinate position in the current sequence number Pn and the preset vehicle departure coordinate (x_e, y_e), if it is less than the set threshold Qs, Pn meets the abnormal vehicle identification condition. In the abnormal vehicle identification process, if the number of RF OBU vehicle information in Pn (the number of coordinates of the device coordinates) is greater than 1, the output is an abnormal vehicle (the vehicle carries multiple OBUs); if the number of RF OBU vehicle information in Pn is equal to 0, the output is an abnormal vehicle (no OBU information); if the number of RF OBU vehicle information in Pn is equal to 1 and the RF OBU vehicle license plate information does not completely match the vehicle license plate information characters and / or the vehicle feature information does not match, the output is an abnormal vehicle (the license plate number hung on the vehicle is inconsistent with the OBU information carried); if the number of RF OBU vehicle information in Pn is equal to 1 and the RF OBU vehicle license plate information completely matches the vehicle license plate information characters and the vehicle feature information matches, the output is a normal vehicle.

[0131] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned 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 does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can 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 to be 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.

[0132] Based on the same inventive concept, the embodiment of the present application also provides an abnormal vehicle identification device for implementing the abnormal vehicle 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 abnormal vehicle identification device embodiments provided below can refer to the limitations on the abnormal vehicle identification method above, and will not be repeated here.

[0133] In an exemplary embodiment, Figure 7As shown, an abnormal vehicle identification device 700 is provided, comprising: an acquisition module 702, an image recognition module 704, a signal processing module 706, a coordinate matching module 708 and a recognition result module 710, wherein:

[0134] An acquisition module 702 is used to acquire a target vehicle image of a target vehicle in a target lane and a target electronic tag signal returned by an electronic tag device in the target vehicle;

[0135] The image recognition module 704 is used to perform license plate recognition on the target vehicle image to obtain the recognized license plate and license plate coordinates, and perform vehicle model recognition on the target vehicle image to obtain the recognized vehicle model and vehicle coordinates;

[0136] The signal processing module 706 is used to determine the device coordinates, the real license plate and the real vehicle model corresponding to the electronic tag device based on the target electronic tag signal;

[0137] A coordinate matching module 708 is used to use the device coordinates as reference coordinates of the target vehicle when matching the device coordinates with the license plate coordinates and the vehicle coordinates;

[0138] The recognition result module 710 is used to identify the target vehicle as an abnormal vehicle based on the coordinate quantity of the reference coordinate, the real license plate, the recognized license plate, the real vehicle model and the recognized vehicle model when the reference coordinate is within the vehicle detection range, and obtain an abnormal vehicle recognition result.

[0139] In an exemplary embodiment, the image recognition module 704 is further used to input the target vehicle image into the license plate recognition model, output the recognized license plate and the two-dimensional image coordinates of the license plate corresponding to the target vehicle; obtain the device acquisition angle = of the image acquisition device corresponding to the target vehicle image; based on the device acquisition angle =, convert the two-dimensional image coordinates of the license plate into the three-dimensional space coordinates of the license plate to obtain the license plate coordinates

[0140] In an exemplary embodiment, the abnormal vehicle identification device 700 is also used to obtain a vehicle tracking sequence corresponding to a target lane, and obtain a candidate vehicle information sequence corresponding to the target vehicle based on the vehicle tracking sequence; compare the identified license plate with the last identified license plate in the candidate vehicle information sequence, and when the comparison is successful, add the identified license plate and the license plate coordinates to the last identified license plate; match the identified vehicle model with the last identified vehicle model in the candidate vehicle information sequence, and when the match is successful, add the identified vehicle model and the vehicle coordinates to the last identified vehicle model, and determine the candidate vehicle information sequence as the target vehicle information sequence corresponding to the target vehicle; the target vehicle information sequence is used to perform abnormal vehicle identification on the target vehicle.

[0141] In an exemplary embodiment, an image acquisition device and a radio frequency transceiver device are installed on the target lane; the acquisition module 702 is also used to synchronously trigger the radio frequency transceiver device to send a radio frequency communication signal within the specified range and receive the target electronic tag signal returned by the electronic tag device in the target vehicle within the specified range when acquiring the target vehicle image corresponding to the target vehicle within the specified range of the target lane at the current acquisition moment based on the image acquisition device according to the image acquisition frequency.

[0142] In an exemplary embodiment, the recognition result module 710 is also used to determine that the abnormal vehicle recognition result of the target vehicle is a normal vehicle when the number of coordinates is one and the recognized license plate is consistent with the real license plate, and the recognized vehicle model is consistent with the real vehicle model; otherwise, determine that the abnormal vehicle recognition result of the target vehicle is an abnormal vehicle.

[0143] In an exemplary embodiment, the abnormal vehicle identification device 700 is also used to perform a payment operation based on the user account information in the electronic tag signal when the target vehicle is a normal vehicle, and to control the interception device to release the target vehicle when the payment is successful; and to control the interception device to intercept the target vehicle when the target vehicle is an abnormal vehicle.

[0144] Each module in the abnormal vehicle identification device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0145] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 8 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, 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. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as target vehicle images. 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 program is executed by the processor, an abnormal vehicle identification method is implemented.

[0146] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Fig. 9 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the 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 can be implemented through WIFI, a mobile cellular network, near field communication (Near Field Communication, NFC) or other technologies. When the computer program is executed by the processor, an XXX method is implemented. The display unit of the computer device is used to form a visually visible picture, which can 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.

[0147] Those skilled in the art will understand that Figure 8-Figure 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0148] In an exemplary embodiment, in one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0149] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0150] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0151] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0152] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it 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 the present 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.

[0153] 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.

[0154] The above-described 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 method for identifying abnormal vehicles, characterized in that: The method comprises: Acquire a target vehicle image of a target vehicle in a target lane and a target electronic tag signal returned by an electronic tag device in the target vehicle; Performing license plate recognition on the target vehicle image to obtain the recognized license plate and license plate coordinates, and performing vehicle type recognition on the target vehicle image to obtain the recognized vehicle type and vehicle coordinates; Determine the device coordinates, real license plate and real vehicle model corresponding to the electronic tag device based on the target electronic tag signal; When the device coordinates match the license plate coordinates and the vehicle coordinates, the device coordinates are used as reference coordinates of the target vehicle; When the reference coordinates are within the vehicle detection range, the target vehicle is identified as an abnormal vehicle based on the coordinate quantity of the reference coordinates, the real license plate, the identified license plate, the real vehicle model and the identified vehicle model to obtain an abnormal vehicle identification result.

2. The method according to claim 1, characterized in that The performing license plate recognition on the target vehicle image to obtain the recognized license plate and license plate coordinates includes: Input the target vehicle image into the license plate recognition model, and output the recognized license plate and the two-dimensional image coordinates of the license plate corresponding to the target vehicle; Acquire a device acquisition angle of an image acquisition device corresponding to the target vehicle image; Based on the acquisition angle of the device, the two-dimensional image coordinates of the license plate are converted into three-dimensional space coordinates of the license plate to obtain the license plate coordinates.

3. The method according to claim 1, characterized in that The method further comprises: Acquire a vehicle tracking sequence corresponding to a target lane, and acquire a candidate vehicle information sequence corresponding to the target vehicle based on the vehicle tracking sequence; Compare the identified license plate with the last identified license plate in the candidate vehicle information sequence, and when the comparison is successful, add the identified license plate and the license plate coordinates to the end of the last identified license plate; The identified vehicle model is matched with the last identified vehicle model in the candidate vehicle information sequence. When the match is successful, the identified vehicle model and the vehicle coordinates are added to the last identified vehicle model, and the candidate vehicle information sequence is determined as the target vehicle information sequence corresponding to the target vehicle; the target vehicle information sequence is used to identify the target vehicle as an abnormal vehicle.

4. The method according to claim 1, characterized in that: An image acquisition device and a radio frequency transceiver are installed on the target lane; The step of acquiring a target vehicle image of a target vehicle in a target lane and a target electronic tag signal returned by an electronic tag device in the target vehicle includes: Based on the image acquisition device according to the image acquisition frequency, when collecting the target vehicle image corresponding to the target vehicle within the specified range of the target lane at the current acquisition moment, the radio frequency transceiver device is synchronously triggered to send a radio frequency communication signal within the specified range, and receive the target electronic tag signal returned by the electronic tag device in the target vehicle within the specified range.

5. The method according to claim 1, characterized in that The abnormal vehicle identification is performed on the target vehicle based on the number of coordinates of the reference coordinates, the real license plate, the identified license plate, the real vehicle model and the identified vehicle model to obtain an abnormal vehicle identification result, including: When the number of coordinates is one and the identified license plate is consistent with the real license plate, and the identified vehicle model is consistent with the real vehicle model, determining that the abnormal vehicle identification result of the target vehicle is a normal vehicle; Otherwise, the abnormal vehicle identification result of the target vehicle is determined to be an abnormal vehicle.

6. The method according to claim 1, characterized in that The method further comprises: When the target vehicle is a normal vehicle, a payment operation is performed based on the user account information in the electronic tag signal, and when the payment is successful, the interception device is controlled to release the target vehicle; When the target vehicle is an abnormal vehicle, the interception device is controlled to intercept the target vehicle.

7. An abnormal vehicle identification device, characterized in that: The device comprises: An acquisition module, used to acquire a target vehicle image of a target vehicle in a target lane and a target electronic tag signal returned by an electronic tag device in the target vehicle; An image recognition module is used to perform license plate recognition on the target vehicle image to obtain the recognized license plate and license plate coordinates, and to perform vehicle model recognition on the target vehicle image to obtain the recognized vehicle model and vehicle coordinates; A signal processing module, used to determine the device coordinates, real license plate and real vehicle model corresponding to the electronic tag device based on the target electronic tag signal; A coordinate matching module, used to use the device coordinates as reference coordinates of the target vehicle when the device coordinates match the license plate coordinates and the vehicle coordinates; The identification result module is used to identify the target vehicle as an abnormal vehicle when the device coordinates are within the vehicle detection range based on the coordinate quantity of the reference coordinates, the real license plate, the identified license plate, the real vehicle model and the identified vehicle model to obtain an abnormal vehicle identification result.

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