Toll vehicle type identification method, device and equipment, storage medium and program product

Abstract

The invention relates to a toll vehicle type identification method and device, equipment, a storage medium and a program product. The method comprises the following steps: performing image acquisition on a vehicle through a first camera, and identifying vehicle type information based on the acquired first image; acquiring images of the vehicle through a second camera, and splicing the acquired second images to obtain a first spliced image; identifying a first vehicle body length of the vehicle based on the first spliced image; axle number identification is carried out according to the first spliced image obtained through current splicing, and axle number information of the front portion of the vehicle is obtained; axle number recognition is conducted according to a third image collected by the first camera, and axle number information of the rear portion of the vehicle is obtained; according to the invention, based on the axle number information of the front part and the axle number information of the rear part, the toll model of the vehicle is determined, and the toll model of the vehicle can be accurately and effectively identified, so that the toll model can be transmitted to a toll system, the toll service or card issuing service of a toll station can be improved, and the traffic travel of the vehicle is prevented from being influenced.

Description

Technical Field

[0001] The present application relates to the field of image recognition technology, and in particular to a method, device, equipment, storage medium and program product for identifying a toll vehicle type. Background Art

[0002] The vehicle type recognition equipment at a toll station is usually installed at a distance less than a certain value (such as 20, in meters) from the toll booth or self-service card issuing machine. If the length of the vehicle is greater than the installation distance, the vehicle will not completely pass through the detection area of ​​the vehicle side camera in the vehicle type recognition equipment when it arrives at the toll booth or self-service card issuing machine. The toll model of the vehicle cannot be effectively identified for transmission to the toll system, thus affecting the toll collection or card issuance business of the toll station, and further affecting the vehicle's traffic. Summary of the invention

[0003] Based on this, it is necessary to provide a toll vehicle type identification method, device, equipment, storage medium and program product to address the above technical problems, which can accurately and effectively identify the toll vehicle type for transmission to the toll system, thereby helping to improve the toll collection or card issuance business of the toll station and avoid affecting the vehicle's traffic.

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

[0005] When the vehicle passes through the first detection area, the first camera is used to capture an image of the vehicle, and the vehicle type information is identified based on the captured first image;

[0006] When the vehicle passes through the second detection area, the second camera is used to capture images of the vehicle, and the captured second images are stitched to obtain a first stitched image;

[0007] recognizing a first body length of the vehicle based on the first stitched image;

[0008] When the vehicle has not completely left the second detection area, the vehicle model information meets the preset vehicle model condition, and the first vehicle body length is greater than the preset vehicle body length, performing axle number recognition according to the first spliced ​​image currently obtained by splicing to obtain axle number information of the front part of the vehicle;

[0009] Performing axle number recognition according to a third image captured by the first camera to obtain axle number information of the rear of the vehicle; the third image is captured when the vehicle passes through the second detection area;

[0010] The toll model of the vehicle is determined based on the front axle number information and the rear axle number information.

[0011] In one embodiment, the first camera and the second camera are two cameras on a vehicle type recognition device, and are used to capture different parts of the vehicle;

[0012] The vehicle type recognition device is installed in the toll lane or over-speed lane of the toll station;

[0013] The first camera and the second camera are connected to the same main control unit of the vehicle type recognition device, so that the time source of the first camera is the same as the time source of the second camera.

[0014] In one embodiment, the first camera uses a zoom lens, and the second camera uses a zoom fisheye lens;

[0015] The blind area between the first detection area of ​​the first camera and the detection area of ​​the second camera is less than or equal to a preset length value.

[0016] In one of the embodiments, the distance between the vehicle type identification device and the toll booth or the self-service card issuing machine is not less than a preset distance;

[0017] The preset distance is shorter than the conventional installation distance, which is 20 meters.

[0018] In one embodiment, the method further comprises:

[0019] When the vehicle completely leaves the second detection area, or the vehicle model information does not meet the preset vehicle model condition, or the first vehicle body length is less than or equal to the preset vehicle body length, axle number recognition is performed based on the first spliced ​​image currently spliced ​​to obtain the total number of axles of the vehicle;

[0020] The toll model of the vehicle is determined based on the total number of axles.

[0021] In one embodiment, the performing of axle number identification according to the third image captured by the first camera to obtain the axle number information of the rear of the vehicle includes:

[0022] While the vehicle passes through the second detection area, the first camera continues to capture images of the vehicle, and during the capture process, the axle number is identified for the captured third image until the identified axle number information meets the preset axle number condition, thereby obtaining the axle number information of the rear of the vehicle.

[0023] In a second aspect, the present application further provides a device for identifying a toll vehicle type, the device comprising:

[0024] A first acquisition module, used for acquiring an image of the vehicle through a first camera when the vehicle passes through a first detection area;

[0025] A first recognition module, used to recognize vehicle model information based on the collected first image;

[0026] A second acquisition module is used to acquire images of the vehicle through a second camera when the vehicle passes through a second detection area, and to stitch the acquired second images to obtain a first stitched image;

[0027] A second recognition module, configured to recognize a first body length of the vehicle based on the first stitched image;

[0028] a third recognition module, configured to, when the vehicle has not completely left the second detection area, the vehicle model information satisfies a preset vehicle model condition, and the first vehicle body length is greater than a preset vehicle body length, perform axle number recognition based on the first spliced ​​image currently obtained by splicing, and obtain axle number information of the front part of the vehicle;

[0029] a fourth recognition module, configured to perform axle number recognition based on a third image captured by the first camera to obtain axle number information of the rear portion of the vehicle; the third image is captured when the vehicle passes through a second detection area;

[0030] A determination module is used to determine the toll model of the vehicle based on the front axle number information and the rear axle number information.

[0031] In one embodiment, the first camera and the second camera are two cameras on a vehicle type recognition device, and are used to capture different parts of the vehicle;

[0032] The vehicle type recognition device is installed in the toll lane or over-speed lane of the toll station;

[0033] The first camera and the second camera are connected to the same main control unit of the vehicle type recognition device, so that the time source of the first camera is the same as the time source of the second camera.

[0034] In one embodiment, the first camera uses a zoom lens, and the second camera uses a zoom fisheye lens;

[0035] The blind area between the first detection area of ​​the first camera and the detection area of ​​the second camera is less than or equal to a preset length value.

[0036] In one of the embodiments, the distance between the vehicle type identification device and the toll booth or the self-service card issuing machine is not less than a preset distance;

[0037] The preset distance is shorter than the conventional installation distance, which is 20 meters.

[0038] In one embodiment, the device further comprises:

[0039] a fifth identification module, configured to identify the number of axles according to the first spliced ​​image currently obtained by splicing, to obtain the total number of axles of the vehicle when the vehicle completely leaves the second detection area, or the vehicle model information does not meet the preset vehicle model condition, or the first vehicle body length is less than or equal to the preset vehicle body length;

[0040] The determination module is further used to determine the toll model to which the vehicle belongs based on the total number of axles.

[0041] In one embodiment, the fourth recognition module is also used to continue to capture images of the vehicle through the first camera while the vehicle passes through the second detection area, and to perform axle number recognition on the captured third image during the acquisition process until the recognized axle number information meets a preset axle number condition, thereby obtaining the axle number information of the rear of the vehicle.

[0042] In a third aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the toll vehicle type identification method when executing the computer program.

[0043] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method for identifying a toll vehicle type are implemented.

[0044] In a fifth aspect, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the method for identifying a toll vehicle type are implemented.

[0045] The above-mentioned toll vehicle type recognition method, device, equipment, storage medium and program product, when the vehicle passes through the first detection area, the first camera is used to capture images of the vehicle, and the vehicle type information is recognized based on the captured first image; when the vehicle passes through the second detection area, the second camera is used to capture images of the vehicle, and the captured second images are spliced ​​to obtain a first spliced ​​image; the first body length of the vehicle is recognized based on the first spliced ​​image; when the vehicle has not completely left the second detection area, the vehicle type information meets the preset vehicle type conditions and the first body length is greater than the preset body length, the number of axles is recognized based on the first spliced ​​image obtained by the current splicing to obtain the number of axles of the front of the vehicle; the number of axles is recognized based on the third image captured by the first camera to obtain the number of axles of the rear of the vehicle; the third image is captured when the vehicle passes through the second detection area; based on the front axle number information and the rear axle number information, the toll vehicle type to which the vehicle belongs is determined, so that even if the vehicle has not completely left the detection area of ​​the second camera in the vehicle type recognition device, the toll vehicle type to which the vehicle belongs can be accurately and effectively recognized, and can be transmitted to the toll collection system, which is beneficial to improving the toll collection business or card issuance business of the toll station and avoiding affecting the traffic travel of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A diagram showing an application environment of a method for identifying a charging vehicle type in an embodiment;

[0047] Figure 2 A schematic diagram of a flow chart of a method for identifying a charging vehicle type in one embodiment;

[0048] Figure 3 is a schematic diagram of a vehicle entering a detection area of ​​a vehicle side camera in one embodiment;

[0049] Figure 4 A structural block diagram of a vehicle type identification device in one embodiment;

[0050] Figure 5 A schematic diagram of the rear end of a vehicle entering the detection area of ​​a front camera in one embodiment;

[0051] Figure 6 A schematic diagram of a vehicle rear end image captured by a vehicle front camera in one embodiment;

[0052] Figure 7 A schematic diagram of a flow chart of a method for identifying a charging vehicle type in another embodiment;

[0053] Figure 8 It is a structural block diagram of a device for identifying a toll vehicle type in one embodiment;

[0054] Fig. 9 It is a structural block diagram of a device for identifying a toll vehicle type in another embodiment;

[0055] Fig.10 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0056] 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.

[0057] It should be noted that in the following description, the terms "first, second, ..., fifth" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first, second, ..., fifth" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described here can be implemented in an order other than that illustrated or described here.

[0058] The toll vehicle type recognition method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown in the figure, the vehicle type recognition device 104 can collect images of the vehicle 102 through a camera. For example, when the vehicle enters the detection area of ​​the first camera (such as the front camera), the first camera collects images of the vehicle, thereby identifying the vehicle type information, such as a medium truck or a large truck; in addition, after obtaining the vehicle type information, the vehicle axle number information is further identified to determine the toll vehicle type to which the vehicle belongs.

[0059] Among them, the vehicle type recognition device 104 can be a device equipped with at least two cameras for detecting the toll vehicle type to which the vehicle belongs. For example, the vehicle type recognition device 104 includes a first camera and a second camera. The first camera can be a front camera, which can be used to capture images of the front of the vehicle 102, thereby identifying the vehicle type information of the vehicle 102. In addition, it can also capture images of the rear of the vehicle 102, thereby identifying the axle number information of the rear of the vehicle 102; in the process of capturing images of the rear of the vehicle 102, the second camera also synchronously captures images of the front of the vehicle 102, thereby identifying the axle number information of the front of the vehicle 102, and combining the front axle number information and the rear axle number information, the total axle number of the vehicle 102 can be obtained, and then the toll vehicle type to which the vehicle belongs can be determined based on the total axle number.

[0060] The vehicle 102 may be any type of vehicle, such as a truck, a professional vehicle, and other types of vehicles, such as a household motor vehicle and a passenger car.

[0061] In one embodiment, Figure 2 As shown, a method for identifying a charging vehicle type is provided, wherein the method is Figure 1The vehicle identification device in the example is used to illustrate the process, which includes the following steps:

[0062] S202, when the vehicle passes through the first detection area, the first camera is used to capture an image of the vehicle, and the vehicle type information is identified based on the captured first image.

[0063] The first detection area may be the area that can be covered by the first camera when acquiring images, such as Figure 1 The detection area covered by the front camera (referred to as the front detection area).

[0064] The vehicle passing through the first detection area may be the entire process from the vehicle initially entering to the vehicle leaving the first detection area.

[0065] In one embodiment, when the front of a vehicle begins to enter a first monitoring area, the vehicle identification device begins to capture images of the vehicle in real time through a first camera, and then identifies the vehicle model information based on the captured first image to obtain the vehicle model information.

[0066] The vehicle model information recognition process may specifically include: the vehicle recognition device may extract vehicle head features from the captured first image, recognize the vehicle model information based on the vehicle head features, and when the confidence level of the recognition result meets the recognition conditions (such as the confidence level is greater than or equal to a preset confidence level), use the recognition result as the vehicle model information.

[0067] For example, when a vehicle begins to enter the detection area of ​​the front camera, the front camera can start to capture images of the vehicle, and then identify the vehicle model information of the first image captured. For example, when part of the front of the vehicle (such as more than half of the front of the vehicle) or all of it enters the detection area, the vehicle model information of the first image captured at this time can be identified to obtain the vehicle model information, and then the vehicle model information is sent to the second camera.

[0068] In one embodiment, after acquiring the first image, the vehicle type recognition device may preprocess the first image (such as image denoising and image enhancement), and then recognize the vehicle type information based on the preprocessed first image.

[0069] S204, when the vehicle passes through the second detection area, the second camera is used to collect images of the vehicle, and the collected second images are stitched to obtain a first stitched image.

[0070] The second detection area may be the area that can be covered by the second camera when collecting images, such as Figure 1 The coverage area of ​​the vehicle side camera and Figure 3 The detection area covered by the vehicle side camera (referred to as the vehicle side detection area).

[0071] The vehicle passing through the second detection area may be the entire process from the vehicle initially entering to the vehicle leaving the second detection area.

[0072] The first stitched image may refer to a vehicle image obtained by stitching together non-repeated parts of the collected second images.

[0073] In one embodiment, the first camera and the second camera are two cameras on a vehicle type recognition device, which are used to capture different parts of the vehicle; the vehicle type recognition device is installed in a toll lane or an overload control lane of a toll station; the first camera and the second camera are connected to the same main control unit of the vehicle type recognition device so that the time source of the first camera and the time source of the second camera are the same.

[0074] The vehicle type recognition device may also be referred to as a video vehicle type recognition device, which has at least two cameras, such as a first camera (such as a front camera) and a second camera (such as a side camera). In addition, the two cameras may be installed on the same horizontal line of the vehicle type recognition device, but at different image acquisition angles. Figure 4 , so that the two cameras cover different acquisition areas. The first camera can capture a first image (i.e., a front image) and a third image (i.e., a rear image) of the vehicle, and the second camera can capture a second image (i.e., a front image) of the vehicle.

[0075] The first camera and the second camera are connected to the same main control unit. Figure 4 , thereby ensuring that the time sources of the two cameras are the same, and image acquisition and recognition of the two detection areas can be performed simultaneously.

[0076] In one embodiment, the first camera uses a zoom lens, and the second camera uses a zoom fisheye lens; the blind area between the first detection area of ​​the first camera and the detection area of ​​the second camera is less than or equal to a preset length value.

[0077] The first camera may use a zoom lens Z1 (focal length 3mm-18mm), and the second camera may use a zoom fisheye lens Z2 (focal length 1mm-5mm).

[0078] By adjusting the focal length of the zoom lens Z1, the blind area between the first detection area of ​​the first camera and the detection area of ​​the second camera is less than or equal to the preset length value. For example, the focal length of the zoom lens Z1 is adjusted to ensure that the blind area between the detection area of ​​the front camera and the detection area of ​​the side camera is less than or equal to A meters, A can be 3 meters, and the scene can be adjusted according to the actual situation. Among them, A is less than the minimum body length of the vehicle.

[0079] In one embodiment, the distance between the vehicle type identification device and the toll booth or the self-service card issuing machine is not less than a preset distance; the preset distance is less than a conventional installation distance, which is 20 meters.

[0080] Among them, by adopting the method of the present application, the installation distance between the vehicle type identification equipment and the toll booth or self-service card issuing machine can be shortened from the original not less than 20 meters to not less than C meters = A meters + B meters, where B is the axle number fusion body length threshold, which is 6 meters by default and its size can be configured. For example, the installation distance can be shortened from the original not less than 20 meters to not less than 9 meters; when the vehicle's body length is greater than C meters, the vehicle does not need to completely pass through the detection area of ​​the vehicle type identification equipment to output the toll vehicle type to which the vehicle belongs, which speeds up the efficiency of toll vehicle type identification and also expands the application scenarios of the vehicle type identification equipment.

[0081] The vehicle completely passing through the detection area of ​​the vehicle type recognition device may be the vehicle leaving the detection area of ​​the vehicle type recognition device (ie, the vehicle has left the detection area of ​​the vehicle type recognition device).

[0082] For example, Figure 3 As shown, when the vehicle passes through the second detection area, the vehicle type recognition device collects images of the vehicle through the vehicle side camera, and splices the collected second images to obtain a first spliced ​​image.

[0083] It should be pointed out that when performing image stitching, each time a frame image or a key frame image is acquired, the acquired frame image is stitched with the first stitched image obtained from the last stitching; or, in the process of image acquisition, images separated by a target number of frames are used as key frame images, and then stitched with the first stitched image obtained from the last stitching.

[0084] In one embodiment, before performing image stitching, the vehicle type recognition device may preprocess the second image to be stitched (such as image denoising and image enhancement), and then stitch the preprocessed second image with the first stitched image obtained by the previous stitching to obtain the current first stitched image.

[0085] S206: Identify a first body length of the vehicle based on the first stitched image.

[0086] The first vehicle body length may be the length of the portion of the vehicle body that is identified by using the first spliced ​​image and passes through the second detection area.

[0087] In one embodiment, the vehicle type recognition device may extract the vehicle outline in the first spliced ​​image and obtain the vehicle position information through a vehicle detection algorithm, and finally calculate the first vehicle body length according to the vehicle position information.

[0088] For example, when a vehicle passes through a vehicle model recognition device, it first passes through the detection area of ​​the front camera. The front camera collects images in the detection area in real time and performs recognition. The vehicle model information can be recognized based on the collected front image, such as whether the front feature of the vehicle is a medium-sized truck or above, and the vehicle model information is sent to the side camera. Then, when the vehicle passes through the detection area of ​​the side camera, the side camera collects images in the detection area in real time and performs recognition. When the front model of the vehicle is recognized (that is, when the vehicle begins to pass through the detection area of ​​the side camera), the real-time splicing of the vehicle body image begins. When the rear model of the vehicle is recognized (that is, after the vehicle completely leaves the side camera), the vehicle is separated and the splicing of the vehicle body image ends. In particular, when the real-time splicing of the vehicle body image is performed, the side camera will also calculate the vehicle body length based on the real-time spliced ​​image, which is recorded as L meters.

[0089] S208, when the vehicle has not completely left the second detection area, the vehicle model information meets the preset vehicle model condition, and the first vehicle body length is greater than the preset vehicle body length, the axle number is identified according to the first stitched image currently stitched to obtain the axle number information of the front of the vehicle.

[0090] Among them, the preset vehicle type conditions can be medium-sized and above vehicles, such as medium-sized trucks, large trucks, medium-sized professional vehicles and large professional vehicles.

[0091] The vehicle is divided in the middle. The part on the front side is called the front of the vehicle, and the part on the rear side is called the rear of the vehicle (also known as the tail of the vehicle).

[0092] The first condition is that the vehicle has not completely left the second detection area, the second condition is that the vehicle model information satisfies the preset vehicle model condition, and the third condition is that the first vehicle body length is greater than the preset vehicle body length. When the vehicle satisfies the above three conditions at the same time, the axle number is identified according to the first stitched image currently stitched to obtain the axle number information of the front of the vehicle.

[0093] S210, performing axle number recognition based on the third image captured by the first camera to obtain axle number information of the rear of the vehicle; the third image is captured when the vehicle passes through the second detection area.

[0094] In one embodiment, while the vehicle passes through the second detection area, the first camera continues to capture images of the vehicle, and during the capture process, the axle number is identified for the captured third image until the identified axle number information reaches a preset axle number condition, thereby obtaining the axle number information of the rear of the vehicle.

[0095] Specifically, when the vehicle passes through the second detection area, the first camera also collects images in the first detection area in real time to obtain a third image, which can be referred to as Figure 5 and Figure 6 , and recognize the third image; if there is no front feature in the third image captured by the first camera, and after recognizing that the axle number information is the target axle number, the recognition can be stopped to obtain the axle number information of the rear of the vehicle.

[0096] For example, when a vehicle passes by the side camera, the front camera is also collecting and identifying images in the detection area of ​​the front camera in real time. If there is no front feature in the image and a 2-axle or 3-axle is identified, the starting position of the 2-axle or 3-axle is located in the 1 / 3 area at the bottom of the image. At this time, the axle number information P is sent to the side camera.

[0097] S212, determining the toll model of the vehicle based on the front axle number information and the rear axle number information.

[0098] The total number of axles of the vehicle is related to the toll model to which the vehicle belongs. The toll models are classified as follows:

[0099] Passenger cars: Category 1 to Category 4 passenger cars;

[0100] Trucks: Class 1 to Class 6;

[0101] Professional vehicles: Category 1 professional vehicles to Category 6 professional vehicles.

[0102] Among them, trucks and professional vehicles of categories 3 to 6 are distinguished according to the number of axles, and are all medium-sized trucks and above. For example, for trucks, those with 3 axles are category 3 trucks, those with 4 axles are category 4 trucks, those with 5 axles are category 5 trucks, and those with 6 axles or more are category 6 trucks. The same is true for professional vehicles.

[0103] In another embodiment, when the vehicle does not meet at least one of the above three conditions, the vehicle type recognition device performs axle number recognition based on the first stitched image currently stitched to obtain the total number of axles of the vehicle; and determines the toll vehicle type to which the vehicle belongs based on the total number of axles.

[0104] Specifically, when the vehicle completely leaves the second detection area, or the vehicle model information does not meet the preset vehicle model conditions, or the first vehicle body length is less than or equal to the preset vehicle body length, the vehicle model recognition device performs axle number recognition based on the first spliced ​​image currently spliced ​​to obtain the total number of axles of the vehicle; based on the total number of axles, the toll model to which the vehicle belongs is determined.

[0105] As an example, when the side camera receives the axis number information from the front camera, it checks whether the following conditions are met:

[0106] a. Whether the vehicle has completed the stitching of the vehicle body images (i.e., whether the vehicle has completely passed the vehicle side camera);

[0107] b. Whether the vehicle model information is a medium-sized truck or above;

[0108] c. Whether the body length L meters of the vehicle identified according to the stitched image is greater than a preset body length, the preset body length may be referred to as an axle number fusion body length threshold, denoted as B meters, 6 meters by default, and is configurable.

[0109] When the above three conditions are met, that is, the vehicle has not passed the vehicle side camera, the vehicle model information is a medium truck or above, and the vehicle body length L meters is greater than B meters, the vehicle side camera recognizes the completed stitching image to obtain the vehicle's axle number information Q. The axle number information Q recognized by the vehicle side camera is combined with the axle number information P transmitted to the vehicle side camera by the front camera, and finally the vehicle's axle number information S can be obtained, that is, when L meters>C meters=A meters+B meters, the total number of axles of the vehicle S=P+Q, and the toll model of the vehicle can be determined by the axle number information S; when at least one of the above three conditions is not met, the vehicle will completely pass through the model recognition device, and the vehicle side camera recognizes the stitching completed stitching image to obtain the vehicle's axle number information Q and passenger and cargo characteristics, that is, when L meters≤C meters=A meters+B meters, the total number of axles of the vehicle S=Q, and then the toll model of the vehicle can be obtained by using the toll model fusion algorithm.

[0110] It should be pointed out that when the vehicle passes through or leaves the vehicle type recognition device, it may be the detection area covered by the cameras of the vehicle type recognition device; when the vehicle passes through or leaves the first camera, it may be the detection area covered by the first camera; when the vehicle passes through or leaves the second camera, it may be the detection area covered by the second camera.

[0111] In the above embodiment, when the vehicle passes through the first detection area, the first camera is used to capture images of the vehicle, and the vehicle model information is identified based on the captured first image; when the vehicle passes through the second detection area, the second camera is used to capture images of the vehicle, and the captured second images are spliced ​​to obtain a first spliced ​​image; the first body length of the vehicle is identified based on the first spliced ​​image; when the vehicle has not completely left the second detection area, the vehicle model information meets the preset vehicle model condition, and the first body length is greater than the preset body length, the number of axles is identified based on the first spliced ​​image obtained by the current splicing to obtain the number of axles of the front of the vehicle; the number of axles is identified based on the third image captured by the first camera to obtain the number of axles of the rear of the vehicle; the third image is captured when the vehicle passes through the second detection area; based on the front axle number information and the rear axle number information, the toll vehicle model to which the vehicle belongs is determined, so even if the vehicle has not completely left the detection area of ​​the second camera in the vehicle model recognition device, the toll vehicle model to which the vehicle belongs can be accurately and effectively identified, and can be transmitted to the toll collection system, which is beneficial to improving the toll collection business or card issuance business of the toll station and avoiding affecting the traffic travel of the vehicle.

[0112] In order to more clearly and intuitively understand the technical solution of this application, Figure 7 Describe as follows:

[0113] (1) The front camera collects and recognizes the vehicle in the front detection area, obtains the vehicle model information, and sends the vehicle model information to the side camera;

[0114] (2) When a vehicle enters the vehicle side detection area, the vehicle side camera collects images of the vehicle and stitches the collected images to obtain a stitched image;

[0115] (3) The vehicle side camera detects the vehicle body length based on the stitched image, which is recorded as L meters;

[0116] (4) During the process of stitching and calculating the vehicle body length, the front camera continues to collect images and identify the number of axles, and sends the obtained axle number information P to the side camera;

[0117] (5) The vehicle side camera determines whether the following three conditions are met:

[0118] A. The vehicle has not passed the side camera; B. The vehicle model information is a medium-sized truck or above; C. The vehicle body length L is greater than B meters;

[0119] (6) If the above three conditions are met at the same time, the axis number information Q is identified according to the current stitched image;

[0120] (7) Add the axle number information P obtained by the front camera and the axle number information Q obtained by the side camera to obtain the axle number information S of the vehicle;

[0121] (8) Using the vehicle fare model fusion algorithm, determine the toll model of the vehicle based on the axle number information S;

[0122] (9) If the above three conditions are not met at the same time, the vehicle axle number information S is identified based on the current stitched image, and S = Q at this time.

[0123] 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.

[0124] Based on the same inventive concept, the embodiment of the present application also provides a toll vehicle type identification device for implementing the toll vehicle type 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 the embodiments of one or more toll vehicle type identification devices provided below can refer to the limitations of the toll vehicle type identification method above, and will not be repeated here.

[0125] In one embodiment, Figure 8 As shown, a toll vehicle type recognition device is provided, including: a first acquisition module 802, a first recognition module 804, a second acquisition module 806, a second recognition module 808, a third recognition module 810, a fourth recognition module 812 and a determination module 814, wherein:

[0126] A first acquisition module 802 is used to acquire images of the vehicle through a first camera when the vehicle passes through a first detection area;

[0127] A first recognition module 804, configured to recognize vehicle type information based on the collected first image;

[0128] The second acquisition module 806 is used to acquire images of the vehicle through the second camera when the vehicle passes through the second detection area, and to stitch the acquired second images to obtain a first stitched image;

[0129] A second recognition module 808, configured to recognize a first body length of the vehicle based on the first stitched image;

[0130] The third recognition module 810 is used to identify the number of axles according to the first spliced ​​image obtained by current splicing to obtain the number of axles of the front part of the vehicle when the vehicle has not completely left the second detection area, the vehicle model information meets the preset vehicle model condition, and the first vehicle body length is greater than the preset vehicle body length;

[0131] The fourth recognition module 812 is used to perform axle number recognition based on the third image captured by the first camera to obtain axle number information of the rear of the vehicle; the third image is captured when the vehicle passes through the second detection area;

[0132] The determination module 814 is used to determine the toll model of the vehicle based on the front axle number information and the rear axle number information.

[0133] In one embodiment, the first camera and the second camera are two cameras on a vehicle type recognition device, and are used to capture different parts of the vehicle;

[0134] The vehicle type recognition equipment is installed in the toll lane or over-speed lane of the toll station;

[0135] The first camera and the second camera are connected to the same main control unit of the vehicle type recognition device, so that the time source of the first camera and the time source of the second camera are the same.

[0136] In one embodiment, the first camera uses a zoom lens and the second camera uses a zoom fisheye lens;

[0137] The blind area between the first detection area of ​​the first camera and the detection area of ​​the second camera is less than or equal to a preset length value.

[0138] In one of the embodiments, the distance between the vehicle type identification device and the toll booth or the self-service card issuing machine is not less than a preset distance;

[0139] The preset distance is shorter than the conventional installation distance, which is 20 meters.

[0140] In one embodiment, if Fig. 9 As shown, the device also includes:

[0141] The fifth identification module 816 is used to identify the number of axles according to the first spliced ​​image obtained by current splicing to obtain the total number of axles of the vehicle when the vehicle completely leaves the second detection area, or the vehicle model information does not meet the preset vehicle model condition, or the first vehicle body length is less than or equal to the preset vehicle body length;

[0142] The determination module 814 is further configured to determine the toll model of the vehicle based on the total number of axles.

[0143] In one embodiment, the fourth recognition module 812 is also used to continue to capture images of the vehicle through the first camera while the vehicle passes through the second detection area, and to perform axle number recognition on the captured third image during the collection process until the recognized axle number information reaches a preset axle number condition, thereby obtaining the axle number information of the rear of the vehicle.

[0144] In the above embodiment, when the vehicle passes through the first detection area, the first camera is used to capture images of the vehicle, and the vehicle model information is identified based on the captured first image; when the vehicle passes through the second detection area, the second camera is used to capture images of the vehicle, and the captured second images are spliced ​​to obtain a first spliced ​​image; the first body length of the vehicle is identified based on the first spliced ​​image; when the vehicle has not completely left the second detection area, the vehicle model information meets the preset vehicle model condition, and the first body length is greater than the preset body length, the number of axles is identified based on the first spliced ​​image obtained by the current splicing to obtain the number of axles of the front of the vehicle; the number of axles is identified based on the third image captured by the first camera to obtain the number of axles of the rear of the vehicle; the third image is captured when the vehicle passes through the second detection area; based on the front axle number information and the rear axle number information, the toll vehicle model to which the vehicle belongs is determined, so even if the vehicle has not completely left the detection area of ​​the second camera in the vehicle model recognition device, the toll vehicle model to which the vehicle belongs can be accurately and effectively identified, and can be transmitted to the toll collection system, which is beneficial to improving the toll collection business or card issuance business of the toll station and avoiding affecting the traffic travel of the vehicle.

[0145] Each module in the above-mentioned toll vehicle type recognition device can be implemented in whole or in part by software, hardware or a combination thereof. Each of the above-mentioned modules 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 the corresponding operations of each of the above modules.

[0146] In one embodiment, a computer device is provided. The computer device may be a vehicle type identification device, and its internal structure diagram may be as follows: Fig.10As shown. 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 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 image data. 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, a method for identifying a charging vehicle type is implemented.

[0147] Those skilled in the art will understand that Fig.10 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 one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps of the above-mentioned toll vehicle type identification method 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 of the above-mentioned toll vehicle type identification method are implemented.

[0150] In one embodiment, a computer program product is provided, including a computer program, which implements the steps of the above-mentioned toll vehicle type identification method 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 laws, regulations and standards of relevant countries and regions.

[0152] 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 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 this application can include at least one of non-volatile 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), magnetoresistive 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, 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 specification.

[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 a toll vehicle type, characterized in that: The method comprises: When the vehicle passes through the first detection area, the first camera is used to capture an image of the vehicle, and the vehicle type information is identified based on the captured first image; When the vehicle passes through the second detection area, the second camera is used to capture images of the vehicle, and the captured second images are stitched to obtain a first stitched image; recognizing a first body length of the vehicle based on the first stitched image; When the vehicle has not completely left the second detection area, the vehicle model information meets the preset vehicle model condition, and the first vehicle body length is greater than the preset vehicle body length, performing axle number recognition according to the first spliced ​​image currently obtained by splicing to obtain axle number information of the front part of the vehicle; Performing axle number recognition according to a third image captured by the first camera to obtain axle number information of the rear of the vehicle; the third image is captured when the vehicle passes through the second detection area; The toll model of the vehicle is determined based on the front axle number information and the rear axle number information.

2. The method according to claim 1, characterized in that The first camera and the second camera are two cameras on the vehicle type recognition device, and are used to capture different parts of the vehicle; The vehicle type recognition device is installed in the toll lane or over-speed lane of the toll station; The first camera and the second camera are connected to the same main control unit of the vehicle type recognition device, so that the time source of the first camera is the same as the time source of the second camera.

3. The method according to claim 2, characterized in that The first camera uses a zoom lens, and the second camera uses a zoom fisheye lens; The blind area between the first detection area of ​​the first camera and the detection area of ​​the second camera is less than or equal to a preset length value.

4. The method according to claim 2, characterized in that: The distance between the vehicle type identification device and the toll booth or the self-service card issuing machine is not less than the preset distance; The preset distance is shorter than the conventional installation distance, which is 20 meters.

5. The method according to claim 1, characterized in that The method further comprises: When the vehicle completely leaves the second detection area, or the vehicle model information does not meet the preset vehicle model condition, or the first vehicle body length is less than or equal to the preset vehicle body length, axle number recognition is performed according to the first spliced ​​image currently spliced ​​to obtain the total number of axles of the vehicle; The toll model of the vehicle is determined based on the total number of axles.

6. The method according to any one of claims 1 to 5, characterized in that: The step of performing axle number recognition according to the third image captured by the first camera to obtain axle number information of the rear portion of the vehicle includes: When the vehicle passes through the second detection area, the first camera continues to capture images of the vehicle, and during the capture process, the axle number is identified for the captured third image until the identified axle number information meets the preset axle number condition, thereby obtaining the axle number information of the rear of the vehicle.

7. A vehicle type identification device, characterized in that: The device comprises: A first acquisition module, used for acquiring an image of the vehicle through a first camera when the vehicle passes through a first detection area; A first recognition module, used to recognize vehicle model information based on the collected first image; A second acquisition module is used to acquire images of the vehicle through a second camera when the vehicle passes through a second detection area, and to stitch the acquired second images to obtain a first stitched image; A second recognition module, configured to recognize a first body length of the vehicle based on the first stitched image; a third recognition module, configured to, when the vehicle has not completely left the second detection area, the vehicle model information satisfies a preset vehicle model condition, and the first vehicle body length is greater than a preset vehicle body length, perform axle number recognition based on the first spliced ​​image currently obtained by splicing, and obtain axle number information of the front part of the vehicle; a fourth recognition module, configured to perform axle number recognition based on a third image captured by the first camera to obtain axle number information of the rear portion of the vehicle; the third image is captured when the vehicle passes through a second detection area; A determination module is used to determine the toll model of the vehicle based on the front axle number information and the rear axle number information.

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