Rear camera vehicle following supplementary shooting method, system and device and storage medium

Abstract

The invention provides a rear camera vehicle following supplementary shooting method, system and device and a storage medium, and the method comprises the steps: enabling a current vehicle to shield the license plate of a to-be-detected vehicle, enabling the license plate in a first image shot by a front camera to be shielded, and enabling the license plate information to be not normally recognized, automatically switching to the rear camera, adjusting the angle of the rear camera, and then carrying out the recognition of the license plate information. And shooting a second image in which the license plate is shielded least or not, obtaining license plate information corresponding to the to-be-detected vehicle from the second image, and recording the currently obtained license plate information in the parking lot to ensure the integrity and accuracy of the vehicle entering and exiting record in the parking lot. Furthermore, the system can automatically detect the shielding condition of the front vehicle and intelligently switch the cameras for supplementary shooting, manual intervention of parking lot management is reduced, the completeness of vehicle entering and exiting records is improved through supplementary shooting of the rear camera, and efficient operation of the parking lot management system is facilitated.

Description

Technical Field

[0001] The present application relates to the field of license plate recognition technology, and in particular to a method, system, device and storage medium for taking supplementary photos following a vehicle with a rear-mounted camera. Background Art

[0002] In the field of intelligent transportation systems and vehicle management, the automatic recognition technology of vehicle identity is one of the key technologies to achieve efficient traffic management and improve road safety. At present, vehicle identity recognition mainly relies on the license plate recognition system to identify the license plate number by capturing vehicle images. Existing technologies generally integrate the implementation of computer vision technologies such as image acquisition, license plate positioning, and character recognition. However, due to relying solely on visual data, the accuracy and robustness of the recognition system in complex environments such as poor light, damaged or occluded license plates are still limited. In modern parking lots, automated vehicle recognition systems have been widely used in vehicle access management and toll collection systems, which usually rely on front cameras to capture vehicle license plate information.

[0003] When multiple vehicles follow closely in and out of a parking lot, the multiple cameras used to identify license plates may lose the opportunity to identify the license plate information of the vehicle behind due to the obstruction of the vehicle in front, resulting in the failure to identify the following vehicle. In traditional parking lots, when license plates cannot be identified, the vehicle may be guided to reverse and then move forward to trigger a second recognition. However, when the traffic volume is heavy, there is often no space for the car to reverse and then move forward for recognition, or repeated maneuvers waste a lot of time, causing congestion. Summary of the invention

[0004] The technical problem to be solved by this application is that when multiple vehicles follow closely in and out of a parking lot, multiple cameras used to identify license plates may lose the opportunity to identify the license plate information of the vehicle behind due to the obstruction of the vehicle in front, resulting in the failure to identify the following vehicle. In traditional parking lots, when license plates cannot be identified, the vehicle may be guided to reverse and then move forward to trigger secondary identification. However, when the traffic volume is heavy, there is often no space for the car to reverse and then move forward for identification, or repeated maneuvers waste a lot of time, causing congestion.

[0005] In order to solve the above problems, in order to solve the above technical problems or at least partially solve the above technical problems, the present application provides a method, system, device and storage medium for following a vehicle with a rear camera.

[0006] In a first aspect, the present invention discloses a method for taking supplementary photos of a vehicle with a rear camera, which comprises the following steps:

[0007] The vehicle to be detected enters the detection area; the detection area is provided with a front camera and a rear camera, and the rear camera is installed on the top or side of the vehicle entrance channel of the detection area;

[0008] The front camera captures the license plate image of the vehicle to be detected to obtain a first image, and detects the integrity of the license plate of the vehicle to be detected from the first image;

[0009] When the license plate of the vehicle to be detected is incomplete, the rear camera is started to capture a second image of the license plate of the vehicle to be detected from another angle, and the license plate information is recognized from the second image.

[0010] Preferably, the vehicle to be detected enters the detection area, comprising the following steps:

[0011] The sensing device is installed near the detection area to detect vehicles in the detection area. The sensing device collects the electrical signal of the front camera corresponding to the sensing device when the vehicle to be detected enters the detection area.

[0012] Preferably, after the vehicle to be detected enters the detection area, the following steps are included: collecting the distance between the vehicle to be detected and the vehicle in front, comparing it with a preset distance, when the distance between the vehicle to be detected and the vehicle in front is greater than the preset distance, capturing a first image through a front camera, recognizing the license plate information from the first image, and when the distance between the vehicle to be detected and the vehicle in front is less than or equal to the preset distance, detecting the integrity of the vehicle through the first image captured by the front camera.

[0013] Preferably, the front camera captures the license plate image of the vehicle to be detected to obtain a first image, and the integrity of the license plate of the vehicle to be detected is detected from the first image, specifically comprising the following steps:

[0014] Predetermine the shape of the license plate;

[0015] The front camera captures the license plate image of the vehicle to be detected to obtain a first image;

[0016] Performing a license plate region feature extraction process on the first image to obtain a shape feature of the first license plate region, a color of the first license plate, and a text feature in the first license plate region;

[0017] Comparing the shape feature of the first license plate area with the predetermined license plate shape to determine the integrity of the license plate area;

[0018] Based on the color of the first license plate, extract the number of characters in the license plate area based on the text features in the first license plate area, compare the number of characters in the traditional license plate rules, and determine the integrity of the characters in the license plate area;

[0019] Based on the above results, the license plate integrity of the vehicle to be tested is detected.

[0020] Preferably, when the vehicle to be detected is close to the vehicle and the license plate of the vehicle to be detected is incomplete, the rear camera is started to shoot the license plate behind the vehicle to be detected and identify the license plate information, which specifically includes the following steps:

[0021] If the distance between the vehicle to be detected and the vehicle in front is less than the preset distance, and the license plate of the vehicle to be detected is blocked by other vehicles, it is determined that the vehicle license plate cannot be recognized normally, and the rear camera is started to take pictures;

[0022] The rear camera temporarily captures the license plate image to obtain a temporary image, determines the coordinates of the license plate according to the first image and the temporary image, and adjusts the shooting direction of the rear camera until the license plate image with the least obstruction can be captured to obtain a second image;

[0023] Perform license plate recognition processing on the second image to obtain a license plate number corresponding to the license plate.

[0024] Preferably, the rear camera temporarily captures the license plate image to obtain a temporary image, determines the coordinates of the license plate according to the first image and the temporary image, and adjusts the shooting direction of the rear camera until the least obstructed license plate image can be captured to obtain the second image, which specifically includes the following steps:

[0025] After the rear camera is started, it first takes an image with the license plate to be detected to obtain a temporary image;

[0026] Get the coordinates and parameters of the front camera and rear camera, and obtain the relative position and direction between the front camera and rear camera through camera calibration.

[0027] Detecting the position of the license plate in the first image and the temporary image, and obtaining the coordinates of the license plate in the first image and the coordinates of the license plate in the temporary image;

[0028] Calculate the difference in the license plate position coordinates in the front and rear camera images to get the disparity, perform depth calculation based on the disparity, front camera parameters, and rear camera parameters to get the license plate depth, that is, the distance between the front camera, rear camera and the license plate;

[0029] Using the coordinates of the license plate in the first image and the temporary image, the parameters of the front camera, the parameters of the rear camera, and the depth of the license plate, the spatial coordinates of the license plate are reversely calculated, thereby determining the position of the license plate;

[0030] The rear camera is rotated until the license plate image with the least obstruction can be captured to obtain a second image.

[0031] Preferably, the method further comprises the following steps:

[0032] The second image cannot completely obtain the license plate number of the vehicle to be detected, and is marked as an abnormal identification of the vehicle to be detected;

[0033] The sensor detects that the vehicle has left the detection area and determines that the current vehicle is in an abnormal state;

[0034] Generate an exception report and notify the parking lot management staff to handle it manually.

[0035] In a second aspect, the present invention discloses a system for following a vehicle with a rear camera and then taking supplementary photos, which includes the steps of the above-mentioned method for following a vehicle with a rear camera and then taking supplementary photos.

[0036] In a third aspect, the present invention discloses an electronic device, which includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0037] Memory, used to store computer programs;

[0038] The processor is used to implement the steps of the method of following a vehicle and taking supplementary photos with a rear camera when executing a program stored in the memory.

[0039] In a fourth aspect, the present invention discloses a storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the above-mentioned method for following a vehicle and taking supplementary photos with a rear-mounted camera.

[0040] The above technical solution provided by this application has the following advantages compared with the prior art:

[0041] The present application provides a method, system, device and storage medium for following a vehicle and taking supplementary photos with a rear camera. In the method, when the current vehicle blocks the license plate, the license plate is blocked in the first image taken by the front camera, and the license plate information cannot be normally recognized. The method automatically switches to the rear camera, adjusts the angle of the rear camera, and takes a second image in which the license plate is least blocked or not blocked. The license plate information corresponding to the vehicle to be detected is obtained from the second image, and the parking lot records the currently obtained license plate information to ensure the integrity and accuracy of the records of vehicles entering and exiting the parking lot.

[0042] Furthermore, when determining whether the rear camera needs to be switched, the results of detecting the distance between the vehicle to be detected and the vehicle in front and whether the first image is blocked can be considered to determine whether the rear camera needs to be started, thereby ensuring that the license plate can be acquired correctly and quickly so that the vehicle can pass through the parking lot quickly.

[0043] Furthermore, the system can automatically detect obstructions caused by the vehicle in front and intelligently switch the camera for supplementary shooting, reducing manual intervention in parking lot management. The supplementary shooting with the rear camera improves the integrity of vehicle entry and exit records, which helps the efficient operation of the parking lot management system. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0045] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0046] Figure 1 A flowchart of a method for taking supplementary photos with a rear camera following a vehicle provided in this application Figure 1 ;

[0047] Figure 2 A flowchart of a method for taking supplementary photos with a rear camera following a vehicle provided in this application Figure 2 . DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0049] First, see Figure 1-2 The present invention discloses a method for supplementary shooting with a rear camera following a vehicle, which comprises the following steps:

[0050] Step S1: The vehicle to be detected enters the detection area; the detection area is provided with a front camera and a rear camera, and the rear camera is installed on the top or side of the vehicle entrance channel of the detection area;

[0051] Step S2: Collect the distance between the vehicle to be detected and the vehicle in front, and compare it with the preset distance. When the distance between the vehicle to be detected and the vehicle in front is greater than the preset distance, capture a first image through the front camera, and recognize the license plate information from the first image. When the distance between the vehicle to be detected and the vehicle in front is less than or equal to the preset distance, detect the integrity of the vehicle through the first image captured by the front camera.

[0052] Step S3: the front camera captures the license plate image of the vehicle to be detected to obtain a first image, and detects the integrity of the license plate of the vehicle to be detected from the first image;

[0053] Step S4: When the vehicle to be detected is too close to the vehicle in front and the license plate of the vehicle to be detected is blocked, the rear camera is started to capture a second image of the license plate of the vehicle to be detected from another angle, and the license plate information is identified from the second image;

[0054] Step S5: If the recognition is successful, the recognized license plate information and the first image and the second image are uploaded to the parking lot management system; if the second image cannot fully obtain the license plate number of the vehicle to be detected, it is marked as an abnormal recognition of the vehicle to be detected; the sensor detects that the vehicle has left the detection area, determines that the current vehicle is in an abnormal condition, generates an abnormality report, and notifies the parking lot management personnel to handle it manually.

[0055] Specifically, in step S1, a detection area is reserved before entering the parking lot for vehicle license plate recognition and obtaining relevant information of the vehicle, so as to facilitate the management of vehicles entering and leaving the parking lot. The front camera and the rear camera are set near the detection area. The front camera is installed at the end of the vehicle entrance channel and faces the front of the vehicle; the rear camera can be installed on the top or side of the vehicle entrance channel, and the license plate of the vehicle in the detection area can be photographed from the top or side. Among them, the top installation method is adopted, according to the height range of most vehicles on the market, the position of the front of the vehicle to be tested can be photographed when the front vehicle blocks the vehicle to be tested, and the rear camera is installed at this position; the side installation method is adopted, and the position of the front of the rear vehicle to be tested can be photographed when the front vehicle blocks the vehicle to be tested according to the specific width of the channel, and the rear camera is set at this position.

[0056] Specifically, in step S2, the distance between the vehicle to be detected and the vehicle in front is obtained and compared with the preset distance. If it is less than or equal to the preset distance, it is judged that the detected vehicle is following the vehicle too closely. In the subsequent steps, it is necessary to combine the license plate integrity detection to determine whether it is necessary to start the rear camera to take a supplementary shot. If it is greater than the preset distance, it can be judged that the detected vehicle is not following the vehicle too closely, and the first image can be taken by the front camera to identify the license plate.

[0057] Specifically, in step S3, the first image taken by the front camera is used to extract the license plate information and license plate shape, including license plate characters, the number of license plate characters, the location of the license plate, the color of the vehicle, etc., through an image recognition algorithm. The extracted license plate shape is used to determine whether it is blocked. When it is detected that there is no obstruction, the license plate recognition is directly performed to obtain the license plate information. When it is detected that there is obstruction, the rear camera is started to shoot.

[0058] Specifically, in step S4, based on the detection result of the front camera, it is determined whether the license plate in the first image is blocked. After determining that the license plate is blocked, the rear camera is started, and the rear camera captures a more complete license plate image to obtain a second image, and the license plate information is obtained from the second image. In addition, step S4 can be combined with the results of steps S2 and S3 to determine whether the rear camera needs to be started, but it is also feasible to determine whether the rear camera needs to be started only based on the result of step S3.

[0059] Specifically, in step S5, the license plate is successfully identified from the first image or the second image, and the license plate information is uploaded to the parking lot management system together with the first image and the second image to facilitate the management of entering vehicles. However, the complete license plate number cannot be obtained in the second image, and it is edited as an exception. The exception information is uploaded to the system, and the management personnel are notified to perform manual processing to maintain the normal operation of the parking lot.

[0060] It can be understood that the rear camera follow-up shooting method provided by the present application, when the current vehicle blocks the license plate, resulting in the license plate being blocked in the first image shot by the front camera, and the license plate information cannot be normally recognized, the rear camera is automatically switched to, and after adjusting the angle of the rear camera, the second image with the least or no blocking of the license plate is shot, and the license plate information corresponding to the vehicle to be detected is obtained from the second image, and the parking lot records the currently obtained license plate information to ensure the integrity and accuracy of the vehicle entry and exit records in the parking lot. Further, when the rear camera needs to be switched, it can be considered to combine the results of detecting the distance between the vehicle to be detected and the front vehicle and whether the first image is blocked, to determine whether the rear camera needs to be started, to ensure that the license plate can be correctly and quickly obtained, so that the vehicle can quickly pass through the parking lot. Further, the system can automatically detect the blocking situation of the front vehicle, and intelligently switch the camera for supplementary shooting, reducing manual intervention in parking lot management, and improving the integrity of vehicle entry and exit records through supplementary shooting with the rear camera, which is conducive to the efficient operation of the parking lot management system.

[0061] Furthermore, since the front camera is fixedly installed, the license plate of the vehicle to be detected cannot be obtained after it is blocked by the vehicle in front. By taking supplementary photos with the rear camera, more complete license plate information can be obtained to meet the actual needs of the parking lot.

[0062] Step S1 includes the following steps:

[0063] The sensing device is installed near the detection area to detect vehicles in the detection area. The sensing device collects the electrical signal of the front camera corresponding to the sensing device when the vehicle to be detected enters the detection area.

[0064] It can be understood that sensing equipment, front camera and rear camera are set near the detection area. When the vehicle arrives at the detection area, the sensing equipment senses whether the vehicle to be detected has reached the corresponding position, and then wakes up the front camera through an electrical signal to capture the first image.

[0065] Optionally, the sensing device includes a combination of one or more sensing devices such as an infrared sensor, an ultrasonic sensor, and a lidar.

[0066] In step S2, the distance between the vehicle to be detected and the vehicle in front is collected by a sensing device. In this embodiment, the preset vehicle distance is 20 cm, but the preset vehicle distance can be customized and is not limited to the preset vehicle distance in this embodiment, and can be adjusted according to actual needs.

[0067] Optionally, the distance between the vehicle to be detected and the preceding vehicle is collected by using any one of an infrared sensor, an ultrasonic sensor, and a laser radar.

[0068] Step S3 specifically includes the following steps:

[0069] Step S31: predetermine the shape of the license plate;

[0070] Step S32: The front camera captures the license plate image of the vehicle to be detected to obtain a first image;

[0071] Step S33: performing a license plate region feature extraction process on the first image to obtain a first license plate region shape feature, a first license plate color, and text features within the first license plate region;

[0072] Step S34: comparing the shape feature of the first license plate area with the predetermined license plate shape to determine the integrity of the license plate area;

[0073] Step S35: based on the color of the first license plate, extract the number of characters in the license plate area from the text features in the first license plate area, compare the number of characters in the traditional license plate rules, and determine the integrity of the characters in the license plate area;

[0074] Step S36: Based on the above results, the integrity of the license plate of the vehicle to be inspected is detected.

[0075] Specifically, the first license plate area is compared with the predetermined license plate shape to determine whether the first license plate area is complete, and then all text features are obtained in the first license plate area, and the characters and the number of characters in the text features are extracted. In the traditional license plate rules, the number of characters is fixed, such as the license plate of new energy vehicles is 8-bit characters, and the license plate of ordinary fuel vehicles is 7-bit characters. According to the color of the license plate, it can be determined which type of vehicle the current vehicle to be detected belongs to, and then according to the traditional license plate rules, it is determined whether the number of extracted characters is complete. If characters are missing, it can be determined that the license plate in the current first image is blocked. If there are no missing characters, it can be determined that the license plate in the current first image is not blocked. Using multi-feature detection, such as comparing the shape features of the license plate area with the predetermined shape, analyzing the text features based on the license plate color to determine the number of characters and comparing them with the traditional rules, it is comprehensively determined from multiple aspects whether the license plate is blocked, avoiding the misjudgment of a single factor.

[0076] Step S4 specifically includes the following steps:

[0077] Step S41: the distance between the vehicle to be detected and the preceding vehicle is less than a preset distance, and the license plate of the vehicle to be detected is blocked by other vehicles, so it is determined that the vehicle license plate cannot be recognized normally, and the rear camera is started to take pictures;

[0078] Step S42: the rear camera temporarily captures the license plate image to obtain a temporary image, determines the coordinates of the license plate according to the first image and the temporary image, and adjusts the shooting direction of the rear camera until the license plate image with the least obstruction can be captured to obtain a second image;

[0079] Step S43: performing license plate recognition processing on the second image to obtain a license plate number corresponding to the license plate.

[0080] Specifically, based on the distance between the vehicle to be detected and the vehicle in front and whether the license plate is blocked by a vehicle in the first image, it is determined whether the vehicle license plate cannot be recognized normally. When the recognition result is that the vehicle license plate is blocked and the full license plate information cannot be obtained, the rear camera is started to shoot and the complete license plate and the license plate information above are obtained. The rear camera captures a temporary image, and the spatial coordinates of the license plate in the detection area are determined based on the license plate in the temporary image, so that the rear camera can adjust its own orientation to ensure that the license plate to be detected in the subsequent images can reduce occlusion, so that the character information on the license plate can be captured. For the recognition of the license plate in the second image, the license plate information in the second image is obtained according to the steps of license plate area recognition, license plate color recognition, and license plate character recognition.

[0081] Step S42 specifically includes the following steps:

[0082] Step S421: After the rear camera is started, an image with the license plate to be detected is first captured to obtain a temporary image;

[0083] Step S422: Obtain the coordinates and parameters of the front camera and the rear camera, and obtain the relative position and direction between the front camera and the rear camera through camera calibration processing; (parameters, such as focal length, baseline distance, camera optical center image coordinates)

[0084] Step S423: Detecting the position of the license plate in the first image and the temporary image, and obtaining the coordinates of the license plate in the first image and the coordinates of the license plate in the temporary image;

[0085] Step S424: Calculate the difference in the position coordinates of the license plate in the front and rear camera images to obtain the parallax, perform depth calculation processing according to the parallax, the front camera parameters, and the rear camera parameters to obtain the license plate depth, that is, the distance between the front camera, the rear camera and the license plate;

[0086] Step S425: using the coordinates of the license plate in the first image and the temporary image, the front camera parameters, the rear camera parameters and the license plate depth, reversely calculate the spatial coordinates of the license plate, and then determine the license plate position;

[0087] Step S426: Rotate the rear camera until the least obstructed license plate image can be captured to obtain a second image.

[0088] Specifically, the rear camera is provided with a rotatable platform so that the rear camera can adjust its shooting angle. First, a temporary image with the license plate to be detected is taken as a reference for subsequent adjustment of its own shooting angle, and the coordinates and parameters of the front camera and the rear camera are obtained to obtain the relative position and direction of the two cameras. The license plate position in the first image and the license plate position in the temporary image are combined, and the three-dimensional coordinates of the license plate in space are estimated through parallax, so as to adjust the shooting angle of the rear camera and take clearer license plate images.

[0089] As an embodiment, the coordinate system of the front camera is set to C1, and the coordinate system of the rear camera is set to C2. The position of the license plate detected by the front camera in the image is obtained as (u1, v1), and the position of the license plate detected by the rear camera is obtained as (u2, v2). The three-dimensional coordinates of the license plate are calculated using the parallax formula, d = u1-u2. The parallax represents the difference in the horizontal coordinates of the two camera images of the license plate. This difference is a key factor in the subsequent triangulation calculation of the license plate depth. Based on the parallax d, the depth of the license plate can be estimated by triangulation, that is, the distance between the license plate and the two cameras. The depth calculation formula is: Z = (f*B) / d, where f is the focal length of the camera, which reflects the optical characteristics of the camera lens and determines the size and distance relationship of the image; B is the baseline distance between the two cameras, which is an important parameter of the position relationship between the two cameras; d is the parallax. The X coordinate calculation formula of the license plate coordinates is as follows: Where (u1, v1) is the coordinate of the license plate in the front camera image, c x is the image coordinate of the camera optical center, f x is the focal length of the camera on the x-axis, and the Y coordinate calculation formula of the license plate coordinates is as follows: Where (u1, v1) is the coordinate of the license plate in the front camera image, c y is the image coordinate of the camera optical center, f y is the focal length of the camera on the y-axis, according to the horizontal coordinate u1 of the license plate in the front camera image and the horizontal coordinate c of the camera optical center x , the focal length f of the camera on the x-axis x And the depth Z calculated previously is used to determine the X and Y coordinates of the license plate in space, thereby obtaining the position of the license plate in three-dimensional space relative to the two cameras.

[0090] In a second aspect, the present invention discloses a system for following a vehicle with a rear camera and then taking supplementary photos, which includes the steps of the above-mentioned method for following a vehicle with a rear camera and then taking supplementary photos.

[0091] Specifically, the system includes a front camera, a rear camera, and a sensing device. The front camera faces the vehicle to be detected, shoots the license plate in front of the vehicle, and captures the license plate information. The rear camera can be installed on the top or side of the detection area. It has a rotation function and can adjust the shooting angle through its own servo motor (or stepper motor). The servo motor control system can adjust the camera's pitch angle (up and down adjustment) and horizontal angle (left and right adjustment) according to the input control signal, and the rear camera can turn on the autofocus system to make the captured image clearer. The sensing device is used to obtain information about the vehicle's arrival at the detection area and collect the distance between the vehicle to be detected and the vehicle in front.

[0092] The system runs a method for supplementary shooting with a rear camera. When the license plate is blocked by the front camera, the license plate is blocked in the first image captured by the front camera, and the license plate information cannot be recognized normally. The system automatically switches to the rear camera, adjusts the angle of the rear camera, and captures a second image in which the license plate is least blocked or not blocked. The license plate information corresponding to the vehicle to be detected is obtained from the second image, and the parking lot records the currently obtained license plate information to ensure the integrity and accuracy of the vehicle entry and exit records in the parking lot. Further, when determining whether the rear camera needs to be switched, the results of combining the distance between the vehicle to be detected and the front vehicle and whether the first image is blocked can be considered to determine whether the rear camera needs to be started, so as to ensure that the license plate can be correctly and quickly acquired, so that the vehicle can quickly pass through the parking lot. Further, the system can automatically detect the blocking of the front vehicle, and intelligently switch the camera for supplementary shooting, reducing manual intervention in parking lot management. The supplementary shooting of the rear camera improves the integrity of the vehicle entry and exit records, which helps the efficient operation of the parking lot management system.

[0093] In a third aspect, the present invention discloses an electronic device, which includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0094] Memory, used to store computer programs;

[0095] The processor is used to implement the steps of the method of following a vehicle and taking supplementary photos with a rear camera when executing a program stored in the memory.

[0096] Specifically, the electronic device can run a program in the memory, which implements the method of supplementary shooting with the rear camera following the vehicle. When the current vehicle blocks the license plate, the license plate is blocked in the first image captured by the front camera, and the license plate information cannot be recognized normally. The rear camera is automatically switched to adjust the angle of the rear camera, and the second image with the least or no blocking of the license plate is captured. The license plate information corresponding to the vehicle to be detected is obtained from the second image, and the parking lot records the currently obtained license plate information to ensure the integrity and accuracy of the vehicle entry and exit records in the parking lot. Further, when the rear camera needs to be switched, it can be considered to combine the results of detecting the distance between the vehicle to be detected and the front vehicle and whether the first image is blocked, to determine whether the rear camera needs to be started, to ensure that the license plate can be correctly and quickly obtained, so that the vehicle can quickly pass through the parking lot. Further, the system can automatically detect the blocking situation of the front vehicle, and intelligently switch the camera for supplementary shooting, reduce the manual intervention of the parking lot management, and improve the integrity of the vehicle entry and exit records through the supplementary shooting of the rear camera, which is conducive to the efficient operation of the parking lot management system.

[0097] In a fourth aspect, the present invention discloses a storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the above-mentioned method for following a vehicle and taking supplementary photos with a rear-mounted camera.

[0098] Specifically, a computer program is stored in the storage medium, and the program can be run to implement the method of supplementary shooting with a rear camera following a vehicle. When the current vehicle blocks the license plate, the license plate is blocked in the first image captured by the front camera, and the license plate information cannot be normally recognized. The rear camera is automatically switched to adjust the angle of the rear camera, and the second image with the least or no blocking of the license plate is captured. The license plate information corresponding to the vehicle to be detected is obtained from the second image, and the parking lot records the currently obtained license plate information to ensure the integrity and accuracy of the vehicle entry and exit records in the parking lot. Further, when the rear camera needs to be switched, the results of combining the distance between the vehicle to be detected and the front vehicle and whether the first image is blocked can be considered to determine whether the rear camera needs to be started, so as to ensure that the license plate can be correctly and quickly obtained, so that the vehicle can quickly pass through the parking lot. Further, the system can automatically detect the blocking situation of the front vehicle, and intelligently switch the camera for supplementary shooting, reduce the manual intervention of the parking lot management, and improve the integrity of the vehicle entry and exit records through the supplementary shooting of the rear camera, which is conducive to the efficient operation of the parking lot management system.

[0099] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0100] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0101] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0102] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be connected, detachably connected, or integrated; it can be mechanically connected or electrically connected; it can be directly connected or indirectly connected through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0103] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may include that the first and second features are in direct contact, or may include that the first and second features are not in direct contact but are in contact through another feature between them. Moreover, a first feature being "above", "above" and "above" a second feature includes that the first feature is directly above and obliquely above the second feature, or simply indicates that the first feature is higher in level than the second feature. A first feature being "below", "below" and "below" a second feature includes that the first feature is directly below and obliquely below the second feature, or simply indicates that the first feature is lower in level than the second feature.

[0104] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms should not be understood as necessarily referring to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification.

[0105] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

[0106] The above is a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for taking supplementary photos with a rear camera following a vehicle, characterized in that: The following steps are involved: The vehicle to be detected enters the detection area; the detection area is provided with a front camera and a rear camera, and the rear camera is installed on the top or side of the vehicle entrance channel of the detection area; The front camera captures the license plate image of the vehicle to be detected to obtain a first image, and detects the integrity of the license plate of the vehicle to be detected from the first image; When the license plate of the vehicle to be detected is incomplete, the rear camera is started to capture a second image of the license plate of the vehicle to be detected from another angle, and the license plate information is recognized from the second image.

2. The method according to claim 1, characterized in that: The vehicle to be detected enters the detection area, including the following steps: The sensing device is installed near the detection area to detect vehicles in the detection area. The sensing device collects the electrical signal of the front camera corresponding to the sensing device when the vehicle to be detected enters the detection area.

3. The method according to claim 1, characterized in that: After the vehicle to be detected enters the detection area, the following steps are included: collecting the distance between the vehicle to be detected and the vehicle in front, comparing it with the preset distance; when the distance between the vehicle to be detected and the vehicle in front is greater than the preset distance, taking a first image through the front camera, recognizing the license plate information from the first image; when the distance between the vehicle to be detected and the vehicle in front is less than or equal to the preset distance, detecting the integrity of the vehicle through the first image taken by the front camera.

4. The method according to claim 1, characterized in that: The front camera captures the license plate image of the vehicle to be detected to obtain a first image, and detects the integrity of the license plate of the vehicle to be detected from the first image, specifically comprising the following steps: Predetermine the shape of the license plate; The front camera captures the license plate image of the vehicle to be detected to obtain a first image; Performing a license plate region feature extraction process on the first image to obtain a shape feature of the first license plate region, a color of the first license plate, and a text feature in the first license plate region; Comparing the shape feature of the first license plate area with the predetermined license plate shape to determine the integrity of the license plate area; Based on the color of the first license plate, extract the number of characters in the license plate area based on the text features in the first license plate area, compare the number of characters in the traditional license plate rules, and determine the integrity of the characters in the license plate area; Based on the above results, the license plate integrity of the vehicle to be tested is detected.

5. The method according to claim 1, characterized in that: When the vehicle to be detected is close to the vehicle and the license plate of the vehicle to be detected is incomplete, the rear camera is started to shoot the license plate behind the vehicle to be detected and identify the license plate information, which specifically includes the following steps: If the distance between the vehicle to be detected and the vehicle in front is less than the preset distance, and the license plate of the vehicle to be detected is blocked by other vehicles, it is determined that the vehicle license plate cannot be recognized normally, and the rear camera is started to take pictures; The rear camera temporarily captures the license plate image to obtain a temporary image, determines the coordinates of the license plate according to the first image and the temporary image, and adjusts the shooting direction of the rear camera until the license plate image with the least obstruction can be captured to obtain a second image; Perform license plate recognition processing on the second image to obtain a license plate number corresponding to the license plate.

6. The method according to claim 5, characterized in that: The rear camera temporarily captures the license plate image to obtain a temporary image, determines the coordinates of the license plate according to the first image and the temporary image, and adjusts the shooting direction of the rear camera until the license plate image with the least obstruction can be captured to obtain a second image, which specifically includes the following steps: After the rear camera is started, it first takes an image with the license plate to be detected to obtain a temporary image; Get the coordinates and parameters of the front camera and rear camera, and obtain the relative position and direction between the front camera and rear camera through camera calibration. Detecting the position of the license plate in the first image and the temporary image, and obtaining the coordinates of the license plate in the first image and the coordinates of the license plate in the temporary image; Calculate the difference in the license plate position coordinates in the front and rear camera images to get the disparity, perform depth calculation based on the disparity, front camera parameters, and rear camera parameters to get the license plate depth, that is, the distance between the front camera, rear camera and the license plate; Using the coordinates of the license plate in the first image and the temporary image, the parameters of the front camera, the parameters of the rear camera, and the depth of the license plate, the spatial coordinates of the license plate are reversely calculated, thereby determining the position of the license plate; The rear camera is rotated until the license plate image with the least obstruction can be captured to obtain a second image.

7. The method according to claim 1, characterized in that: The following steps are then included: The second image cannot completely obtain the license plate number of the vehicle to be detected, and is marked as an abnormal identification of the vehicle to be detected; The sensor detects that the vehicle has left the detection area and determines that the current vehicle is in an abnormal state; Generate an exception report and notify the parking lot management staff to handle it manually.

8. A rear camera following vehicle supplementary shooting system, characterized in that: The method comprises the steps of the method for taking supplementary photos by following a vehicle with a rear camera as described in any one of claims 1 to 7.

9. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; The processor is used to implement the steps of the method for following a vehicle and taking supplementary photos with a rear camera as described in any one of claims 1 to 7 when executing the program stored in the memory.

10. A 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 for following a vehicle with a rear camera and taking supplementary photos are implemented as described in any one of claims 1 to 7.

Images