Vehicle illegal parking evidence collection method, electronic device and computer readable storage medium

Abstract

The present application discloses a method for obtaining evidence of illegal parking of a vehicle, an electronic device, and a computer-readable storage medium, including: detecting a target vehicle, obtaining first detection information and second detection information including the ID information of the target vehicle; matching the ID information with the ID information stored in a database; in response to the absence of the ID information generated based on the target vehicle in the database, saving the first detection information and the second detection information as the initial first detection information and the second initial detection information; capturing the target vehicle based on the first control parameter and / or the second control parameter included in the detection information; in response to the last captured image being a close-up image, comparing the license plate information extracted from the close-up image with the license plate information in the second initial detection information, so as to generate the illegal parking evidence result of the target vehicle based on the comparison result. The present application can solve the problems of low capture rate and low evidence collection rate caused by long-term detection of the same target vehicle.

Description

Technical Field

[0001] The present application relates to the field of traffic monitoring technology, and in particular to a method for collecting evidence of illegal parking of vehicles, an electronic device, and a computer-readable storage medium. Background Art

[0002] With the rapid increase in the number of motor vehicles in cities, there is an imbalance between the rapidly growing parking demand and the supply of parking spaces. At the same time, due to the weak safety awareness of drivers, illegal parking incidents occur frequently, which will cause traffic congestion and traffic control difficulties in cities. Therefore, illegal parking incidents need to be supervised.

[0003] At present, there are two main types of supervision for illegal parking: on-site evidence collection and camera monitoring. On-site evidence collection is heavily dependent on the number of police officers and police force in the traffic department, and limited manpower alone cannot meet the needs of supervision. In the existing technology, spherical cameras are deployed in the urban road traffic network, and intelligent analysis algorithms are built into the spherical cameras to use machine vision instead of artificial vision to collect evidence for illegal parking, thereby saving police force.

[0004] However, the existing time for collecting evidence of illegal parking is generally tens of minutes. In actual scenarios, especially in the long-range state, when the existing intelligent analysis algorithm performs long-term detection on the same target vehicle, due to the small amount of effective information that can be extracted from the long-range image, the algorithm cannot determine whether the multiple images obtained within the evidence collection time are of the same target vehicle. It will be considered that a new target has appeared and the previously obtained data will be discarded. In this way, the camera will continue to capture but will never be able to form a evidence chain diagram, resulting in a low capture rate and a low evidence collection rate when detecting the same target vehicle for a long time. Summary of the invention

[0005] The main technical problem solved by the present application is to provide a method for collecting evidence of illegal parking of vehicles, an electronic device and a computer-readable storage medium, which can solve the problems of low capture rate and low evidence collection rate in the prior art when performing long-term detection on the same target vehicle.

[0006] In order to solve the above technical problems, the first technical solution adopted by the present application is to provide a method for collecting evidence of illegal parking of a vehicle, comprising: detecting a target vehicle to obtain first detection information and second detection information; wherein the first detection information and the second detection information include ID information generated based on the target vehicle; matching the ID information generated based on the target vehicle included in the first detection information and the second detection information with the ID information stored in a database; in response to the absence of the ID information generated based on the target vehicle in the database, saving the first detection information and the second detection information as initial first detection information and second initial detection information; wherein the first initial detection information Including a first control parameter, the second initial detection information includes the license plate information of the target vehicle and the second control parameter; based on the first control parameter and / or the second control parameter, the target vehicle is captured to obtain multiple captured images; wherein, the image captured based on the first control parameter is a distant image including the body information of the target vehicle, and the image captured based on the second control parameter is a close-up image including the license plate information; in response to the last captured image being a close-up image of the target vehicle, the license plate information extracted from the last captured image is compared with the license plate information in the second initial detection information, and based on the first comparison result, a parking violation evidence collection result of the target vehicle is generated.

[0007] In order to solve the above-mentioned technical problems, the second technical solution adopted in the present application is to provide an electronic device, including: a memory, used to store program data, and when the program data is executed, the steps in the vehicle illegal parking evidence collection method as mentioned above are implemented; a processor, used to execute the program data stored in the memory to implement the steps in the vehicle illegal parking evidence collection method as mentioned above.

[0008] In order to solve the above technical problems, the third technical solution adopted in this application is to provide a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by the processor, the steps in the above-mentioned vehicle illegal parking evidence collection method are implemented.

[0009] The beneficial effects of the present application are as follows: Different from the prior art, the present application provides a method for obtaining evidence of illegal parking of a vehicle, an electronic device, and a computer-readable storage medium. By matching the ID information of the target vehicle included in the first detection information and the second detection information obtained by the detection with the ID information stored in the database, and after determining that the first detection information and the second detection information are the information obtained by the first detection, the first detection information and the second detection information are saved as the first initial detection information and the second initial detection information, it is possible to determine whether the current detection of the target vehicle is the first detection, so as to avoid the algorithm determining that a new target has appeared, thereby avoiding the waste of captured images, and then improving the capture efficiency. Furthermore, by extracting the license plate information in the last close-up image and comparing the license plate information with the license plate information extracted from the second initial detection information, more effective information can be obtained for matching, so as to avoid algorithm detection errors, and then the obtained multiple captured images can be used to efficiently generate illegal parking evidence results, thereby improving the efficiency of evidence collection, and then solving the problems of low capture rate and low evidence collection rate caused by long-term detection of the same target vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 It is a flow chart of the first implementation method of the vehicle parking violation evidence collection method of the present application;

[0012] Figure 2 It is a flow chart of the second implementation method of the vehicle parking violation evidence collection method of the present application;

[0013] Figure 3 yes Figure 2 S29 is a flow chart of a specific implementation method;

[0014] Figure 4 This application is based on the image that is not the first image to be captured. Figure 1 Workflow diagram of the application scenario;

[0015] Figure 5 It is a flow chart of the third implementation method of the vehicle parking violation evidence collection method of the present application;

[0016] Figure 6 This is a workflow diagram of the first application scenario of the vehicle parking violation evidence collection method of the present application;

[0017] Figure 7 yes Figure 6Schematic diagram of the specific process of the first detection in China and Africa;

[0018] Figure 8 It is a structural schematic diagram of an implementation method of a vehicle parking violation evidence collection device of the present application;

[0019] Fig. 9 It is a structural schematic diagram of an embodiment of the electronic device of the present application;

[0020] Fig.10 It is a schematic diagram of the structure of an embodiment of a computer-readable storage medium of the present invention. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0022] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. The singular forms of "a", "said", and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms, unless otherwise clearly indicated above, and "multiple" generally includes at least two, but does not exclude the inclusion of at least one.

[0023] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0024] It should be understood that the terms "include", "comprises" or any other variations used herein are intended to cover non-exclusive inclusion, so that a process, method, article or device that includes a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of more restrictions, the elements defined by the sentence "includes..." do not exclude the presence of other identical elements in the process, method, article or device that includes the elements.

[0025] See also Figure 1 , Figure 1 It is a flow chart of the first embodiment of the vehicle parking violation evidence collection method of the present application. In this embodiment, the vehicle parking violation evidence collection method includes:

[0026] S11: Detect the target vehicle and obtain first detection information and second detection information; wherein the first detection information and the second detection information include ID information generated based on the target vehicle.

[0027] In this embodiment, the target vehicle is an illegally parked vehicle.

[0028] Specifically, illegally parked vehicles are vehicles parked in illegal parking detection areas. The illegal parking detection areas are set by users or traffic police. If the parking time in these areas is long, illegal parking evidence will be collected.

[0029] In this embodiment, the first detection information and the second detection information are obtained by a monitoring camera installed on the traffic road network, wherein the monitoring camera can be a spherical camera or other types of cameras, which is not limited in this application.

[0030] Specifically, the first detection information is information obtained based on long-range detection, including ID information generated based on the target vehicle, a detection frame of the target vehicle in the picture, a first control parameter, and a detection time. The second detection information is information obtained based on close-range detection, including ID information generated based on the target vehicle, a detection frame of the target license plate in the picture, a second control parameter, and a detection time.

[0031] Among them, the order of obtaining the first detection information and the second detection information can be set based on user needs. In a specific implementation scenario, the first detection information can be obtained based on long-range detection, and then the second detection information can be obtained based on close-range detection. In another specific implementation scenario, the second detection information can be obtained based on close-range detection, and then the first detection information can be obtained based on long-range detection. This application is not limited to this.

[0032] In this implementation manner, the first detection information and the second detection information are only structured data, not captured images. The camera can subsequently capture images based on the first control parameters and the second control parameters in the structured data.

[0033] Among them, structured data is also called row data, which is data logically expressed and implemented by a two-dimensional table structure. It strictly follows the data format and length specifications and is mainly stored and managed through a relational database.

[0034] It can be understood that this embodiment can enhance the detection stability of the same target vehicle and avoid detection errors caused by only long-range detection by performing long-range detection and close-range detection on the target vehicle and associating the target vehicle with the ID information generated by the two detections.

[0035] S12: Matching the ID information generated based on the target vehicle and included in the first detection information and the second detection information with the ID information stored in the database.

[0036] In this embodiment, the database stores a large number of captured images of illegally parked vehicles and corresponding ID information. By matching the ID information generated based on the target vehicle included in the first detection information and the second detection information with the ID information stored in the database, it can be determined whether this detection of the target vehicle is the first detection.

[0037] S13: In response to the absence of ID information generated based on the target vehicle in the database, the first detection information and the second detection information are saved as initial first detection information and second initial detection information; wherein the first initial detection information includes a first control parameter, and the second initial detection information includes the license plate information of the target vehicle and a second control parameter.

[0038] In this implementation manner, if there is no matching ID information in the database, it indicates that the detection performed on the target vehicle is the first detection.

[0039] It can be understood that the first detection information and the second detection information obtained in the first detection are saved as the initial first detection information and the second initial detection information. When the target vehicle is detected subsequently, it can be known through matching that the detection is not the first detection, so as to avoid the algorithm judging that a new target has appeared, thereby avoiding the waste of captured images and improving the capture efficiency.

[0040] S14: Capture the target vehicle based on the first control parameter and / or the second control parameter to obtain multiple captured images; wherein the image captured based on the first control parameter is a distant image including the body information of the target vehicle, and the image captured based on the second control parameter is a close-up image including the license plate information.

[0041] In this implementation, the first control parameter and the second control parameter are control parameters corresponding to the far view detection preset position and the near view detection preset position respectively. The camera can call the control parameters of the corresponding preset position to capture based on the type of the captured image.

[0042] In this embodiment, whether to call the first control parameter or the second control parameter to capture is determined based on the preset image type set by the user for each captured image, wherein the preset image type includes a distant image, a close-up image, a mid-range image, and a close-up image.

[0043] In a specific implementation scenario, if the user sets the image type of the first captured image to a distant image, then after the detection is completed, the first control parameter is called to capture the image under distant detection to obtain the corresponding captured image, and the capture sequence number is marked as the initial number. In another specific implementation scenario, if the user sets the image type of the first captured image to a close-up image or a close-up image, then after the detection is completed, the second control parameter is called to capture the image under close-up detection to obtain the corresponding captured image, and the capture needs to be marked as the initial number. In yet another specific implementation scenario, if the user sets the image type of the first captured image to a mid-range image, no capture is performed during distant detection or close-up detection.

[0044] In this implementation manner, after the capture of the first image is completed, capture is continued based on a preset time interval and the image type of the next captured image until a plurality of required captured images are acquired.

[0045] S15: In response to the last captured image being a close-up image of the target vehicle, the license plate information extracted from the last captured image is compared with the license plate information in the second initial detection information, and a parking violation evidence collection result of the target vehicle is generated based on the first comparison result.

[0046] In this embodiment, the first comparison result is that the license plate information extracted from the last captured image is the same as the license plate information in the second initial detection information, and the target vehicle did not move during the entire evidence collection time between the first detection and the acquisition of the last captured image.

[0047] It can be understood that by extracting the license plate information in the last close-up image and comparing the license plate information with the license plate information extracted from the second initial detection information, more effective information can be obtained for matching to avoid algorithm detection errors.

[0048] Furthermore, the existing illegal parking evidence collection time is generally tens of minutes. The present embodiment obtains multiple snapshot images within the illegal parking evidence collection time, and generates a first comparison result only when the license plate information extracted from the last snapshot image matches the license plate information in the second initial detection information, and based on the first comparison result, uses the multiple snapshot images obtained to synthesize an illegal parking evidence chain diagram to generate an illegal parking evidence collection result based on the illegal parking evidence chain diagram.

[0049] In other implementations, in response to the last captured image being a distant image or a mid-range image of the target vehicle, it is also necessary to call the second control parameter to detect the license plate of the target vehicle after the capture is completed to obtain third detection information.

[0050] It is understandable that if the last captured image is a distant image or a mid-range image, valid license plate information may not be extracted from the image, and cannot be compared with the license plate information in the second detection information obtained in the first detection. Therefore, it is necessary to call the second control parameter to separately detect the license plate information of the target vehicle. The third detection information obtained in this detection is only saved as structured data instead of taking a photo again.

[0051] Different from the prior art, this embodiment matches the ID information of the target vehicle included in the first detection information and the second detection information obtained by the detection with the ID information stored in the database, and after determining that the first detection information and the second detection information are the information obtained by the first detection, the first detection information and the second detection information are saved as the first initial detection information and the second initial detection information, so as to determine whether the current detection of the target vehicle is the first detection, so as to avoid the algorithm judging that a new target has appeared, thereby avoiding the waste of captured images and improving the capture efficiency. Furthermore, by extracting the license plate information in the last close-up image and comparing the license plate information with the license plate information extracted from the second initial detection information, more effective information can be obtained for matching to avoid algorithm detection errors, and then the multiple captured images obtained can be used to efficiently generate illegal parking evidence results, thereby improving the efficiency of evidence collection, and then solving the problems of low capture rate and low evidence collection rate caused by long-term detection of the same target vehicle.

[0052] See also Figure 2 , Figure 2 It is a flow chart of the second embodiment of the vehicle parking violation evidence collection method of the present application. In this embodiment, the vehicle parking violation evidence collection method includes:

[0053] S21: Obtaining a preset number of images to be captured, a preset image type of each image to be captured, and a preset time interval between two adjacent images to be captured; wherein the preset image types include distant image, near image, mid-range image, and close-up image.

[0054] In this implementation, the preset number of snapshots, the preset image type of each image to be captured, and the preset time interval between two adjacent images to be captured are all set by the user based on needs, and this application does not limit this.

[0055] For example, the preset number of snapshots can be 4, the first image to be captured is a close-up image, the second image to be captured is a distant image, the third image to be captured is a mid-range image, and the fourth image to be captured is a close-up image. The time interval between the first image to be captured and the second image to be captured is 5 minutes, the time interval between the second image to be captured and the third image to be captured is 20 minutes, and the time interval between the third image to be captured and the fourth image to be captured is 35 minutes.

[0056] In this embodiment, the distant image and the mid-range image are video images obtained by the spherical camera at a small magnification and a second small magnification. The distant image and the mid-range image include a vehicle body detection frame. The mid-range image includes a larger vehicle body detection frame than the distant image. The relative position of the target vehicle and the surrounding scenery can be extracted from the distant image and the mid-range image. The close-up image is a video image obtained by the spherical camera at a large magnification. The close-up image includes a license plate detection frame. The license plate information, some detailed features of the vehicle body, and part of the background environment of the target vehicle can be extracted from the close-up image. The close-up image is an image of the close-up image processed by software and presented according to the target vehicle at a user-set ratio.

[0057] S22: Detect the target vehicle and obtain first detection information and second detection information; wherein the first detection information and the second detection information include ID information generated based on the target vehicle.

[0058] For the specific process, please refer to the description in S11 and will not be repeated here.

[0059] S23: Match the ID information generated based on the target vehicle and included in the first detection information and the second detection information with the ID information stored in the database.

[0060] For the specific process, please refer to the description in S12 and will not be repeated here.

[0061] S24: In response to the absence of ID information generated based on the target vehicle in the database, the first detection information and the second detection information are saved as initial first detection information and second initial detection information; wherein the first initial detection information includes first gimbal control parameters, and the second initial detection information includes the license plate information of the target vehicle and second gimbal control parameters.

[0062] In this implementation manner, if there is no matching ID information in the database, it indicates that the detection performed on the target vehicle is the first detection.

[0063] In this embodiment, the first initial detection information also includes a first initial detection frame for marking the target vehicle. The second initial detection information also includes a second initial detection frame for marking the license plate of the target vehicle. The first control parameter is a first gimbal control parameter calibrated by the first initial detection frame, and the second control parameter is a second gimbal control parameter calibrated by the second initial detection frame.

[0064] Specifically, the pan / tilt control parameters include a horizontal parameter, a vertical parameter, and a zoom parameter, wherein the horizontal parameter is the current horizontal tilt angle of the spherical camera, the vertical parameter is the current vertical tilt angle of the spherical camera, and the zoom parameter is the current zoom value of the spherical camera.

[0065] In this embodiment, the first pan / tilt control parameter is a parameter of the spherical camera in the best capture position under long-range detection, and the second pan / tilt control parameter is a parameter of the spherical camera in the best capture position under close-range detection. After the first pan / tilt control parameter and the second pan / tilt control parameter are calibrated, the corresponding pan / tilt control parameter can be directly called based on the preset image type of the image to be captured each time in the subsequent capture, so as to quickly adjust the spherical camera back to the preset position state of the corresponding detection scene, thereby improving the capture efficiency.

[0066] Furthermore, the target vehicle is captured based on the first gimbal control parameter and / or the second gimbal control parameter to obtain a plurality of captured images.

[0067] S25: Obtain the preset image type of the first image to be captured, call the corresponding gimbal control parameters based on the preset image type of the first image to be captured to capture the target vehicle, obtain the first captured image, mark the capture sequence number as the initial number, and record the capture time.

[0068] In a specific implementation scenario, in response to the first image to be captured being a distant image, the first gimbal control parameter is called to capture the target vehicle to obtain the first captured image, and the capture sequence number is marked as the initial number, and the capture time is recorded.

[0069] In another specific implementation scenario, in response to the first image to be captured being a close-up image or a close-up image, the second gimbal control parameter is called to capture the target vehicle to obtain the first captured image, and the capture sequence number is marked as the initial number, and the capture time is recorded.

[0070] When the first captured image is a close-up image, it is necessary to record the license plate information extracted from the close-up image and the second detection frame information, wherein the second detection frame is a detection frame added to the license plate.

[0071] In another specific implementation scenario, in response to the first image to be captured being a mid-ground image, a third gimbal control parameter is obtained based on the first gimbal control parameter and the second gimbal control parameter, the third gimbal parameter is called to capture the target vehicle to obtain the first captured image, and the capture sequence number is marked as the initial number, and the capture time is recorded at the same time.

[0072] Among them, the step of obtaining the third gimbal control parameter based on the first gimbal control parameter and the second gimbal control parameter specifically includes: obtaining the second horizontal parameter and the second vertical parameter corresponding to the second gimbal control parameter as the third horizontal parameter and the third vertical parameter corresponding to the third gimbal control parameter; obtaining the first scaling parameter corresponding to the first gimbal control parameter and the second scaling parameter corresponding to the second gimbal control parameter, and calculating the difference between the second scaling parameter and the first scaling parameter; multiplying the difference by a preset magnification coefficient and adding the difference to the first scaling parameter to obtain the third scaling parameter corresponding to the third gimbal control parameter.

[0073] For example, if the first PTZ control parameter is (P f ,T f ,Z f ), the second PTZ control parameter is (P n ,T n ,Z n ), then the third PTZ control parameter obtained based on the above method is (P n ,T n ,(Z n -Z f )*φ), where P f is the first level parameter, T f is the first vertical parameter, Z f is the first scaling parameter, P n is the second level parameter, T n is the second vertical parameter, Z n is the second scaling parameter, and φ is the magnification factor. The magnification factor can be set by the user or automatically selected by the program.

[0074] In this implementation manner, the initial numbers are all set to 1.

[0075] S26: In response to the difference between the current time and the capture time recorded in the first captured image being equal to or greater than the preset time interval between the first image to be captured and the second image to be captured, a preset image type of the second image to be captured is acquired.

[0076] S27: Based on the preset image type of the second image to be captured, the corresponding PTZ control parameters are called to capture the target vehicle or license plate to obtain the second captured image, the capture sequence number is increased by 1, and the capture time is recorded at the same time.

[0077] In this implementation manner, the specific calling method and capturing method refer to the description in S26 and will not be repeated here.

[0078] S28: Repeat the above steps until a number of captured images consistent with the preset number of captured images are obtained.

[0079] For example, if the preset number of snapshots is 4, then based on the preset number of snapshots of the images to be captured, the preset image type of each image to be captured, and the preset time interval between two adjacent images to be captured, after capturing 4 images, the capture of the target vehicle is stopped.

[0080] S29: In response to the last captured image being a close-up image of the target vehicle, the license plate information extracted from the last captured image is compared with the license plate information in the second initial detection information, and a parking violation evidence collection result of the target vehicle is generated based on the first comparison result.

[0081] Specifically, see Figure 3 , Figure 3 yes Figure 2 In S29, a flowchart of a specific implementation method is shown. In this implementation method, in response to the last captured image being a close-up image of the target vehicle, the license plate information extracted from the last captured image is compared with the license plate information in the second initial detection information, and the steps of generating the illegal parking evidence collection result of the target vehicle based on the first comparison result specifically include:

[0082] S291: In response to the last captured image being a close-up image of the target vehicle, and the license plate information extracted from the close-up image is the same as the license plate information included in the second initial detection information, the center point coordinates of the second final detection frame in the last captured image are obtained.

[0083] It can be understood that the license plate information can be extracted from the last close-up image, indicating that the license plate is not blocked, and the extracted license plate information is the same as the license plate information detected for the first time, indicating that the capture is still of the same target vehicle.

[0084] S292: Calculate based on the center point coordinates of the second final detection frame and the center point coordinates of the second initial detection frame.

[0085] In this implementation manner, it is calculated whether the difference between the coordinates of the center point of the second final detection frame and the coordinates of the center point of the second initial detection frame is less than a preset deviation value.

[0086] In a specific implementation scenario, assuming that the coordinates of the center point of the second initial detection frame are (x F ,y F ), the coordinates of the center point of the second final detection frame are (x L ,yL ), judge (x F ,y F ) and (x L ,y L ) satisfies the following formula:

[0087]

[0088] Among them, x F is the horizontal coordinate of the center point of the second initial detection frame, y F is the ordinate of the center point of the second initial detection frame, x L is the horizontal coordinate of the center point of the second final detection frame, y L is the ordinate of the center point of the second final detection frame, and δ is the pixel deviation value. The pixel deviation value can be set by the user or automatically selected by the program.

[0089] S293: In response to the calculation result being less than or equal to the preset deviation value, generating a first comparison result indicating that the target vehicle has not moved during the capturing process.

[0090] It can be understood that in response to the calculation result being less than or equal to the preset deviation value, it indicates that the detection frame added based on the license plate has not moved, that is, the target vehicle has not moved during the entire capture process.

[0091] S294: Based on the first comparison result, a plurality of captured images are combined to generate a parking violation evidence collection result based on the combined image.

[0092] In this embodiment, after obtaining the first comparison result that determines that the license plate information is consistent and that the vehicle has not moved during the entire evidence collection process, the multiple captured images obtained are combined to generate a parking violation evidence chain diagram, and the parking violation evidence collection results are generated based on the parking violation evidence chain diagram.

[0093] In another embodiment, in response to the last captured image being a close-up image, the license plate information extracted from the last captured image is compared with the license plate information included in the second initial detection information, and multiple captured images are released based on the second comparison result.

[0094] In a specific implementation scenario, in response to the license plate information extracted from the last captured image being different from the license plate information included in the second initial detection information, a second comparison result is generated.

[0095] In another specific scenario, in response to the license plate information extracted from the last captured image being the same as the license plate information included in the second initial detection information, but the calculation result is greater than a preset deviation value, a second comparison result is generated.

[0096] It can be understood that if the license plate information is different, it means that it is not the same target vehicle and the evidence is invalid; if the calculation result is greater than the preset deviation value, it means that the same target vehicle has moved during the evidence collection time and the evidence is still invalid.

[0097] In another embodiment, in response to the last captured image being a distant image or a mid-range image of the target vehicle, the second gimbal control parameter is called to detect the license plate of the target vehicle to obtain third detection information. The third detection information includes license plate information and a second final detection frame. In response to the license plate information included in the third detection information being the same as the license plate information included in the second initial detection information, the center point coordinates of the second final detection frame are obtained. Calculation is performed based on the center point coordinates of the second final detection frame and the center point coordinates of the second initial detection frame. In response to the calculation result being less than or equal to a preset deviation value, a first comparison result is generated that the target vehicle has not moved during the capture process. Based on the first comparison result, a plurality of captured images are combined to generate a parking violation evidence collection result based on the composite image.

[0098] In which, in response to the license plate information included in the third detection information being different from the license plate information included in the second initial detection information, or in response to the license plate information included in the third detection information being the same as the license plate information included in the second initial detection information but the calculation result is greater than a preset deviation value, a second comparison result is generated, and multiple captured images obtained during the evidence collection process are released.

[0099] It is understandable that if the last captured image is a distant image or a mid-range image of the target vehicle, the license plate information cannot be effectively obtained from the last captured image, and thus the license plate of the target vehicle needs to be detected again to improve the detection accuracy.

[0100] See also Figure 4 , Figure 4 This application is based on the image that is not the first image to be captured. Figure 1Workflow diagram of application scenario. In this embodiment, after obtaining the current time, it is determined whether there is a captured image of the target vehicle in the database. If it does not exist, it indicates that no capture has been performed based on the target vehicle, and the target vehicle needs to be detected, and this capture process ends. If it exists, it indicates that a capture has been performed based on the target vehicle before, that is, the relevant preset information (including the preset image type of the next image to be captured and the preset time interval between two adjacent images to be captured) has been obtained, and the capture time of the most recent captured image of the target vehicle with the same ID information in the database is obtained at this time. The difference between the current time and the capture time of the most recent captured image is obtained, and it is determined whether the difference is equal to or greater than the preset time interval. If the difference is less than the preset time interval, it indicates that the current time has not reached the capture time, and this capture process ends. If the difference is equal to or greater than the preset time interval, it indicates that the current time has reached the capture time, then the corresponding pan-tilt control parameter is called based on the preset image type of the next image to be captured, and the body or license plate of the target vehicle is captured, the capture sequence number is increased by 1, and the capture time is recorded at the same time, and this capture process ends.

[0101] See also Figure 5 , Figure 5 1 is a flow chart of the third embodiment of the vehicle parking violation evidence collection method of the present application. In this embodiment, the vehicle parking violation evidence collection method includes:

[0102] S51: Detect the target vehicle and obtain first detection information and second detection information; wherein the first detection information and the second detection information include ID information generated based on the target vehicle.

[0103] For the specific process, please refer to the description in S11 and will not be repeated here.

[0104] S52: Match the ID information generated based on the target vehicle and included in the first detection information and the second detection information with the ID information stored in the database.

[0105] For the specific process, please refer to the description in S12 and will not be repeated here.

[0106] S53: In response to the existence of ID information generated based on the target vehicle in the database, a preset image type of the next image to be captured is obtained.

[0107] In this embodiment, the database contains ID information generated based on the target vehicle, indicating that this detection is not the first detection, and the preset number of images to be captured, the preset image type of each image to be captured, and the preset time interval between two adjacent images to be captured have been obtained before.

[0108] S54: In response to the preset image type of the next image to be captured being a close-up image or a close-up image, and the capture number of the next image to be captured being equal to the preset capture number, the second gimbal control parameter is called to capture the target vehicle to obtain the last captured image, and the capture number is increased by 1.

[0109] In this embodiment, the capture sequence number of the next image to be captured is equal to the preset capture number, indicating that this capture is the last capture, and multiple captured images have been obtained before. For the specific capture process, please refer to the description in S25 to S27, which will not be repeated here.

[0110] In other embodiments, in response to the preset image type of the next image to be captured being a distant image or a mid-view image, and the capture sequence number of the next image to be captured being equal to the preset capture number, the first pan-tilt control parameter is called to capture the target vehicle to obtain the last captured image, and the capture sequence number is increased by 1. After the last image is captured, the second pan-tilt control parameter is called to detect the target vehicle to obtain third detection information. The third detection information includes the license plate information and the second final detection frame.

[0111] S55: In response to the last captured image being a close-up image of the target vehicle, the license plate information extracted from the last captured image is compared with the license plate information in the second initial detection information, and a parking violation evidence collection result of the target vehicle is generated based on the first comparison result.

[0112] For the specific process, please refer to the description in S29 and S291 to S294, which will not be repeated here.

[0113] See also Figure 6 , Figure 6 This is a workflow diagram of the first application scenario of the vehicle parking violation evidence collection method. Figure 7 yes Figure 6Specific flow diagram of the first detection in China and Africa. In this embodiment, the target vehicle is detected, the first detection information and the second detection information are obtained, and the ID information generated based on the target vehicle included in the first detection information and the second detection information is matched with the ID information stored in the database. In response to the absence of the ID information generated based on the target vehicle in the database, the first detection information is saved as the initial first detection information. It is determined whether the preset image type of the first image to be captured is a distant image. In response to the first image to be captured being a distant image, the first control parameter is called to capture the target vehicle, the first captured image is obtained, and the capture sequence number is marked as the initial number, and the capture time is recorded. In response to the first image to be captured being a close-up image or a close-up image, the second detection information is saved as the initial second detection information, and it is determined whether the preset image type of the first image to be captured is a close-up image. In response to the first image to be captured being a close-up image or a close-up image, the second control parameter is called to capture the target vehicle, the first captured image is obtained, and the capture sequence number is marked as the initial number, and the capture time is recorded.

[0114] In which, in response to the existence of ID information generated based on the target vehicle in the database, non-first detection is entered. It is determined whether the preset image type of the image to be captured this time is a close-up image or a close-up image. In response to the preset image type of the image to be captured this time being a close-up image or a close-up image, the captured image is obtained this time, and the license plate information and the second detection frame information in the captured image are extracted. It is determined whether the capture sequence number of the captured image this time is equal to the preset capture number. In response to the capture sequence number of the captured image this time not being equal to the preset capture number, the non-first detection process ends this time. In response to the capture sequence number of the captured image this time being equal to the preset capture number, the license plate information and the second detection frame information extracted from the captured image this time are compared with the license plate information and the second initial detection frame information extracted from the second initial detection information, and it is determined whether a first comparison result is generated. In response to the failure to generate the first comparison result, the cached multiple captured images are released, and the non-first detection process ends this time. In response to the generation of the first comparison result, the multiple captured images obtained are used to synthesize the illegal parking evidence chain diagram, and the non-first detection process ends this time.

[0115] Among them, in response to the preset image type of the image to be captured this time being not being a close-up image or a close-up image, the captured image is acquired this time, and it is determined whether the capture sequence number of the captured image this time is equal to the preset capture number. In response to the capture sequence number of the captured image this time being not being equal to the preset capture number, this non-first detection process ends. In response to the capture sequence number of the captured image this time being equal to the preset capture number, the second gimbal control parameter is called to detect the target vehicle, and the third detection information is obtained, so as to compare the license plate information extracted from the third detection information and the second detection frame information with the license plate information extracted from the second initial detection information and the second initial detection frame information, and determine whether the first comparison result is generated. In response to the first comparison result not being generated, the cached multiple captured images are released, and this non-first detection process ends. In response to the generation of the first comparison result, the multiple captured images obtained are used to synthesize the illegal parking evidence chain diagram, and this non-first detection process ends.

[0116] Correspondingly, the present application provides a vehicle illegal parking evidence collection device.

[0117] See also Figure 8 , Figure 8 This is a schematic diagram of the structure of an embodiment of the vehicle parking violation evidence collection device of the present application. Figure 8 As shown, the vehicle illegal parking evidence collection device 80 includes a detection module 81, a matching module 82, a storage module 83, a capture module 84, and a generation module 85.

[0118] The detection module 81 is used to detect the target vehicle and obtain first detection information and second detection information; wherein the first detection information and the second detection information include ID information generated based on the target vehicle.

[0119] The matching module 82 is used to match the ID information generated based on the target vehicle included in the first detection information and the second detection information with the ID information stored in the database.

[0120] The saving module 83 is used to save the first detection information and the second detection information as the initial first detection information and the second initial detection information in response to the absence of ID information generated based on the target vehicle in the database; wherein the first initial detection information includes the first control parameter, and the second initial detection information includes the license plate information of the target vehicle and the second control parameter.

[0121] The capture module 84 is used to capture the target vehicle based on the first control parameter and / or the second control parameter to obtain multiple captured images; wherein the image captured based on the second control parameter is a close-up image including the license plate information.

[0122] The generation module 85 is used to compare the license plate information extracted from the last captured image with the license plate information in the second initial detection information in response to the last captured image being a close-up image of the target vehicle, and generate a parking violation evidence collection result of the target vehicle based on the first comparison result.

[0123] For the specific process, please refer to the relevant text descriptions in S11 to S15, S21 to S29, S291 to S294 and S51 to S55, which will not be repeated here.

[0124] Different from the prior art, this embodiment matches the ID information of the target vehicle included in the first detection information and the second detection information obtained by the detection with the ID information stored in the database through the matching module 82, and after determining that the first detection information and the second detection information are the information obtained by the first detection, the first detection information and the second detection information are saved as the first initial detection information and the second initial detection information through the saving module 83, so as to determine whether the detection of the target vehicle is the first detection, so as to avoid the algorithm judging that a new target has appeared, thereby avoiding the waste of the captured image, and then improving the capture efficiency. Further, the capture module 84 is used to capture, and the generation module 85 is used to extract the license plate information in the last close-up image, and the license plate information is compared with the license plate information extracted from the second initial detection information, so as to obtain more effective information for matching, so as to avoid algorithm detection errors, and then the multiple captured images obtained can be used to efficiently generate the illegal parking evidence collection results, thereby improving the evidence collection efficiency, and then solving the problems of low capture rate and low evidence collection rate caused by long-term detection of the same target vehicle.

[0125] Correspondingly, the present application provides an electronic device.

[0126] See also Fig. 9 , Fig. 9 Schematic diagram of the structure of an electronic device of the present application. Fig. 9 As shown, the electronic device 90 includes a memory 91 and a processor 92 .

[0127] In this embodiment, the memory 91 is used to store program data, and when the program data is executed, the steps in the vehicle illegal parking evidence collection method as described above are implemented; the processor 92 is used to execute the program instructions stored in the memory 91 to implement the steps in the vehicle illegal parking evidence collection method as described above.

[0128] Specifically, the processor 92 is used to control itself and the memory 91 to implement the steps in the vehicle parking violation evidence collection method as described above. The processor 92 can also be called a CPU (Central Processing Unit). The processor 92 may be an integrated circuit chip with signal processing capabilities. The processor 92 can also be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field-programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. In addition, the processor 92 can be implemented by multiple integrated circuit chips.

[0129] Different from the prior art, the present embodiment matches the ID information of the target vehicle included in the first detection information and the second detection information obtained by the detection with the ID information stored in the database through the processor 92, and after determining that the first detection information and the second detection information are the information obtained by the first detection, the first detection information and the second detection information are saved as the first initial detection information and the second initial detection information, which can determine whether the detection of the target vehicle is the first detection, so as to avoid the algorithm judging that a new target has appeared, thereby avoiding the waste of captured images, and then improving the capture efficiency. Furthermore, by extracting the license plate information in the last close-up image and comparing the license plate information with the license plate information extracted from the second initial detection information, more effective information can be obtained for matching, so as to avoid algorithm detection errors, and then the obtained multiple captured images can be used to efficiently generate illegal parking evidence results, thereby improving the efficiency of evidence collection, and then solving the problems of low capture rate and low evidence collection rate caused by long-term detection of the same target vehicle.

[0130] Correspondingly, the present application provides a computer-readable storage medium.

[0131] See also Fig.10 , Fig.10 It is a schematic diagram of the structure of an embodiment of a computer-readable storage medium of the present invention.

[0132] The computer-readable storage medium 100 includes a computer program 1001 stored on the computer-readable storage medium 100. When the computer program 1001 is executed by the processor, the steps in the vehicle parking violation evidence collection method described above are implemented. Specifically, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium 100. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a computer-readable storage medium 100, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (processor) to perform all or part of the steps of each embodiment of the present application. The aforementioned computer-readable storage medium 100 includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0133] In the several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device implementation described above is only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0134] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0135] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0136] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of each implementation method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.

[0137] The above description is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

[0138] If the technical solution of this application involves personal information, the product using the technical solution of this application has clearly informed the personal information processing rules and obtained the individual's voluntary consent before processing the personal information. If the technical solution of this application involves sensitive personal information, the product using the technical solution of this application has obtained the individual's separate consent before processing the sensitive personal information, and at the same time meets the "explicit consent" requirement. For example, on personal information collection devices such as cameras, clear and prominent signs are set to inform that the personal information collection scope has been entered and personal information will be collected. If the individual voluntarily enters the collection scope, it is deemed that he or she agrees to the collection of his or her personal information; or on the device that processes personal information, the personal information processing rules are notified by obvious signs / information, and the individual's authorization is obtained through pop-up information or by asking the individual to upload his or her personal information; among them, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the type of personal information processed.

Claims

1. A method for collecting evidence of illegal parking of a vehicle, characterized in that: include Detecting a target vehicle to obtain first detection information and second detection information; wherein the first detection information and the second detection information include ID information generated based on the target vehicle; matching the ID information generated based on the target vehicle and included in the first detection information and the second detection information with the ID information stored in a database; In response to the ID information generated based on the target vehicle not existing in the database, the first detection information and the second detection information are saved as first initial detection information and second initial detection information; wherein the first initial detection information includes a first control parameter, and the second initial detection information includes the license plate information of the target vehicle and a second control parameter; The target vehicle is captured based on the first control parameter and / or the second control parameter to obtain a plurality of captured images; wherein the image captured based on the first control parameter is a distant image including the body information of the target vehicle, and the image captured based on the second control parameter is a close-up image including the license plate information; In response to the last captured image being a close-up image of the target vehicle, the license plate information extracted from the last captured image is compared with the license plate information in the second initial detection information, and a parking violation evidence collection result of the target vehicle is generated based on the first comparison result.

2. The vehicle parking violation evidence collection method according to claim 1, characterized in that: The first initial detection information further includes a first initial detection frame for marking the target vehicle; the second initial detection information further includes a second initial detection frame for marking the license plate of the target vehicle; the first control parameter is a first pan / tilt control parameter calibrated by the first initial detection frame, and the second control parameter is a second pan / tilt control parameter calibrated by the second initial detection frame; The step of capturing the target vehicle based on the first control parameter and / or the second control parameter to obtain a plurality of captured images includes: The target vehicle is captured based on the first pan-tilt control parameter and / or the second pan-tilt control parameter to obtain a plurality of captured images.

3. The vehicle parking violation evidence collection method according to claim 2, characterized in that: Before the step of detecting the target vehicle and obtaining the first detection information and the second detection information, the method includes: Obtaining a preset number of images to be captured, a preset image type of each image to be captured, and a preset time interval between two adjacent images to be captured; wherein the preset image types include a distant image, a close-up image, a mid-range image, and a close-up image; The step of capturing the target vehicle based on the first pan / tilt control parameter and / or the second pan / tilt control parameter to obtain a plurality of captured images includes: Obtaining a preset image type of the first image to be captured, calling corresponding PTZ control parameters based on the preset image type of the first image to be captured to capture the target vehicle, obtaining the first captured image, marking the captured image sequence number as an initial number, and recording the capture time; In response to the difference between the current time and the capture time recorded in the first captured image being equal to or greater than a preset time interval between the first image to be captured and the second image to be captured, acquiring a preset image type of the second image to be captured; Based on the preset image type of the second image to be captured, the corresponding PTZ control parameter is called to capture the target vehicle or the license plate to obtain a second captured image, the capture sequence number is increased by 1, and the capture time is recorded; Repeat the above steps until a number of captured images consistent with the preset number of captured images are obtained.

4. The vehicle parking violation evidence collection method according to claim 3 is characterized in that: The step of acquiring a preset image type of the first image to be captured, calling a corresponding pan / tilt control parameter based on the preset image type of the first image to be captured to capture the target vehicle, obtaining the first captured image, marking the captured image sequence number as an initial number, and recording the capture time includes: In response to the first image to be captured being the distant view image, calling the first PTZ control parameter to capture the target vehicle to obtain the first captured image, marking the captured image sequence number as the initial number, and recording the capture time; In response to the first image to be captured being the close-up image or the close-up image, calling the second pan / tilt control parameter to capture the target vehicle to obtain the first captured image, marking the captured image sequence number as the initial number, and recording the capturing time; In response to the first image to be captured being the mid-ground image, a third gimbal control parameter is obtained based on the first gimbal control parameter and the second gimbal control parameter, the third gimbal parameter is called to capture the target vehicle to obtain the first captured image, and the capture sequence number is marked as the initial number, and the capture time is recorded at the same time.

5. The vehicle parking violation evidence collection method according to claim 4 is characterized in that: The PTZ control parameters include horizontal parameters, vertical parameters and zoom parameters; The step of acquiring the third gimbal control parameter based on the first gimbal control parameter and the second gimbal control parameter comprises: Acquire a second horizontal parameter and a second vertical parameter corresponding to the second gimbal control parameter as a third horizontal parameter and a third vertical parameter corresponding to the third gimbal control parameter; Acquire a first scaling parameter corresponding to the first gimbal control parameter and a second scaling parameter corresponding to the second gimbal control parameter, and calculate a difference between the second scaling parameter and the first scaling parameter; The difference is multiplied by a preset magnification coefficient and then added to the first scaling parameter to obtain a third scaling parameter corresponding to the third gimbal control parameter.

6. The vehicle parking violation evidence collection method according to claim 4 is characterized in that: In response to the last captured image being a close-up image of the target vehicle, the step of comparing the license plate information extracted from the last captured image with the license plate information in the second initial detection information, and generating a parking violation evidence collection result of the target vehicle based on the first comparison result includes: In response to the last captured image being the close-up image of the target vehicle, and the license plate information extracted from the close-up image is the same as the license plate information included in the second initial detection information, obtaining the coordinates of the center point of the second final detection frame in the last captured image; Calculating based on the coordinates of the center point of the second final detection frame and the coordinates of the center point of the second initial detection frame; In response to the calculation result being less than or equal to the preset deviation value, generating the first comparison result indicating that the target vehicle has not moved during the capturing process; Based on the first comparison result, a combination operation is performed on the plurality of captured images to generate the illegal parking evidence collection result based on the composite image.

7. The vehicle parking violation evidence collection method according to claim 6, characterized in that: After the step of capturing the target vehicle based on the first control parameter and / or the second control parameter to obtain a plurality of captured images, the method further includes: In response to the last captured image being the distant image or the mid-range image of the target vehicle, calling the second pan / tilt control parameter to detect the license plate of the target vehicle to obtain third detection information; wherein the third detection information includes the license plate information and the second final detection frame; In response to the license plate information included in the third detection information being the same as the license plate information included in the second initial detection information, acquiring the coordinates of the center point of the second final detection frame; Calculating based on the coordinates of the center point of the second final detection frame and the coordinates of the center point of the second initial detection frame; In response to the calculation result being less than or equal to the preset deviation value, generating the first comparison result indicating that the target vehicle has not moved during the capturing process; The combining operation is performed on the plurality of captured images based on the first comparison result, so as to generate the parking violation evidence collection result based on the combined image.

8. The vehicle parking violation evidence collection method according to claim 6, characterized in that: After the step of capturing the target vehicle based on the first control parameter and / or the second control parameter to obtain a plurality of captured images, the method further includes: In response to the last captured image being the close-up image, the license plate information extracted from the last captured image is compared with the license plate information included in the second initial detection information, and multiple captured images are released based on the second comparison result; wherein the second comparison result is that the license plate information extracted from the last captured image is different from the license plate information included in the second initial detection information, or, the license plate information extracted from the last captured image is the same as the license plate information included in the second initial detection information but the calculation result is greater than the preset deviation value.

9. The vehicle parking violation evidence collection method according to claim 3, characterized in that: After the step of matching the ID information generated based on the target vehicle and included in the first detection information and the second detection information with the ID information stored in the database, the method further comprises: In response to the ID information generated based on the target vehicle existing in the database, obtaining a preset image type of the next image to be captured; In response to the preset image type of the next image to be captured being the close-up image or the close-up image, and the capture number of the next image to be captured is equal to the preset capture number, the second gimbal control parameter is called to capture the target vehicle to obtain the last captured image, and the capture number is increased by 1.

10. An electronic device, characterized in that: include: A memory for storing program data, wherein the program data, when executed, implements the steps of the vehicle parking violation evidence collection method according to any one of claims 1 to 9; A processor is used to execute the program data stored in the memory to implement the steps in the vehicle parking violation evidence collection method as described in any one of claims 1 to 9.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the vehicle parking violation evidence collection method as described in any one of claims 1 to 9 are implemented.

Images