Forensic image acquisition method, device, electronic device and storage medium

Abstract

This application relates to a method, apparatus, electronic device, and storage medium for collecting evidence images. The method includes: obtaining the real-time zoom ratio of an image acquisition device; detecting whether a historical evidence image collected at the same zoom ratio exists based on the real-time zoom ratio; if the historical evidence image exists, obtaining the historical PTZ coordinates corresponding to the historical evidence image; and collecting a target evidence image based on the historical PTZ coordinates. This application solves the problem of low reliability of evidence images and achieves the technical effect of ensuring a consistent background of evidence images in the surveillance evidence chain of illegally parked vehicles.

Description

Technical Field

[0001] The present application relates to the field of intelligent transportation, and in particular to a method, device, electronic device and storage medium for collecting evidence images. Background Art

[0002] With the rapid growth of my country's national economy, the number of private cars is increasing day by day. Along with this, a large number of vehicles are illegally parked, resulting in traffic jams, pedestrian crossings being occupied and other problems. To address this problem, spherical cameras have emerged to identify illegally parked vehicles.

[0003] The types of images used for parking violation evidence collection are divided into two categories: original images and composite images. Original images are single-channel video images or partially enlarged images, which are further divided into long-range images, medium-range images, close-up images, and close-up images. Long-range images and medium-range images are video images taken at low and medium magnifications from a spherical camera, which clearly show the target vehicle's license plate, body, and other detailed features, as well as part of the target's surrounding background. Close-up images are images of the target vehicle that have been processed by software and presented at a user-specified ratio. Composite images are images that combine multiple original images into one image in a user-specified style. Evidence collection refers to the process of capturing multiple original images of the illegal target at several time periods as set by the user to form a record of the violation. Generally, close-up images or close-up images are captured at variable magnification based on the target's location output by the target detection module. Due to fluctuations in the detection frame output by the target detection module's algorithm, the surrounding background environment of the target in the same set of evidence chain may vary in the same type of images. Later manual review is required to determine whether the target has moved.

[0004] With regard to the problem of low reliability of forensic images in related technologies, no effective solution has been proposed so far. Summary of the Invention

[0005] In this embodiment, a method, apparatus, electronic device, and storage medium for collecting evidence images are provided to solve the problem of low reliability of evidence images in related technologies.

[0006] Firstly, in this embodiment, a method for collecting forensic images is provided, including: obtaining a real-time zoom ratio of an image acquisition device; detecting whether there is a historical forensic image collected at the same zoom ratio based on the real-time zoom ratio, and if the historical forensic image exists, obtaining the historical pan-tilt coordinates corresponding to the historical forensic image; and collecting the target forensic image based on the historical pan-tilt coordinates.

[0007] In one embodiment, obtaining the real-time zoom ratio of the image acquisition device includes: obtaining a surveillance image of a preset area; determining whether there is an illegally parked target in the preset area based on the surveillance image, and if there is an illegally parked target, recording the illegally parked position of the illegally parked target and adjusting the image acquisition device to a preset zoom ratio, wherein the preset zoom ratio is the zoom ratio of the target evidence collection picture pre-configured by the image acquisition device.

[0008] In one embodiment, the detecting whether there is an illegally parked target in the preset area based on the surveillance image includes: detecting whether there is a target to be detected in the preset area based on the surveillance image; if the target to be detected exists, detecting whether the target to be detected moves within a preset period; if the target to be detected does not move within the preset period, determining the target to be detected as the illegally parked target.

[0009] In one embodiment, after determining whether there is an illegally parked target in the preset area based on the surveillance image, the method further includes: if the illegally parked target exists, obtaining the identity of the illegally parked target; and after obtaining the target evidence picture, associating the identity with the target evidence picture.

[0010] In one embodiment, before obtaining the real-time zoom ratio of the image acquisition device, the method further includes: obtaining the number of historical forensic pictures that have been collected; comparing the number of pictures with a preset number, and if the number of pictures is greater than or equal to the preset number, stopping the collection of the target forensic pictures.

[0011] In one embodiment, after detecting whether there is a historical forensic picture with the same zoom ratio according to the real-time zoom ratio, the method further includes: if the historical forensic picture does not exist, adjusting the illegally parked target to the center position of the surveillance image according to the target detection result of the image acquisition device, and using the current pan-tilt coordinates of the image acquisition device as the preset pan-tilt coordinates; and acquiring the target forensic picture according to the preset pan-tilt coordinates.

[0012] In one embodiment, after collecting the target forensic picture according to the preset gimbal coordinates, the method includes: using the target forensic picture as a historical forensic picture; and generating a forensic record according to the historical forensic picture and the corresponding preset gimbal coordinates.

[0013] Secondly, in this embodiment, a forensic image acquisition device is provided, comprising:

[0014] An acquisition module is used to obtain the real-time zoom ratio of the image acquisition device;

[0015] a processing module, configured to detect, based on the real-time zoom magnification, whether there is a historical forensic picture collected at the same zoom magnification; and if the historical forensic picture exists, obtain the historical PTZ coordinates corresponding to the historical forensic picture;

[0016] The acquisition module is used to acquire target forensic images according to the historical PTZ coordinates.

[0017] In a third aspect, an electronic device is provided in this embodiment, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the forensic image acquisition method described in the first aspect above is implemented.

[0018] In a fourth aspect, a storage medium is provided in this embodiment, on which a computer program is stored. When the program is executed by a processor, the forensic image acquisition method described in the first aspect is implemented.

[0019] Compared with related technologies, the evidence image acquisition method provided in this embodiment obtains the real-time zoom ratio of the image acquisition device; based on the real-time zoom ratio, it detects whether there is a historical evidence image acquired at the same zoom ratio; if the historical evidence image exists, it obtains the historical PTZ coordinates corresponding to the historical evidence image; and acquires the target evidence image based on the historical PTZ coordinates. By obtaining the historical PTZ coordinates, it is ensured that images at the same zoom ratio in the evidence chain are acquired according to the same PTZ coordinates, thereby ensuring that the background of evidence images at the same zoom ratio is consistent, eliminating the need for manual background verification of the image, solving the problem of low reliability of evidence images, and achieving the technical effect of ensuring the consistency of the background of evidence images in the surveillance evidence chain of illegally parked vehicles.

[0020] The details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0022] Figure 1 This is a hardware structure block diagram of the terminal of the forensic image collection method of this embodiment;

[0023] Figure 2 is a flow chart of the forensic image collection method of this embodiment;

[0024] Figure 3 is a flow chart of a method for collecting evidence images according to another embodiment of the present application;

[0025] Figure 4 This is a structural block diagram of the evidence picture acquisition device of this embodiment;

[0026] Figure 5 It is a schematic diagram of a parking violation evidence collection system according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0028] Unless otherwise defined, the technical terms or scientific terms involved in this application should have the general meaning understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "an", "a", "the", "these" and the like in this application do not indicate quantitative restrictions, and they can be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "plurality" involved in this application refers to two or more. "And / or" describes the relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, and B exists alone. Generally, the character " / " indicates that the related objects are in an "or" relationship. The terms "first," "second," "third," etc. used in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0029] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. For example, running on a terminal, Figure 1 This is a hardware block diagram of the terminal of the forensic image acquisition method of this embodiment. Figure 1 As shown, the terminal may include one or more ( Figure 1 Only one is shown) a processor 102 and a memory 104 for storing data, wherein the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. The above terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above terminal. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0030] The memory 104 can be used to store computer programs, such as software programs and modules of application software, such as the computer program corresponding to the forensic image acquisition method in this embodiment. The processor 102 executes the computer program stored in the memory 104 to perform various functional applications and data processing, thereby implementing the above-mentioned method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories may be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0031] The transmission device 106 is used to receive or send data via a network. The network may include a wireless network provided by the terminal's telecommunications provider. In one embodiment, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0032] Evidence collection is the process of capturing multiple original images of illegal targets at user-defined time periods to form a record of the violation. In the field of intelligent transportation, smart cameras can automatically capture traffic violations and collect images to form an evidence chain image of the violation. The evidence chain includes multiple evidence images. In the process of illegal parking evidence collection, there are two situations in which evidence collection is invalid: one is that the license plate in the close-up or close-up image in the composite image is obscured, and the other is that the target in the composite image has moved. Generally, the close-up or close-up image is captured at variable magnification based on the target location output by the target detection module. Due to the fluctuation of the detection frame output by the target detection module's algorithm, the surrounding environment background of the target in the same type of image in the same set of evidence chain may vary, requiring later manual review to determine whether the target has moved. Therefore, in order to facilitate the determination of whether the target in the evidence chain has moved, a method for collecting evidence images is urgently needed to improve the reliability of evidence images.

[0033] In this embodiment, a method for collecting evidence images is provided. Figure 2 This is a flow chart of the evidence picture collection method of this embodiment. Figure 2 As shown, the process includes the following steps:

[0034] Step S201: Acquire the real-time zoom ratio of the image acquisition device.

[0035] Specifically, the image acquisition device in this embodiment refers to a camera device. In the monitoring scenario, a spherical camera is used as the preferred image acquisition device. A spherical camera, also referred to as a spherical camera, generally includes an integrated camera, a spherical pan / tilt head, and a decoder, and has functions such as automatic scanning, automatic operation, focal length control, focus control, and aperture control. Zoom ratio refers to the fact that the imaging of a zoom lens will undergo various changes within each focal range. For example, the wide-angle end can expand the shooting range, and the telephoto end can magnify the subject. Even if the camera does not move its position, the shooting range can be freely changed. When collecting evidence of illegally parked objects, it is generally necessary to collect evidence pictures at different zoom ratios, such as collecting a long-range image in the small-magnification mode of the spherical camera; collecting a medium-range image in the second-smallest-magnification mode of the spherical camera; collecting a close-up image in the large-magnification mode of the spherical camera; and collecting a close-up image by performing local magnification processing through software; that is, the image types of the evidence pictures are divided into long-range images, medium-range images, close-up images, and close-up images. In actual applications, the number of image types can be adjusted as needed, for example, only two types can be set: distant view and close view. Since collecting forensic images of different image types requires changing the zoom ratio of the image acquisition device, it is necessary to obtain the real-time zoom ratio of the image acquisition device.

[0036] Step S202 : detecting whether there is a historical forensic picture collected at the same zoom magnification according to the real-time zoom magnification; if the historical forensic picture exists, obtaining the historical PTZ coordinates corresponding to the historical forensic picture.

[0037] Specifically, before the spherical camera is put into use, the user will pre-configure the image acquisition sequence of the evidence pictures for it. The acquisition is set according to different zoom ratios. For example, the acquisition sequence of the evidence pictures is configured as long shot-medium shot-close shot-medium shot, etc. When the spherical camera detects the presence of illegally parked targets and illegal parking behaviors, it will gradually adjust to the corresponding zoom ratio according to the preset acquisition sequence. At this time, at the zoom ratio, it is detected whether the evidence pictures have been collected at the same zoom ratio. The evidence pictures that have been collected are called historical evidence pictures. This is to detect whether the evidence pictures at the zoom ratio are collected for the first time. If it is not the first time, the historical pan-tilt coordinates PTZ corresponding to the historical evidence pictures at the same zoom ratio are obtained. PTZ is the abbreviation of Pan / Tilt / Zoom in security monitoring applications, which represents the full range (left / right / up / down) movement of the pan-tilt and tilt and the zoom and zoom control of the lens. For example: when the pre-configured order of collecting evidence pictures is long shot-medium shot-close shot-medium shot, the dome camera changes the zoom ratio in this order and collects evidence pictures. When it is detected that the real-time zoom ratio of the current dome camera belongs to the second smallest ratio corresponding to the medium shot, it is detected in the currently collected image data whether the dome camera has collected an evidence image of the same illegally parked target at the second smallest ratio. If so, the gimbal coordinates corresponding to the shooting of the evidence image are obtained, and the gimbal coordinates are the historical gimbal coordinates.

[0038] Step S203: collecting target evidence images according to the historical PTZ coordinates.

[0039] Specifically, the image acquisition device adjusts the pan-tilt according to the historical pan-tilt coordinates, and acquires the target evidence picture at the current zoom ratio. In the related art, the image acquisition at each zoom ratio is shot based on the pan-tilt coordinates calculated by the camera algorithm. Since the zoom ratio of the image acquisition device is constantly changing during the acquisition of the evidence picture of the evidence chain, the pan-tilt coordinates of the image acquisition device are changed, and each change requires re-target recognition. During the recognition process, the position of the illegally parked target will be marked by a detection frame, but it is difficult to ensure that the recognition position of the detection frame is consistent at the same zoom ratio. The evidence picture acquisition method of this embodiment acquires the target evidence picture by acquiring the historical pan-tilt coordinates of the historical evidence pictures at the same zoom ratio, thereby ensuring the consistency of the pan-tilt coordinates when acquiring evidence pictures at the same zoom ratio, thereby achieving the technical effect of keeping the background of the evidence picture the same, and improving the reliability of the evidence picture.

[0040] Through the above steps, the evidence picture acquisition method of the embodiment of the present application can control the gimbal to perform image acquisition according to the same gimbal coordinates when shooting the same type of pictures, thereby ensuring that the picture backgrounds of the same type of evidence pictures are consistent, and then maintaining the stability of the target detection frame, making it easier for the machine to identify whether the target in the evidence picture has moved, reducing the collection of invalid evidence, and improving the reliability of evidence picture acquisition. If the target moves too far and the target disappears in the evidence picture collected according to the same gimbal coordinates, it means that there is no illegal parking at this time, and the camera stops collecting evidence. In addition, compared with manual image background recognition, the evidence picture acquisition method of the embodiment of the present application ensures the consistency of the picture background, and does not require manual secondary recognition of the background, thereby improving the efficiency of image recognition.

[0041] In one embodiment, the real-time zoom ratio of the image acquisition device is obtained before: acquiring a surveillance image of a preset area; determining whether there is an illegally parked target in the preset area based on the surveillance image, recording the illegally parked position of the illegally parked target and adjusting the image acquisition device to a preset zoom ratio, wherein the preset zoom ratio is the zoom ratio of the target evidence picture pre-configured with the image acquisition device.

[0042] Specifically, in existing monitoring scenarios, illegal parking detection is an important monitoring function. Illegally parked vehicles can lead to problems such as traffic jams and occupied crosswalks. Therefore, the evidence picture collection method in this embodiment can be applied to the evidence collection scenario of illegal parking. Illegal parking is referred to as illegal parking. When performing illegal parking detection, the surveillance image within the preset area can be collected by a dome camera. The preset area is the monitoring range of the dome camera, and it can also be the prohibited parking area within the monitoring range of the dome camera. Whether there is an illegal parking problem can be determined by detecting whether there is a vehicle in the preset area; further, the target detection algorithm can be used to process multiple frames of surveillance images to determine whether there is a stationary vehicle in the prohibited parking area within a preset period to determine whether an illegal parking target appears. If an illegal parking target exists, the position of the illegal parking target in the current surveillance image is obtained, and according to the preset evidence collection strategy, the zoom ratio of the camera is adjusted to start evidence collection of the illegal parking target.

[0043] In one embodiment, the detecting whether there is an illegally parked target in the preset area based on the surveillance image includes: detecting whether there is a target to be detected in the preset area based on the surveillance image; if the target to be detected exists, detecting whether the target to be detected moves within a preset period; if the target to be detected does not move within the preset period, determining the target to be detected as the illegally parked target.

[0044] Specifically, when detecting illegally parked objects, a target recognition algorithm can be used to detect the presence of illegally parked objects in a preset area. Such target recognition algorithms include, but are not limited to, depth recognition algorithms and foreground-background separation algorithms. For example, when using a depth recognition algorithm for target recognition, a training set and a validation set can be formed from images containing illegally parked objects. A neural network is trained based on the training and validation sets to generate a target recognition model. This target recognition model is then used to detect the presence of objects within the preset area. The objects can be vehicles, debris, or other items. Preferably, various types of vehicles, such as cars and motorcycles, are used as targets. Because some surveillance areas have parking time restrictions, a preset period is also set to detect whether the object moves within the preset period. If no movement occurs, indicating illegal parking, evidence image collection is initiated. Alternatively, a target tracking algorithm can be used to directly determine whether the object has moved based on the positional changes of the detection frame within multiple frames of surveillance images. Furthermore, if the object moves during evidence image collection, the collection process is interrupted, and the currently collected evidence image is invalidated. The evidence image collection method of the present application provides a technical means for detecting illegally parked objects, achieving accurate detection of illegally parked objects.

[0045] In one embodiment, after determining whether there is an illegally parked target in the preset area based on the surveillance image, the method further includes: if the illegally parked target exists, obtaining the identity of the illegally parked target, and after obtaining the target evidence picture, associating the identity with the target evidence picture.

[0046] Specifically, in the process of collecting evidence of illegal behavior, it is necessary to collect images of illegally parked targets at different zoom factors to form an evidence chain. This evidence chain corresponds to the illegally parked target in the evidence image. Therefore, after detecting the illegally parked target, it is also necessary to determine the identity of the illegally parked target. This identity can be the attribute identifier of the vehicle itself, such as the license plate number; it can also be a unique identifier assigned to it by the system, such as a serial number, etc. By determining this identity, data association of the same target can be achieved. In addition, the image acquisition time of the evidence image, the vehicle signal of the illegally parked target, the vehicle color, etc. can also be recorded and stored together with the evidence image and the pan-tilt coordinates of the evidence image, the corresponding zoom factor, etc. The data association storage of the evidence chain image is realized, which helps to improve the efficiency of data query.

[0047] In one embodiment, before obtaining the real-time zoom ratio of the image acquisition device, the method further includes: obtaining the number of historical forensic pictures that have been collected; comparing the number of pictures with a preset number, and if the number of pictures is greater than or equal to the preset number, stopping the collection of the target forensic pictures.

[0048] Specifically, when collecting evidence of illegal parking, it's often necessary to capture images of the target over a specific timeframe to prove the vehicle was parked for an extended period. Furthermore, to obtain more information about the target, multiple long-range and close-up images of the target are often captured using zoom. Therefore, multiple images of each type are typically collected. Once a preset number of images of all image types have been collected, the capture process stops and the images are synthesized.

[0049] In one embodiment, the related evidence pictures collected for the same detection target within a preset time period are called an evidence chain. The pan / tilt coordinates of the first captured evidence picture in all close-up and close-up pictures of the same evidence chain are marked as A(P n , T n , Z n ), where P is the horizontal coordinate of the gimbal, T is the vertical coordinate of the gimbal, and Z is the gimbal magnification. All subsequent close-up and close-up images in this chain of evidence are taken on gimbal A (P n , T n , Z n ) to capture the scene. The general process is that the camera's evidence chain control device notifies the pan / tilt module to locate A(P n , T n , Z n ) position, and then the evidence chain control device notifies the capture module to capture the picture.

[0050] In one embodiment, the pan / tilt coordinates of the first captured evidence picture in all perspective pictures of the same set of evidence chain are marked as B(P f , T f , Z f ), where P is the horizontal coordinate of the gimbal, T is the vertical coordinate of the gimbal, and Z is the gimbal magnification. All subsequent perspective images in this group are on gimbal B (P f , T f , Z f ) to take snapshots.

[0051] In one embodiment, the pan / tilt coordinates of the first captured evidence picture in all the mid-shot pictures of the same set of evidence chain are marked as C(P m , T m , Z m ), where P is the horizontal coordinate of the gimbal, T is the vertical coordinate of the gimbal, and Z is the gimbal magnification. All subsequent mid-range images in this group are on the gimbal C (P m , T m , Z m ) to take snapshots.

[0052] In one embodiment, after detecting whether there is a historical evidence picture with the same zoom magnification according to the real-time zoom magnification, the method further includes: if the historical evidence picture does not exist, adjusting the illegally parked target to the center of the surveillance image according to the target detection result of the image acquisition device, and using the current pan-tilt coordinates of the image acquisition device as the preset pan-tilt coordinates; and acquiring the target evidence picture according to the preset pan-tilt coordinates. Specifically, if the target evidence picture is the first acquisition of this type of evidence picture, the pan-tilt coordinates of the camera can be adjusted to the factory preset pan-tilt coordinates for shooting according to the target detection strategy preset by the camera. Preferably, the camera adjusts the pan-tilt coordinates according to the target detection result so that the target is in the center of the image for shooting. The evidence picture acquisition method of this embodiment, while ensuring that the camera pan-tilt coordinates are consistent when acquiring evidence pictures at the same zoom magnification, provides a pan-tilt coordinate selection strategy for the first acquisition of evidence pictures at different zoom magnifications. Selecting the pan-tilt coordinates that display the target in the center of the image as the preset target improves the clarity and recognition of the preset target in the image, thereby ensuring the image quality of the evidence picture.

[0053] In one embodiment, after collecting the target evidence picture according to the preset gimbal coordinates, the following steps are included: using the target evidence picture as a historical evidence picture; and generating an evidence record according to the preset gimbal coordinates corresponding to the historical evidence picture. Specifically, after taking the evidence picture, the gimbal coordinates at the time of this shooting are recorded to facilitate the subsequent shooting according to the gimbal coordinates when collecting the same type of evidence pictures. In addition, the target identity information in the evidence picture, the collection time of the evidence picture, and the gimbal coordinates of the evidence picture can be associated and stored together, which can effectively improve the efficiency of data query and provide data support for the big data analysis of illegal parking data, which is beneficial for relevant management personnel to grasp the rules of illegal parking, make targeted improvements, and improve the management capabilities of prohibited parking areas.

[0054] This embodiment also provides a method for collecting evidence images. Figure 3 This is a flow chart of a method for collecting evidence images according to another embodiment of the present application. Figure 3 As shown, the process includes the following steps:

[0055] Obtain surveillance video, process it according to the target tracking algorithm, and obtain target detection results. Specifically, the target detection result information includes whether the target exists. If the target exists, the target identity information, such as the target ID, is recorded.

[0056] Based on the target detection results, check whether the target has moved. If the target has moved, it means that there is no illegal parking, and the evidence collection of the target is abandoned and the collected images are released; if the target has not moved, check whether the collection of evidence images is completed.

[0057] If forensic image collection for the target has been completed, the system will proceed to the Image Merge module to perform OSD overlay processing on the multiple forensic images collected. OSD overlay involves overlaying the image with preset text. If forensic image collection for the target has not been completed, the system will check whether there is a corresponding historical forensic image of the image type currently being collected.

[0058] If a historical forensic image has been captured, the target ID, image type, and corresponding historical PTZ coordinates are searched in the information table. The PTZ capture is controlled based on the historical PTZ coordinates. The record table is a forensic information record table generated after each forensic image is captured. This record table includes the target ID, image type, and PTZ coordinates corresponding to the forensic image. If no historical forensic image has been captured, the PTZ capture is adjusted based on the target detection results and recorded in the information table. This information table includes the target ID, image type, and corresponding PTZ coordinates.

[0059] Through the above steps, the gimbal coordinates of the same type of captured images are memorized, which solves the problem of inconsistent environmental backgrounds of the targets in the same type of captured images in the same evidence chain.

[0060] In one specific embodiment, the camera evidence collection process requires capturing four forensic images. These images are captured in the following order: long-range view - close-up view - long-range view - close-up view. Correspondingly, the camera zoom ratio during target tracking also captures video images in the order of small magnification - large magnification - small magnification - large magnification. The first and second images are captured by the system using pan / tilt control positioning based on target detection results; the third image is captured using the pan / tilt position of the first image; and the fourth image is captured using the pan / tilt position of the second image with a variable magnification.

[0061] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be performed in an order different from that shown here. In this embodiment, a forensic image acquisition device is also provided, which is used to implement the above embodiments and preferred implementation methods, and those that have been described will not be repeated. The terms "module", "unit", "sub-unit" and the like used below can implement a combination of software and / or hardware that implements predetermined functions. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and conceived.

[0062] Figure 4 This is a structural block diagram of the evidence picture acquisition device of this embodiment. Figure 4 As shown, the device includes:

[0063] An acquisition module 10 is used to acquire a real-time zoom ratio of an image acquisition device;

[0064] The processing module 20 is configured to detect whether there is a historical forensic image captured at the same zoom magnification according to the real-time zoom magnification, and if the historical forensic image exists, obtain the historical PTZ coordinates corresponding to the historical forensic image;

[0065] The acquisition module 30 is used to acquire target forensic images according to the historical PTZ coordinates.

[0066] The evidence picture acquisition device also includes an analysis module, which is used to obtain a surveillance image of a preset area; based on the surveillance image, determine whether there is an illegally parked target in the preset area; if the illegally parked target exists, record the illegally parked position of the illegally parked target and adjust the image acquisition device to a preset zoom ratio, which is a zoom ratio of the target evidence picture acquired in advance by the image acquisition device.

[0067] The analysis module is also used to detect whether there is a target to be detected in the preset area based on the monitoring image. If the target to be detected exists, it is detected whether the target to be detected moves within a preset period; if the target to be detected does not move within the preset period, the target to be detected is determined as the illegally parked target.

[0068] The analysis module is further configured to obtain an identity identifier of the illegally parked target if the illegally parked target exists, and associate the identity identifier with the target evidence picture after obtaining the target evidence picture.

[0069] The acquisition module 10 is further configured to acquire the number of the collected historical forensic pictures; compare the number of pictures with a preset number, and stop acquiring the target forensic pictures if the number of pictures is greater than or equal to the preset number.

[0070] The processing module 20 is also used to adjust the illegally parked target to the center position of the monitoring image according to the target detection result of the image acquisition device if the historical evidence picture does not exist, and use the current pan-tilt coordinates of the image acquisition device as the preset pan-tilt coordinates; and collect the target evidence picture according to the preset pan-tilt coordinates.

[0071] The evidence picture acquisition device also includes a storage module, which is used to use the target evidence picture as a historical evidence picture; and generate an evidence record according to the historical evidence picture and the corresponding preset pan-tilt coordinates.

[0072] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0073] In this embodiment, a parking violation evidence collection system is also provided. Figure 5 Schematic diagram of a parking violation evidence collection system according to an embodiment of the present application. Figure 5 As shown, the parking violation evidence collection system includes: a target detection device 51, an evidence chain control device 52, an evidence chain synthesis device 53, a pan / tilt control device 54, and a capture device 55. The evidence chain control device 52 is connected to the target detection device 51, the pan / tilt control device 54, the evidence chain synthesis device 53, and the capture device 55 respectively; the capture device 55 is also connected to the evidence chain synthesis device 53;

[0074] The target detection device 51 is used to detect illegally parked targets in the video image;

[0075] The pan / tilt control device 54 is used to control pan / tilt movement and zoom;

[0076] The image capture device 55 is used to capture the image of the specified frame number and cache it as a forensic image;

[0077] The evidence chain synthesis device 53 is used to synthesize pictures based on the evidence pictures;

[0078] The evidence chain control device 52 is used to execute any of the above-mentioned evidence image collection methods.

[0079] This embodiment further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0080] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0081] Optionally, in this embodiment, the processor may be configured to execute the following steps through a computer program:

[0082] S1, obtain the real-time zoom ratio of the image acquisition device.

[0083] S2: Detecting whether there is a historical evidence picture collected at the same zoom ratio according to the real-time zoom ratio; if the historical evidence picture exists, obtaining historical PTZ coordinates corresponding to the historical evidence picture.

[0084] S3, collecting target evidence images according to the historical PTZ coordinates.

[0085] It should be noted that, for specific examples in this embodiment, reference may be made to the examples described in the above embodiments and optional implementation modes, and will not be repeated in this embodiment.

[0086] In addition, in conjunction with the evidence image acquisition method provided in the above embodiments, a storage medium may also be provided in this embodiment to implement the method. The storage medium stores a computer program; when the computer program is executed by a processor, any of the evidence image acquisition methods in the above embodiments is implemented.

[0087] It should be understood that the specific embodiments described herein are only used to explain this application and are not used to limit it. Based on the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0088] Obviously, the accompanying drawings are merely examples or embodiments of the present application. A person skilled in the art can also apply the present application to other similar situations based on these drawings without inventive effort. Furthermore, it is understandable that, although the work involved in this development process may be complex and lengthy, certain design, manufacturing, or production changes based on the technical content disclosed in this application are merely routine technical means for a person skilled in the art and should not be considered to constitute a deficiency in the disclosure of the present application.

[0089] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0090] The term "embodiment" as used in this application refers to specific features, structures, or characteristics described in conjunction with the embodiment that can be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily mean that the embodiment is the same, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. It is understood, either explicitly or implicitly, by those skilled in the art that the embodiments described in this application can be combined with other embodiments when there is no conflict.

[0091] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of patent protection. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for collecting evidence images, characterized in that: include: Determine whether there is an illegally parked object in a preset area based on the surveillance image, and if so, adjust the image acquisition device to a preset zoom ratio; The preset zoom ratio is a zoom ratio pre-configured by the image acquisition device for acquiring a target forensic picture; Get the real-time zoom ratio of the image acquisition device; Detecting whether there is a historical forensic picture collected at the same zoom magnification according to the real-time zoom magnification, and if the historical forensic picture exists, obtaining the historical PTZ coordinates corresponding to the historical forensic picture; The target forensic images are collected according to the historical PTZ coordinates.

2. The forensic image acquisition method according to claim 1, characterized in that: The method of obtaining the real-time zoom ratio of the image acquisition device includes: Obtain surveillance images of a preset area; Based on the monitoring image, it is determined whether there is an illegally parked object in the preset area. If there is an illegally parked object, the illegally parked position of the illegally parked object is recorded and the image acquisition device is adjusted to a preset zoom ratio.

3. The forensic image acquisition method according to claim 2, characterized in that: The detecting whether there is an illegally parked object in the preset area based on the monitoring image includes: Detecting whether there is a target to be detected in the preset area based on the monitoring image, and if the target to be detected exists, detecting whether the target to be detected moves within a preset period; If the target to be detected does not move within the preset period, the target to be detected is determined as the illegally parked target.

4. The method for collecting evidence images according to claim 2, wherein: After determining whether there is an illegally parked object in the preset area based on the monitoring image, the method further includes: If the illegally parked target exists, the identity of the illegally parked target is obtained, and after obtaining the target evidence picture, the identity is associated with the target evidence picture.

5. The forensic image acquisition method according to claim 1, characterized in that: Before acquiring the real-time zoom ratio of the image acquisition device, the method further includes: Obtaining the number of historical forensic images that have been collected; The number of pictures is compared with a preset number. If the number of pictures is greater than or equal to the preset number, the acquisition of the target forensic pictures is stopped.

6. The forensic image acquisition method according to claim 1, characterized in that: After detecting whether there is a historical evidence collection picture with the same zoom ratio according to the real-time zoom ratio, the method further includes: If the historical evidence image does not exist, the illegally parked object is adjusted to the center of the surveillance image according to the target detection result of the image acquisition device, and the current pan-tilt coordinates of the image acquisition device are used as the preset pan-tilt coordinates; The target evidence picture is collected according to the preset pan-tilt coordinates.

7. The method for collecting evidence images according to claim 6, wherein: After collecting the target evidence picture according to the preset PTZ coordinates, the following steps are included: Using the target forensic image as a historical forensic image; A forensic record is generated based on the historical forensic images and the corresponding preset gimbal coordinates.

8. A forensic image acquisition device, characterized in that: include: An acquisition module is used to determine whether there is an illegally parked object in a preset area based on the monitoring image, and if so, adjust the image acquisition device to a preset zoom factor, and obtain the real-time zoom factor of the image acquisition device; The preset zoom ratio is a zoom ratio pre-configured by the image acquisition device for acquiring a target forensic picture; a processing module, configured to detect, based on the real-time zoom magnification, whether there is a historical forensic picture collected at the same zoom magnification; and if the historical forensic picture exists, obtain the historical PTZ coordinates corresponding to the historical forensic picture; The acquisition module is used to acquire target forensic images according to the historical PTZ coordinates.

9. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to perform the forensic image acquisition method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the forensic image acquisition method according to any one of claims 1 to 7 are implemented.

Images