Geographic information system (GIS)-based metropolitan area safety video monitoring method and system

Abstract

The embodiment of the invention provides a GIS (Geographic Information System)-based metropolitan area safety video monitoring method and system. The method is applied to the technical field of image processing and comprises the following steps: acquiring a video picture of a coverage area in real time through a camera; performing real-time analysis on the video picture by using a target detection algorithm, and identifying a target in the video picture; converting the position of the target in the video picture into an actual geographic coordinate based on coordinate system conversion; continuously tracking the target in different camera coverage areas through the geographic coordinates; based on perspective transformation, converting the video image into an aerial view angle, and splicing aerial views to form a panoramic view; and visualizing the geographic coordinates of the target in the aerial view. In this way, the efficiency and accuracy of the city monitoring system can be improved, and therefore the requirement for city safety monitoring can be better met.

Description

Technical Field

[0001] The present disclosure relates to the field of image processing technology, and in particular to a metropolitan area security video monitoring method and system based on GIS. Background Art

[0002] In modern urban security management, video surveillance systems play a vital role. With the acceleration of urbanization, the demand for surveillance in urban areas is increasing. Traditional single surveillance systems have gradually shown shortcomings such as low efficiency, many blind spots, and heavy burden of manual analysis due to limited monitoring range and low data processing. Therefore, through the linkage and collaborative work of multiple cameras, security prevention and emergency response capabilities can be improved. Summary of the invention

[0003] The present invention provides a method and system for urban security video monitoring based on GIS, which solves the technical problems of limited monitoring range, low data processing and difficulty in achieving accurate positioning and continuous tracking of targets.

[0004] According to a first aspect of the present disclosure, a GIS-based metropolitan area security video monitoring method is provided. The method comprises:

[0005] Obtain video images of the coverage area in real time through the camera;

[0006] Analyzing the video in real time using a target detection algorithm to identify targets in the video;

[0007] Based on the coordinate system conversion, the position of the target in the video screen is converted into actual geographic coordinates;

[0008] Continuously tracking the target in different camera coverage areas by using the geographic coordinates;

[0009] Based on perspective transformation, the video screen is converted into a bird's-eye view, and the bird's-eye view is spliced ​​to form a panoramic view;

[0010] The geographic coordinates of the target in the panoramic view are visualized.

[0011] According to the above aspects and any possible implementation, an implementation is further provided, wherein the target detection algorithm is YOLOv5, including:

[0012] Read the video images captured from the camera frame by frame;

[0013] Input each frame of the read image into the trained YOLOv5 network model in turn;

[0014] The YOLOv5 network model captures the target in the current frame image, frames the target area, and obtains the target type, outline, and calibration coordinates.

[0015] According to the above aspects and any possible implementation, an implementation is further provided, wherein the conversion of the position of the target in the video screen into actual geographic coordinates based on the coordinate system conversion includes:

[0016] The camera calibration method is used to obtain the intrinsic and extrinsic parameters of the camera. According to its parameters, a perspective projection model is constructed to convert the position of the target in the video screen into actual geographic coordinates.

[0017] According to the above aspects and any possible implementation manner, an implementation manner is further provided, wherein the continuously tracking the target in different camera coverage areas by using the geographic coordinates includes:

[0018] The geographic coordinates of the target are updated in real time and the geographic coordinate information is shared with other related cameras, and the target is tracked by DeepSORT to obtain the trajectory of the target under the camera, wherein the tracking of the target by DeepSORT includes:

[0019] By putting the first few frames of the target's video into the Kalman filter for learning, the position of the target in the next frame is predicted, and the observed coordinates and the predicted coordinates are matched through the Hungarian algorithm. If the two are consistent, they are matched. If not, the parameters of the target are adjusted or the Kalman filter system continues to match.

[0020] According to the above aspects and any possible implementation manner, an implementation manner is further provided, wherein converting the video picture into a bird's-eye view based on perspective transformation includes:

[0021] The homography matrix H is calculated according to the video image, and the homography matrix H is used to complete the bird's-eye view conversion.

[0022] According to the above aspects and any possible implementation manner, an implementation manner is further provided, wherein the method for stitching bird's-eye views to form a panoramic view includes:

[0023] The transformed bird's-eye view images from multiple cameras are stitched together using an image stitching algorithm to generate a panoramic bird's-eye view.

[0024] According to the above aspects and any possible implementation manner, an implementation manner is further provided, wherein the method further includes:

[0025] The geographic coordinates of the target are mapped to the corresponding position in the 3D model, and 3D rendering is used to realize the dynamic display of the target in the 3D model.

[0026] According to a second aspect of the present disclosure, a metropolitan area security video monitoring system based on GIS is provided. The system comprises:

[0027] An acquisition module is used to acquire video images of the coverage area in real time through a camera;

[0028] An analysis module, used to analyze the video image in real time using a target detection algorithm to identify the target in the video image;

[0029] A conversion module, used for converting the position of the target in the video screen into actual geographic coordinates based on coordinate system conversion;

[0030] A tracking module, used to continuously track the target in different camera coverage areas through the geographic coordinates;

[0031] A splicing module, used for converting the video images into a bird's-eye view based on perspective transformation, and splicing the bird's-eye view to form a panoramic view;

[0032] The display module is used to visualize the geographic coordinates of the target in the panoramic view.

[0033] According to a third aspect of the present disclosure, an electronic device is provided, which includes a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the program, the method described above is implemented.

[0034] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the method according to the first aspect and / or the second aspect of the present disclosure is implemented.

[0035] In the present disclosure, GIS-based metropolitan security video surveillance combines video linkage monitoring, perspective projection transformation, target detection and tracking algorithms, and uses the spatial coordinate information provided by GIS to achieve detection and continuous tracking of targets within the camera coverage area, realize multi-camera linkage and dynamic three-dimensional display, and provide real-time, continuous and accurate monitoring effects.

[0036] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, among which:

[0038] Figure 1 A schematic diagram showing an exemplary operating environment in which embodiments of the present disclosure can be implemented;

[0039] Figure 2 A flowchart of a GIS-based metropolitan area security video monitoring method according to an embodiment of the present disclosure is shown;

[0040] Figure 3 A block diagram of a metropolitan area security video monitoring device based on GIS according to an embodiment of the present disclosure is shown;

[0041] Figure 4 A block diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0043] In addition, the term "and / or" in this article is only a description of the association relationship between the 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.

[0044] The present invention realizes multi-camera linkage monitoring within a metropolitan area, converts the target position in the video screen into the actual geographic coordinates through coordinate system conversion, ensures the continuous tracking of the target, and provides an intuitive display of the bird's-eye view through perspective transformation and stitching technology, realizes target monitoring in a wide area, improves the coverage capability and reliability of the system, and enhances the coherence of the monitoring system.

[0045] In conjunction with the accompanying drawings, a GIS-based metropolitan area security video monitoring method and system provided by the embodiment of the present disclosure will be described in detail through specific embodiments.

[0046] Figure 1 A schematic diagram of an exemplary operating environment in which embodiments of the present disclosure can be implemented is shown, Figure 1As shown, the operating environment 100 may include multiple cameras and a central processing unit. The cameras transmit video data to the central processing unit via a network or a local connection, and the central processing unit completes subsequent processing of the video data.

[0047] The camera should have a wide-angle lens to cover the area to the maximum extent and reduce blind spots. In addition, the camera should have a resolution of at least 1080p to ensure that the captured image is clear enough.

[0048] The central processing unit may be a server or a cloud computing platform, which is not limited here.

[0049] As an example, the camera starts to collect video data. In order to reduce bandwidth consumption, the video data is transmitted using H.264 or H.265 compression encoding. The central processing unit receives the compressed and encoded video data, parses the read data, extracts various parameters used in the encoding process, and restores it to the original video image data through decoding based on the parsed parameters, so that it can be directly processed by subsequent operation processes. In this process, the central processing unit may send control signals to the camera as needed to adjust the camera's parameters or operating mode.

[0050] A GIS-based metropolitan area security video monitoring method provided by an embodiment of the present disclosure will be described in detail below, wherein the execution subject may be a central processing unit.

[0051] Figure 2 A flowchart of a GIS-based metropolitan area security video monitoring method according to an embodiment of the present disclosure is shown, as shown in FIG. Figure 2 As shown, a GIS-based metropolitan area security video monitoring method may include the following steps:

[0052] S210, obtaining video images of the coverage area in real time through the camera.

[0053] Exemplarily, multiple high-definition cameras are installed in the monitoring area, each camera covers a different field of view, and the camera captures the video images in its coverage area in real time and transmits the video data to the central processing unit through the network or local connection.

[0054] S220, using a target detection algorithm to analyze the video image in real time to identify the target in the video image.

[0055] In some embodiments, the decoded original video image data is read frame by frame to be detected, and each frame of the read image is sequentially input into the pre-trained YOLOv5 network model.

[0056] The ImageNet dataset is used to train the YOLOv5 network model to frame the target in the image. The bounding box contains the location information of the target and the confidence score related to each category. At the same time, the upper left corner coordinates, height, width and category of the target box are extracted. The location information includes the upper left corner x, y coordinate values ​​and width and height.

[0057] In some embodiments, the YOLOv5 network model captures the target of the current frame image, frames the target area, and obtains the target type and calibration coordinates.

[0058] Exemplarily, the current frame image is first input into a convolutional neural network for feature extraction, each cell generates multiple bounding boxes based on the prediction results, and redundant bounding boxes are eliminated through non-maximum suppression (NMS); then, the input current frame image is divided into a fixed-size grid, each cell is responsible for predicting a set of bounding boxes and the confidence of the corresponding category, each bounding box contains the location information of the object and the confidence score associated with each category, and the Softmax function is used to calculate the probability that each bounding box belongs to a different category. The category prediction of each bounding box is calculated by the degree of overlap between the bounding box and the target instance and the category confidence score; finally, the detected target bounding box position, category and corresponding confidence score are output.

[0059] S230: Based on the coordinate system conversion, the position of the target in the video image is converted into actual geographic coordinates.

[0060] In some embodiments, a camera calibration method is used to obtain the intrinsic and extrinsic parameters of the camera, and a perspective projection model is constructed based on the parameters to convert the position of the target in the video image into actual geographic coordinates.

[0061] For example, based on the Zhang Zhengyou calibration method, the intrinsic matrix, perspective projection matrix and scale factor of the camera are calculated respectively. Let the pixel coordinate point in the image be (x, y), and the corresponding world coordinate point be (X w ,Y w ,Z w ), we can know from Zhang Zhengyou calibration method:

[0062]

[0063] Where K 3×3 is the camera internal parameter matrix, and the perspective projection matrix is ​​extracted again:

[0064]

[0065] Then we can get:

[0066]

[0067] Order Z c is the scale factor. From the above, we can know the transformation relationship between pixel coordinate points and world coordinate points. According to Zhang Zhengyou's calibration method, use a camera to shoot multiple images of the calibration plate, and first calculate the camera internal parameter matrix K according to the calibration method. 3×3 , and then calculate the perspective projection matrix P 3×4 and the scale factor Z c ,Using Zhang Zhengyou calibration method, the world coordinates of the target can be obtained.

[0068] In some embodiments, the WGS84 world geodetic system is used to convert the Cartesian coordinates in the world coordinate system into longitude and latitude coordinates, and the function of the geographic information system GIS is used to map the acquired longitude and latitude coordinates to the actual position on the map, so that the position of the target on the map can be visualized.

[0069] S240: Continuously track the target in areas covered by different cameras using the geographic coordinates.

[0070] In some embodiments, a data exchange and synchronization mechanism is established between multiple cameras, and the longitude and latitude coordinates of the target are updated in real time. The acquired longitude and latitude coordinates of the target are synchronized between multiple cameras through a network protocol, thereby achieving continuous tracking and trajectory prediction of the target.

[0071] Exemplarily, the target is tracked using the DeepSORT method to obtain the trajectory of the target under the camera, wherein the first few frames of the target's video are put into the Kalman filter for learning, the position of the target in the next frame is predicted, and the observed coordinates and the predicted coordinates are matched by the Hungarian algorithm. If they match, the coefficients of the Kalman filter are updated. If they are inconsistent, the parameters or Kalman filter coefficients of the target are adjusted, and the predicted position is adjusted to continue matching.

[0072] S250, based on perspective transformation, converts the video image into a bird's-eye view, and stitches the bird's-eye view to form a panoramic view.

[0073] In some embodiments, 4 points are set on a frame of monitoring image currently being processed, and a bird's-eye view can be obtained through perspective transformation. In the bird's-eye view, 4 new coordinates corresponding to the 4 points selected on the original image can also be obtained. These 8 points determine the transformation matrix of the original image, i.e., the bird's-eye view. When extracting control points, a principle can be followed: that is, the 4 extracted ground control points must form a measurable rectangle in the bird's-eye view; in order to better restore the bird's-eye view in the real scene, when extracting control points, the other four control point pairs transformed into the bird's-eye view can form a regular rectangle, i.e., a square. The homography matrix H is calculated based on the video screen, and the bird's-eye view conversion is completed using the homography matrix.

[0074] In some embodiments, since different images may be shot under different lighting conditions, resulting in color differences, color balance adjustment can be performed on each bird's-eye view image to keep them as consistent as possible in overall tone and enhance the edges of the bird's-eye view image.

[0075] In some embodiments, feature matching algorithms are used to extract feature points on each bird's-eye view and match them. Euclidean distance is used to measure the similarity between feature points, and feature points with closer distances are considered to be matched. These feature points are used to optimize the existing homography matrix, and the optimized homography matrix is ​​used to transform each bird's-eye view to obtain new coordinates in a unified coordinate system.

[0076] Furthermore, the weighted average stitching method is used to stitch the bird's-eye view images. The weights are calculated according to the positions of the pixels in the images. In the overlapping area, the pixels close to the center of an image are given a larger weight, while the pixels far from the center are given a smaller weight.

[0077] For example, let the distance from the pixel point (x, y) to the center of image I1 be d1, and the distance from the center of image I2 be d2. Then the weight of image I1 at this point is The weight of image I2 at this point At each pixel point in the overlapping area, a weighted average is performed according to the calculated weight, that is, P (x,y) =w1×P1(x,y)+w2×P2(x,y), for the pixels in the non-overlapping area, directly retain the pixels in the original image, and finally combine all the processed pixels according to their original coordinate positions to form the final stitched image.

[0078] S260: Visualize the geographic coordinates of the target in the panoramic view.

[0079] In some embodiments, the method further includes mapping the geographic coordinates of the target to a corresponding position in the three-dimensional model, and using three-dimensional rendering to dynamically display the target in the three-dimensional model. The dynamic display can be in the form of a bird's-eye view or in the form of a first-person perspective.

[0080] The three-dimensional model may be generated in real time according to the panoramic view, or may be generated in advance.

[0081] Exemplarily, the coordinate system used by the three-dimensional model is determined, and coordinate conversion calculations are performed based on the relationship between the target's geographic coordinates and the three-dimensional model coordinate system, thereby mapping the target's geographic coordinates to the three-dimensional model's coordinate system, and by using a graphics rendering engine, dynamic display of the target in the three-dimensional model is achieved.

[0082] In some embodiments, by designing an intuitive and interactive user interface, a real-time bird's-eye view monitoring diagram is provided, so that users can observe the dynamic changes of the target at any time. At the same time, some auxiliary information, such as the name and attributes of the target, can be added to enhance the user's understanding of the target.

[0083] According to the embodiments of the present disclosure, multi-camera linked monitoring is implemented, high-precision and high-real-time target detection and tracking are achieved using various deep learning algorithms, and perspective projection technology is used to convert the target position in the image into actual geographic coordinates, thereby enhancing the accuracy and practicality of target positioning.

[0084] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present disclosure is not limited by the order of the actions described, because according to the present disclosure, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present disclosure.

[0085] The above is an introduction to the method embodiment. The following is a further explanation of the scheme disclosed in the present invention through an apparatus embodiment.

[0086] Figure 3 FIG. 3 is a block diagram of a GIS-based metropolitan area security video monitoring device 300 according to an embodiment of the present disclosure. Figure 3 As shown, the device 300 includes:

[0087] An acquisition module is used to acquire video images of the coverage area in real time through a camera;

[0088] An analysis module, used to analyze the video image in real time using a target detection algorithm to identify the target in the video image;

[0089] A conversion module, used for converting the position of the target in the video screen into actual geographic coordinates based on coordinate system conversion;

[0090] A tracking module, used to continuously track the target in different camera coverage areas through the geographic coordinates;

[0091] A splicing module, used for converting the video images into a bird's-eye view based on perspective transformation, and splicing the bird's-eye view to form a panoramic view;

[0092] The display module is used to visualize the geographic coordinates of the target in the panoramic view.

[0093] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0094] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0095] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0096] Figure 4 A schematic block diagram of an electronic device 400 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0097] The electronic device 400 includes a computing unit 401, which can perform various appropriate actions and processes according to a computer program stored in a ROM 402 or a computer program loaded from a storage unit 406 into a RAM 403. In the RAM 403, various programs and data required for the operation of the electronic device 400 can also be stored. The computing unit 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An I / O interface 405 is also connected to the bus 404.

[0098] Multiple components in the electronic device 400 are connected to the I / O interface 405, including: an input unit 406, such as a keyboard, a mouse, etc.; an output unit 407, such as various types of displays, speakers, etc.; a storage unit 406, such as a disk, an optical disk, etc.; and a communication unit 409, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 409 allows the electronic device 400 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0099] The computing unit 401 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 401 performs the various methods and processes described above, such as method 200. For example, in some embodiments, the method 200 may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of the method 200 described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform the method 200 in any other appropriate manner (e.g., by means of firmware).

[0100] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0101] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0102] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0103] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0104] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0105] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0106] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0107] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A GIS-based metropolitan area security video monitoring method, comprising: Obtain video images of the coverage area in real time through the camera; Analyzing the video in real time using a target detection algorithm to identify targets in the video; Based on the coordinate system conversion, the position of the target in the video screen is converted into actual geographic coordinates; Continuously tracking the target in different camera coverage areas by using the geographic coordinates; Based on perspective transformation, the video screen is converted into a bird's-eye view, and the bird's-eye view is spliced ​​to form a panoramic view; The geographic coordinates of the target in the panoramic view are visualized.

2. The method according to claim 1, characterized in that The target detection algorithm is YOLOv5, including: Read the video images captured from the camera frame by frame; Input each frame of the read image into the trained YOLOv5 network model in turn; The YOLOv5 network model captures the target in the current frame image, frames the target area, and obtains the target type, outline, and calibration coordinates.

3. The method according to claim 1, characterized in that The step of converting the position of the target in the video screen into actual geographic coordinates based on the coordinate system conversion includes: The camera calibration method is used to obtain the intrinsic and extrinsic parameters of the camera. According to its parameters, a perspective projection model is constructed to convert the position of the target in the video screen into actual geographic coordinates.

4. The method according to claim 1, characterized in that The continuously tracking the target in different camera coverage areas by using the geographic coordinates includes: The geographic coordinates of the target are updated in real time and the geographic coordinate information is shared with other related cameras, and the target is tracked by DeepSORT to obtain the trajectory of the target under the camera, wherein the tracking of the target by DeepSORT includes: By putting the first few frames of the target's video into the Kalman filter for learning, the position of the target in the next frame is predicted, and the observed coordinates and the predicted coordinates are matched through the Hungarian algorithm. If the two are consistent, they are matched. If not, the parameters of the target are adjusted or the Kalman filter system continues to match.

5. The method according to claim 1, characterized in that The step of converting the video image into a bird's-eye view based on perspective transformation includes: The homography matrix H is calculated according to the video image, and the homography matrix H is used to complete the bird's-eye view conversion.

6. The method according to claim 1, characterized in that The method for stitching bird's-eye views to form a panoramic view includes: The transformed bird's-eye view images from multiple cameras are stitched together using an image stitching algorithm to generate a panoramic bird's-eye view.

7. The method according to claim 1, characterized in that The method further comprises: The geographic coordinates of the target are mapped to the corresponding position in the 3D model, and 3D rendering is used to realize the dynamic display of the target in the 3D model.

8. A metropolitan area security video surveillance system based on GIS, comprising: An acquisition module is used to acquire video images of the coverage area in real time through a camera; An analysis module, used to analyze the video image in real time using a target detection algorithm to identify the target in the video image; A conversion module, used for converting the position of the target in the video screen into actual geographic coordinates based on coordinate system conversion; A tracking module, used to continuously track the target in different camera coverage areas through the geographic coordinates; A splicing module, used for converting the video images into a bird's-eye view based on perspective transformation, and splicing the bird's-eye view to form a panoramic view; The display module is used to visualize the geographic coordinates of the target in the panoramic view.

9. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-7.

Images