Passing target identification method and device for multidirectional passing area, equipment and medium
By installing multiple cameras on the simultaneously, the video stream is captured simultaneously and 3D spatial coordinates are constructed, the problems of high equipment costs, large sizes and poor flexibility in the pass area are solved, and accurate target recognition and motion trajectory tracking in the multi-direction pass area are achieved.
Patent Information
- Application Number
- CN202510326547.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-19
- Publication Date
- 2025-07-01
AI Technical Summary
In the prior art, the target identification equipment in the pass area is costly, the equipment is large in size and poor in flexibility, and it cannot be effectively applied especially in scenarios where 3D spatial position information is required.
By installing multiple cameras on the sequential cameras, synchronously capture video streams, using object feature recognition and comparison algorithms to identify the target outline, construct 3D spatial coordinates, calculate the angle and distance between the target and the camera, and real-time tracking of the target motion trajectory in the multi-directional pass area.
Accurate target recognition in multi-directional traffic areas is achieved, which reduces equipment costs, reduces equipment volume, improves flexibility, and can be efficiently applied in scenarios where 3D spatial location information is required.
Smart Images
Figure CN120235944A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the technical field of target recognition, and particularly relates to a method, device, equipment and medium for recognizing passing targets in a multi-directional passing area. Background Art
[0002] In related technologies, in scenarios such as turnstiles, passenger flow capture, and security monitoring in a passing area, which have the function of capturing and recognizing the position information of targets, most of them are currently realized based on cameras combined with depth sensors; for two-way passing capture, two sets of cameras and depth sensors are required, and the two sets of cameras are independent of each other; the disadvantages of this implementation method are high cost, large equipment volume, and poor flexibility; assuming the depth sensor is removed and a single camera is used, the position information of 3D space targets cannot be obtained, and it cannot be used in scenarios with requirements for target position information. Summary of the Invention
[0003] This application aims to at least solve one of the technical problems in the above technologies to some extent. For this purpose, an object of this application is to propose a method for recognizing passing targets in a multi-directional passing area, which captures passing targets in the captured area by installing cameras in a facing manner and calculates the position information of the passing targets, so as to achieve the purpose of accurately recognizing in any angular orientation in 3D space, thereby solving the problems of high cost, large volume, and poor flexibility of unidirectional independent capture devices.
[0004] To achieve the above object, the first aspect embodiment of this application proposes a method for recognizing passing targets in a multi-directional passing area, which captures passing targets in the multi-directional passing area by installing multiple cameras in a facing manner. The passing target recognition method includes the following steps: obtaining real-time video streams synchronously captured by multiple cameras to obtain frame images corresponding to each camera; using an object feature recognition and comparison algorithm to recognize the contours of the same part of the passing target in the frame images corresponding to each camera, and obtaining the pixel values of the same part of the passing target in the frame images corresponding to each camera according to the contours; constructing a 3D space coordinate, and obtaining the angle between the passing target and the corresponding camera and the horizontal line according to the pixel values; obtaining the horizontal distance between multiple cameras, and obtaining the horizontal distance between the passing target and the corresponding camera according to the angle between the passing target and the corresponding camera and the horizontal line and the horizontal distance between multiple cameras; and performing real-time tracking and recognition on the movement trajectory of the passing target in the multi-directional passing area according to the horizontal distance between the passing target and the corresponding camera.
[0005] According to the above technical means, in the embodiments of the present application, multiple cameras are installed facing each other, synchronized and aligned, image acquisition is performed, and target recognition is carried out; it is possible to capture passing targets in a multi-directional passing area, and determine the same target through object recognition comparison and edge contour recognition technology, calculate the position information of the object to construct a 3D imaging vision, so as to achieve the purpose of accurately capturing and recognizing at any angle and azimuth in the 3D space, and solve the problems of high cost, large volume and poor flexibility of single independent capture devices.
[0006] In addition, the method for recognizing passing targets in a multi-directional passing area proposed in the above embodiments of the present application may further have the following additional technical features:
[0007] Furthermore, before obtaining the real-time video streams synchronously captured by multiple cameras, it further includes: calibrating the multiple cameras to generate a calibration file, and storing the calibration file.
[0008] Furthermore, the multiple cameras include a first camera and a second camera. According to the following formula, the angle between the passing target and the horizontal line of the first camera, and the angle between the passing target and the horizontal line of the second camera are obtained:
[0009] θ1 = k * p1
[0010] θ2 = k * p2
[0011] Wherein, θ1 represents the angle between the passing target and the horizontal line of the first camera, θ2 represents the angle between the passing target and the horizontal line of the second camera, p1 represents the pixel value of the same part of the passing target in the frame image corresponding to the first camera, p2 represents the pixel value of the same part of the passing target in the frame image corresponding to the second camera, and k represents a dynamically changing constant related to the characteristics of the camera.
[0012] Furthermore, according to the following formula, the horizontal distance between the passing target and the first camera, and the horizontal distance between the passing target and the second camera are obtained:
[0013]
[0014] Wherein, d1 represents the horizontal distance between the passing target and the first camera, d2 represents the horizontal distance between the passing target and the second camera, and D represents the horizontal distance between the first camera and the second camera.
[0015] In the second aspect of the embodiments of the present application, a traffic target recognition device for a multi-directional traffic area is provided. By installing multiple cameras facing each other, the traffic targets in the multi-directional traffic area are captured. The traffic target recognition device includes: an acquisition module, configured to acquire real-time video streams synchronously captured by multiple cameras to obtain frame images corresponding to each camera; a first calculation module, configured to use an object feature recognition and comparison algorithm to recognize the contours of the same part of the traffic target in the frame images corresponding to each camera, and obtain the pixel values of the same part of the traffic target in the frame images corresponding to each camera according to the contours; a space construction module, configured to construct a 3D space coordinate, and obtain the angle between the traffic target and the horizontal line of the corresponding camera according to the pixel values; a second calculation module, configured to obtain the horizontal distance between multiple cameras, and obtain the horizontal distance between the traffic target and the corresponding camera according to the angle between the traffic target and the horizontal line of the corresponding camera and the horizontal distance between multiple cameras; an identification module, configured to perform real-time tracking and identification of the movement trajectory of the traffic target in the multi-directional traffic area according to the horizontal distance between the traffic target and the corresponding camera.
[0016] In addition, the traffic target recognition device for a multi-directional traffic area proposed in the above embodiments of the present application may further have the following additional technical features:
[0017] Furthermore, the traffic target recognition device for a multi-directional traffic area further includes a calibration module, configured to calibrate the multiple cameras to generate a calibration file and store the calibration file.
[0018] Furthermore, the multiple cameras include a first camera and a second camera. The angles between the traffic target and the horizontal line of the first camera and the angles between the traffic target and the horizontal line of the second camera are obtained according to the following formulas:
[0019] θ1 = k * p1
[0020] θ2 = k * p2
[0021] where θ1 represents the angle between the traffic target and the horizontal line of the first camera, θ2 represents the angle between the traffic target and the horizontal line of the second camera, p1 represents the pixel value of the same part of the traffic target in the frame image corresponding to the first camera, p2 represents the pixel value of the same part of the traffic target in the frame image corresponding to the second camera, and k represents a dynamically changing constant related to the characteristics of the camera.
[0022] Furthermore, the horizontal distances between the traffic target and the first camera and the horizontal distances between the traffic target and the second camera are obtained according to the following formulas:
[0023]
[0024] Among them, d1 represents the horizontal distance between the passing target and the first camera, d2 represents the horizontal distance between the passing target and the second camera, and D represents the horizontal distance between the first camera and the second camera.
[0025] The third aspect embodiment of the present application provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor. The processor executes the program to implement the passing target recognition method for the multi-direction passing area as described in the above embodiments.
[0026] The fourth aspect embodiment of the present application provides a computer-readable storage medium. The computer-readable storage medium stores computer instructions for causing the computer to execute the passing target recognition method for the multi-direction passing area as described in the above embodiments.
[0027] Additional aspects and advantages of the present application will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present application. Description of the Drawings
[0028] Figure 1 It is a schematic flow chart of the passing target recognition method for the multi-direction passing area according to the embodiment of the present application;
[0029] Figure 2 It is a schematic diagram of the opposite installation of cameras according to an embodiment of the present application;
[0030] Figure 3 It is a schematic top view of the opposite installation of cameras according to an embodiment of the present application;
[0031] Figure 4 It is a schematic diagram of multi-camera imaging according to an embodiment of the present application;
[0032] Figure 5 It is a schematic diagram of the contour of the same passing target and the same part recognized by multiple cameras according to an embodiment of the present application;
[0033] Figure 6 It is a schematic 3D space structure diagram according to an embodiment of the present application;
[0034] Figure 7 It is a schematic flow chart of the passing target recognition method for the multi-direction passing area according to an embodiment of the present application;
[0035] Figure 8Schematic block diagram of a traffic target recognition device for a multi-directional traffic area according to an embodiment of the present application. Detailed implementation manners
[0036] The embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present application, and should not be construed as limiting the present application.
[0037] To better understand the above technical solution, the exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present application can be more thoroughly understood and the scope of the present application can be completely conveyed to those skilled in the art.
[0038] To better understand the above technical solution, the above technical solution will be described in detail below in combination with the accompanying drawings of the specification and specific implementation manners.
[0039] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of a traffic target recognition method for a multi-directional traffic area according to an embodiment of the present application. By installing multiple pairs of cameras to capture traffic targets in the multi-directional traffic area, as Figure 1 shown, the traffic target recognition method for the multi-directional traffic area includes the following steps:
[0040] S101, Obtain real-time video streams captured synchronously by multiple cameras to obtain frame images corresponding to each camera.
[0041] That is to say, the image frames of multiple cameras are synchronized, and the synchronized real-time video streams are collected.
[0042] As an embodiment, before obtaining the real-time video streams captured synchronously by multiple cameras, it further includes calibrating multiple cameras to generate a calibration file and storing the calibration file.
[0043] As a specific example, the generated calibration file can be stored on the host side and loaded when the software allows initialization.
[0044] It should be noted that calibration is a process of calibrating the camera, including determining the internal and external parameters of the camera, that is, the internal parameters of the camera (such as focal length, principal point coordinates, etc.) and external parameters (such as the position and orientation of the camera relative to the world coordinate system). The purpose of calibration is to accurately convert the image information captured by the camera into actual physical space coordinates, so as to achieve precise measurement and positioning of the target object; generating a calibration file is to save the calculated parameters in the calibration file for subsequent image processing and target recognition; in addition, calibration is also a key step to ensure that the camera system can accurately measure and identify targets in space, which is crucial for improving the system accuracy and reliability; in a multi-camera system, calibration also helps to synchronize the perspectives of different cameras to ensure that they can work together to jointly construct accurate 3D spatial information.
[0045] S102, using the object feature recognition and comparison algorithm to recognize the contour of the same part of the passing target in the frame images corresponding to each camera, and obtaining the pixel values of the same part of the passing target in the frame images corresponding to each camera according to the contour.
[0046] That is to say, for the synchronized frame images collected by multiple cameras, the object feature recognition and comparison algorithm is used to recognize the same part of the same target in multiple frame images, and the contour of the same part is recognized to calculate its pixel value.
[0047] It should be noted that the object feature recognition and comparison algorithm is an algorithm used to detect and recognize specific object features from images and compare these features with known object features. Its main purpose is to accurately identify the target object in a complex scene and determine its identity at different images or different time points. Among them, target detection algorithms (such as HOG, SSD, YOLO, etc.) are used to locate the target object in each image to provide the position and size information of the target object in the image. In the area of the target object, its feature points are extracted. Commonly used feature point extraction algorithms include SIFT, SURF, ORB, etc. These algorithms can extract the local feature points of the object, and these feature points have scale invariance, rotation invariance, and robustness to illumination changes. The feature points extracted from different images are matched to determine the corresponding feature points of the same target object in different images. Commonly used feature matching algorithms include FLANN (Fast Library for Approximate Nearest Neighbors) matching, BF (Brute Force) matching, etc. In the area of the target object, its contour is extracted. Commonly used contour extraction algorithms include Canny edge detection, Sobel edge detection, etc. These algorithms can extract the edge information of the object to obtain the contour of the object. The contours extracted from different images are matched to determine the corresponding contours of the same target object in different images. Commonly used contour matching algorithms include Hausdorff distance, Frechet distance, etc. After determining the contour of the same part of the same target in multiple images, its pixel value can be calculated. The pixel value usually refers to the pixel value of the contour in the image, and the corresponding pixel value can be obtained by calculating statistics such as the average value and median value of all pixels within the contour.
[0048] Specifically, as Figure 2 and Figure 3 shown, multiple cameras include a first camera and a second camera. The first camera and the second camera are installed opposite to each other on both sides of the two-way traffic area. The traffic targets include target A and target B. After installation, the first camera and the second camera capture the images of target A and target B in the two-way traffic area as Figure 4 shown. The head contours of target A recognized by the first camera and the second camera respectively using the object feature recognition and comparison algorithm are as Figure 5 shown.
[0049] S103, construct a 3D space coordinate and obtain the angle between the traffic target and the corresponding camera and the horizontal line according to the pixel value.
[0050] S104, obtain the horizontal distance between multiple cameras, and obtain the horizontal distance between the traffic target and the corresponding camera according to the angle between the traffic target and the corresponding camera and the horizontal line and the horizontal distance between multiple cameras.
[0051] As an embodiment, asFigure 6 As shown in the figure, assume that the horizontal distance between the first camera and the second camera is D, and the imaging pixel sizes of the same target in the first camera and the second camera are p1 and p2; θ1 and θ2 are the angles formed by the passing target with the horizontal line to the corresponding cameras. The calculation methods are as follows:
[0052] θ1 = k * p1
[0053] θ2 = k * p2
[0054] Among them, k represents a dynamically changing constant related to the characteristics of the camera.
[0055] The actual size of the passing target is calculated as follows:
[0056] Actual size = k * p
[0057] Among them, the horizontal distances d1 and d2 of the passing target from the first camera and the second camera are calculated as follows:
[0058]
[0059] Through the above calculations, the position and size information of the target in the 3D space can be determined.
[0060] S105. Real-time track and identify the movement trajectory of the passing target in the multi-directional passing area according to the horizontal distance between the passing target and the corresponding camera.
[0061] Therefore, in this application, multiple cameras in opposite directions capture images synchronously, with a wider area coverage, thus reducing the blind area, and being able to capture passing targets with different orientations and movement directions, thereby having a better ability to capture the best pictures, and being able to accurately calculate the position and size of an object in the 3D space, and thus being better applied to scenarios that require capturing the position and size information of the target.
[0062] In addition, for a better understanding of the above technical solution, as a specific embodiment, as Figure 7 shown, it includes the following steps:
[0063] S1. Install the camera and perform calibration.
[0064] S2. The software starts and loads the calibration file.
[0065] S3. Synchronize the frames of multiple cameras and collect synchronous frames in real time.
[0066] S4. Identify the same target with multiple cameras, identify the contour of the same part, and calculate the pixel values.
[0067] S5. Calculate the target position distance and size through the formula, and construct the 3D space coordinates of the target.
[0068] S6. Track the target in real time and return to S3 to repeat the steps.
[0069] In summary, according to the method for identifying passing targets in a multi-directional passing area according to an embodiment of the present invention, first, obtain real-time video streams captured synchronously by multiple oppositely installed cameras to obtain frame images corresponding to each camera; then, use an object feature recognition and comparison algorithm to recognize the contours of the same part of the passing target in the frame images corresponding to each camera, and obtain the pixel values of the same part of the passing target in the frame images corresponding to each camera according to the contours; then, construct a 3D space coordinate, and obtain the angle between the passing target and the horizontal line of the corresponding camera according to the pixel value; then, obtain the horizontal distance between multiple cameras, and obtain the horizontal distance between the passing target and the corresponding camera according to the angle between the passing target and the horizontal line of the corresponding camera and the horizontal distance between multiple cameras; finally, perform real-time tracking and recognition of the movement trajectory of the passing target in the multi-directional passing area according to the horizontal distance between the passing target and the corresponding camera; thus, capture the passing target in the area captured by the oppositely installed cameras, calculate the position information of the passing target, and achieve the purpose of accurately identifying in any angular orientation in 3D space, thereby solving the problems of high cost, large volume, and poor flexibility of single independent capture devices.
[0070] To implement the above embodiment, a device for identifying passing targets in a multi-directional passing area proposed in an embodiment of the present application is as Figure 8 shown. The device for identifying passing targets in a multi-directional passing area proposed in the present application includes: an acquisition module 10, a first calculation module 20, a space construction module 30, a second calculation module 40, and an identification module 50.
[0071] Among them, the acquisition module 10 is used to obtain real-time video streams captured synchronously by multiple cameras to obtain frame images corresponding to each camera; the first calculation module 20 is used to use an object feature recognition and comparison algorithm to recognize the contours of the same part of the passing target in the frame images corresponding to each camera, and obtain the pixel values of the same part of the passing target in the frame images corresponding to each camera according to the contours; the space construction module 30 is used to construct a 3D space coordinate, and obtain the angle between the passing target and the horizontal line of the corresponding camera according to the pixel value; the second calculation module 40 is used to obtain the horizontal distance between multiple cameras, and obtain the horizontal distance between the passing target and the corresponding camera according to the angle between the passing target and the horizontal line of the corresponding camera and the horizontal distance between multiple cameras; the identification module 50 is used to perform real-time tracking and recognition of the movement trajectory of the passing target in the multi-directional passing area according to the horizontal distance between the passing target and the corresponding camera.
[0072] As an embodiment, the traffic target recognition device for a multi-way traffic area further includes a calibration module for calibrating multiple cameras to generate a calibration file and storing the calibration file.
[0073] As an embodiment, the multiple cameras include a first camera and a second camera. The angles between the traffic target and the horizontal line of the first camera and the angles between the traffic target and the horizontal line of the second camera are obtained according to the following formula:
[0074] θ1 = k * p1
[0075] θ2 = k * p2
[0076] Where θ1 represents the angle between the traffic target and the horizontal line of the first camera, θ2 represents the angle between the traffic target and the horizontal line of the second camera, p1 represents the pixel value of the same part of the traffic target in the frame image corresponding to the first camera, p2 represents the pixel value of the same part of the traffic target in the frame image corresponding to the second camera, and k represents a dynamically changing constant related to the characteristics of the camera.
[0077] As an embodiment, the horizontal distances between the traffic target and the first camera and the horizontal distances between the traffic target and the second camera are obtained according to the following formula:
[0078]
[0079] Where d1 represents the horizontal distance between the traffic target and the first camera, d2 represents the horizontal distance between the traffic target and the second camera, and D represents the horizontal distance between the first camera and the second camera.
[0080] It should be noted that the foregoing explanation of the embodiments of the traffic target recognition method for a multi-way traffic area also applies to the traffic target recognition device for a multi-way traffic area in this embodiment, and will not be elaborated here.
[0081] An embodiment of the present application further provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor. The processor executes the program to implement the traffic target recognition method for a multi-way traffic area as described above.
[0082] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the traffic target recognition method for a multi-way traffic area as described above.
[0083] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of this application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.
[0084] In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise specifically defined.
[0085] Any process or method description shown in the flowchart or described in other ways herein can be understood as representing a module, segment, or portion of code including one or more N executable instructions for implementing a customized logic function or process, and the scope of the preferred embodiments of this application includes additional implementations, where the functions can be executed in a substantially simultaneous manner or in a reverse order according to the functions involved, rather than in the order shown or discussed, which should be understood by those skilled in the art to which the embodiments of this application pertain.
[0086] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definable sequence list of executable instructions for implementing logical functions, which can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or used in combination with these instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection part (electronic device) having one or N wirings, a portable computer disk cartridge (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or other suitable processing as necessary, and then stored in a computer memory.
[0087] It should be understood that various parts of the present application can be implemented by hardware, software, firmware, or a combination thereof. In the above-described embodiments, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having suitable combinational logic gate circuits, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.
[0088] Those of ordinary skill in the art of this technology can understand that all or part of the steps carried by the method of implementing the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.
[0089] In addition, each functional unit in various embodiments of the present application may be integrated into a processing module, may exist separately as individual physical units, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.
[0090] The above-mentioned storage medium may be a read-only memory, a magnetic disk, an optical disc, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.
Claims
1. A method for identifying a traffic target in a multi-directional traffic area, characterized in that: By installing a plurality of cameras for shooting oppositely to each other to capture the passing targets in the multi-directional passing area, the passing target recognition method comprises the following steps: Acquire the real-time video stream captured synchronously by multiple cameras to obtain the frame image corresponding to each camera; An object feature recognition and comparison algorithm is used to identify the contour of the same part of the passing target in the frame image corresponding to each camera, and the pixel value of the same part of the passing target in the frame image corresponding to each camera is obtained according to the contour; Constructing 3D spatial coordinates, and obtaining the angle between the passing target and the corresponding camera and the horizontal line according to the pixel value; Acquire the horizontal distances between the multiple cameras, and obtain the horizontal distance between the passing target and the corresponding camera according to the angle between the passing target and the corresponding camera and the horizontal line and the horizontal distance between the multiple cameras; The motion trajectory of the passing target in the multi-directional passing area is tracked and identified in real time according to the horizontal distance between the passing target and the corresponding camera.
2. The method for identifying traffic targets in a multi-directional traffic area according to claim 1, characterized in that: Before acquiring the real-time video streams captured synchronously by multiple cameras, the method further includes: calibrating the multiple cameras to generate a calibration file, and storing the calibration file.
3. The method for identifying traffic targets in a multi-directional traffic area according to claim 1, characterized in that: The multiple cameras include a first camera and a second camera, and the angle between the passing target and the first camera and the horizontal line, and the angle between the passing target and the second camera and the horizontal line are obtained according to the following formula: θ1=k*p1 θ2=k*p2 Among them, θ1 represents the angle between the passing target and the first camera and the horizontal line, θ2 represents the angle between the passing target and the second camera and the horizontal line, p1 represents the pixel value of the same part of the passing target in the frame image corresponding to the first camera, p2 represents the pixel value of the same part of the passing target in the frame image corresponding to the second camera, and k represents a dynamic change constant related to the camera characteristics.
4. The method for identifying traffic targets in a multi-directional traffic area according to claim 3, characterized in that: The horizontal distance between the passing target and the first camera and the horizontal distance between the passing target and the second camera are obtained according to the following formula: Among them, d1 represents the horizontal distance between the passing target and the first camera, d2 represents the horizontal distance between the passing target and the second camera, and D represents the horizontal distance between the first camera and the second camera.
5. A device for identifying traffic targets in a multi-directional traffic area, characterized in that: By installing multiple cameras for shooting at each other to capture the passing targets in the multi-directional passing area, the passing target recognition device includes: The acquisition module is used to acquire the real-time video streams captured synchronously by multiple cameras to obtain the frame image corresponding to each camera; A first calculation module is used to identify the contour of the same part of the passing target in the frame image corresponding to each camera by using an object feature recognition and comparison algorithm, and obtain the pixel value of the same part of the passing target in the frame image corresponding to each camera according to the contour; A space construction module is used to construct 3D space coordinates and obtain the angle between the passing target and the corresponding camera and the horizontal line according to the pixel value; A second calculation module is used to obtain the horizontal distance between the multiple cameras, and obtain the horizontal distance between the passing target and the corresponding camera according to the angle between the passing target and the corresponding camera and the horizontal line and the horizontal distance between the multiple cameras; The recognition module is used to track and recognize the movement trajectory of the passing target in the multi-directional passage area in real time according to the horizontal distance between the passing target and the corresponding camera.
6. The device for identifying a target in a multi-directional traffic area according to claim 5, characterized in that: The system also includes a calibration module for calibrating the multiple cameras to generate a calibration file and storing the calibration file.
7. The device for identifying a target in a multi-directional traffic area according to claim 6, characterized in that: The multiple cameras include a first camera and a second camera, and the angle between the passing target and the first camera and the horizontal line, and the angle between the passing target and the second camera and the horizontal line are obtained according to the following formula: θ1=k*p1 θ2=k*p2 Among them, θ1 represents the angle between the passing target and the first camera and the horizontal line, θ2 represents the angle between the passing target and the second camera and the horizontal line, p1 represents the pixel value of the same part of the passing target in the frame image corresponding to the first camera, p2 represents the pixel value of the same part of the passing target in the frame image corresponding to the second camera, and k represents a dynamic change constant related to the camera characteristics.
8. The device for identifying a target in a multi-directional traffic area according to claim 7, characterized in that: The horizontal distance between the passing target and the first camera and the horizontal distance between the passing target and the second camera are obtained according to the following formula: Among them, d1 represents the horizontal distance between the passing target and the first camera, d2 represents the horizontal distance between the passing target and the second camera, and D represents the horizontal distance between the first camera and the second camera.
9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement a method for identifying a traffic target in a multi-directional traffic area as described in any one of claims 1 to 4.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement a method for identifying a traffic target in a multi-directional traffic area as described in any one of claims 1 to 4.