Multi-target snapshot method, device and equipment in examination room environment and storage medium

Abstract

The invention discloses a multi-target snapshot method, device and equipment in an examination room environment and a storage medium, and relates to the technical field of computer vision, and the method comprises the steps: detecting the central point coordinate position of each target object in an examination room panoramic top view shot by a panoramic camera; for any target object, determining a to-be-rotated angle of the close-up camera and a field angle required for focusing the close-up camera to the target object based on the central point coordinate position of the target object; and adjusting the close-up camera according to the to-be-rotated angle and the field angle, and capturing the target object through the adjusted close-up camera. According to the method, the binocular camera is installed at the top of the examination room, so that the target object is quickly and accurately captured, the working efficiency of invigilators is improved, meanwhile, the fairness of examinees is ensured, and the effect of efficiently and reliably scanning the examination paper in the remote examination paper marking process is achieved.

Description

Technical Field

[0001] The present application relates to the field of computer vision technology, and in particular to a method, device, electronic device and storage medium for capturing multiple targets in an examination environment. Background Art

[0002] In recent years, Internet-based remote marking technology has been widely used in the education industry. The real-time, convenient and efficient nature of remote marking has become increasingly popular among teachers. The traditional method of manually moving test papers to scanning equipment requires invigilators to collect and seal all students' test papers one by one after each exam. After transporting them a certain distance, they are placed one by one in the scanning machine to scan the contents of the test papers. This greatly increases the workload of invigilators and makes the entire remote marking inefficient. At the same time, in the process of scanning the test papers, invigilators need to manually use cameras or scanners to shoot or scan the test papers one by one, and then import them into the marking system for identification. This manual collection of electronic test papers is also inefficient, and during the transportation of physical test papers, there may be problems such as loss, damage, and replacement of test papers that affect the fairness of candidates.

[0003] Therefore, how to scan the test papers efficiently and reliably during the remote marking process is a problem that needs to be solved urgently. Summary of the invention

[0004] The main purpose of this application is to provide a multi-target capture method, device, electronic equipment and storage medium in an examination environment, aiming to solve the technical problem of how to scan examination papers efficiently and reliably during remote marking.

[0005] To achieve the above-mentioned purpose, the present application proposes a multi-target capture method in an examination room environment, wherein the multi-target capture method in the examination room environment is applied to a multi-target capture system, wherein the multi-target capture system includes a binocular camera, and the binocular camera includes a panoramic camera and a close-up camera. The multi-target capture method in the examination room environment includes: Detect the coordinate position of the center point of each target object in the panoramic bird's-eye view of the examination room taken by the panoramic camera; For any target object, based on the coordinate position of the center point of the target object, determine the angle to be rotated of the close-up camera and the field of view angle required for the close-up camera to focus on the target object; The close-up camera is adjusted according to the angle to be rotated and the field of view, and the target object is captured by the adjusted close-up camera.

[0006] In one embodiment, the angle to be rotated includes a horizontal angle to be rotated and a vertical angle to be rotated, and the step of determining the angle to be rotated of the close-up camera and the field of view angle required for the close-up camera to focus on the target object based on the coordinate position of the center point of the target object includes: Calculate the horizontal rotation angle of the close-up camera and the vertical rotation angle of the close-up camera based on the coordinate position of the center point; The center point coordinate position is converted into an actual physical coordinate position, and the field of view angle required for the close-up camera to focus on the target object is calculated based on the actual physical coordinate position.

[0007] In one embodiment, the step of converting the center point coordinate position into an actual physical coordinate position, and calculating the field of view angle required for the close-up camera to focus on the target object based on the actual physical coordinate position includes: Acquire the maximum field angle of the panoramic camera and the pixel size of the panoramic bird's-eye view of the examination room, and convert the coordinate position of the center point according to the maximum field angle and the pixel size to obtain the actual physical coordinate position; Calculate the actual distance from the target object to the panoramic camera based on the actual physical coordinate position and the distance from the panoramic camera to the plane where the target object is located; A circumscribed circle of the target object is determined, and the field of view angle is calculated according to the radius of the circumscribed circle and the actual distance.

[0008] In one embodiment, the close-up camera is driven by a motor to rotate, and the step of adjusting the close-up camera according to the angle to be rotated and the field of view, and capturing the target object by using the adjusted close-up camera comprises: Calculating a step value of the motor according to the angle to be rotated and a transmission ratio between the close-up camera and the motor, and executing the step value through the motor to adjust the rotation angle of the close-up camera; Determining a lens zoom value corresponding to the field of view angle based on a preset functional relationship, and adjusting a zoom ratio of the close-up camera according to the lens zoom value; The target object is captured by a close-up camera with an adjusted rotation angle and zoom ratio.

[0009] In one embodiment, after the step of taking a snapshot of the target object by using the adjusted close-up camera, the step further includes: Performing corner cutting detection on the captured target image to obtain the detection result; The rotation angle or zoom ratio of the close-up camera is polyphonically adjusted based on the detection result, and the step of capturing the target object is executed based on the polyphonic close-up camera returning.

[0010] In one embodiment, the step of polynomially adjusting the rotation angle or zoom ratio of the close-up camera based on the detection result comprises: When the detection result shows that the target image has both upper and lower cut corners and / or left and right cut corners, reducing the zoom ratio of the close-up camera to obtain a polyphonic close-up camera; When the detection result is that the target image has any one of upper and lower cut angles and / or any one of left and right cut angles, the rotation angle of the close-up camera is adjusted in the direction of the cut angle to obtain a polyphonic close-up camera.

[0011] In one embodiment, after the step of detecting the coordinate position of the center point of each target object in the panoramic bird's-eye view of the examination room captured by the panoramic camera, the step further includes: The coordinate positions of each center point are statistically analyzed to obtain a capture order in which the close-up camera captures each target object, so as to capture each target object based on the capture order.

[0012] In addition, to achieve the above-mentioned purpose, the present application also proposes a multi-target capture device in an examination room environment, wherein the multi-target capture device is applied to a multi-target capture system, wherein the multi-target capture system includes a binocular camera, wherein the binocular camera includes a panoramic camera and a close-up camera, and the multi-target capture device in the examination room environment includes: A detection module is used to detect the coordinate position of the center point of each target object in the panoramic bird's-eye view of the examination room taken by the panoramic camera; A determination module, for determining, for any target object, based on the coordinate position of the center point of the target object, the angle to be rotated of the close-up camera and the field of view angle required for the close-up camera to focus on the target object; The adjustment module is used to adjust the close-up camera according to the angle to be rotated and the field of view, and to capture the target object through the adjusted close-up camera.

[0013] In addition, to achieve the above-mentioned purpose, the present application also proposes an electronic device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the multi-target capture method as described above.

[0014] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the multi-target capture method described above are implemented.

[0015] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the multi-target capture method described above are implemented.

[0016] One or more technical solutions proposed in this application have at least the following technical effects: The present application first detects the center point coordinate position of each target object in the panoramic overhead view of the examination room taken by the panoramic camera, realizes automatic identification and positioning of multiple target objects in the panoramic overhead view of the examination room, and thus the initial positioning of the target object can be quickly completed without human intervention; for any target object, based on the center point coordinate position of the target object, the angle to be rotated of the close-up camera and the field of view angle required for the close-up camera to focus on the target object are determined, thereby realizing accurate calculation of the angle to be rotated and the adjusted field of view angle of the close-up camera according to the position information of the target object, so as to achieve the effect of accurately aiming at the target object; the close-up camera is adjusted according to the angle to be rotated and the field of view angle, and the target object is captured by the adjusted close-up camera, thereby realizing automatic adjustment of the direction and focal length of the close-up camera to perform clear capture of the target object, thereby realizing efficient and automatic examination paper scanning during remote marking.

[0017] In summary, the present application obtains a panoramic bird's-eye view of the examination room captured by a panoramic camera, and detects the coordinate position of the center point of the target object using image processing technology, thereby determining the rotation angle of the close-up camera and the required field of view angle, and then drives the close-up camera to rotate and zoom accurately, thereby achieving accurate capture of the target object, avoiding the inefficiency of traditional manual scanning of test papers and possible problems such as loss, damage, and replacement of test papers, achieving fast and accurate capture of target objects, improving the work efficiency of invigilators, and ensuring fairness for candidates, achieving the effect of efficient and reliable scanning of test papers during remote marking. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 A flowchart diagram of a multi-target capture method embodiment 1 provided in an examination environment of the present application; Figure 2 A schematic diagram of view detection of a multi-target capture method in an examination environment provided in Embodiment 1 of the present application; Figure 3 A schematic diagram of distance representation of a multi-target capture method in an examination environment provided in Example 1 of the present application; Figure 4 A schematic diagram of the functional relationship of the multi-target capture method in the examination environment provided in the first embodiment of the present application; Figure 5 A flow chart of the second embodiment of the multi-target capture method in the examination environment of this application; Figure 6 A schematic diagram of the capture sequence of the multi-target capture method in the examination room environment provided in the second embodiment of the present application; Figure 7 A schematic diagram of a simplified process of a multi-target capture method in an examination environment provided in Example 2 of the present application; Figure 8 A schematic flow chart of a multi-target capture method in an examination environment provided in Embodiment 2 of the present application; Fig. 9 A schematic diagram of a background scene of a multi-target capture method in an examination room environment provided in Example 2 of the present application; Fig.10 This is a schematic diagram of the module structure of a multi-target capture device in an examination environment according to an embodiment of the present application; Fig.11 Schematic diagram of the device structure of the hardware operating environment involved in the multi-target capture method in an examination environment in an embodiment of the present application.

[0021] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0022] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0023] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0024] The main solution of the embodiment of the present application is: to detect the coordinate position of the center point of each target object in the panoramic overhead view of the examination room taken by the panoramic camera; for any target object, based on the coordinate position of the center point of the target object, determine the angle to be rotated of the close-up camera and the field of view angle required for the close-up camera to focus on the target object; adjust the close-up camera according to the angle to be rotated and the field of view angle, and capture the target object with the adjusted close-up camera.

[0025] Since the existing technology requires the invigilator to collect and seal all the students' test papers after each exam, transport them a certain distance, and then put the test papers into the scanning machine to scan the contents of the test papers, which greatly increases the workload of the invigilator and makes the entire remote marking inefficient. At the same time, in the process of scanning the test papers, the invigilator needs to manually use a camera or scanner to shoot or scan the test papers one by one, and then import them into the marking system for identification. This manual collection of electronic test papers is also inefficient, and there may be problems such as loss, damage, and replacement of physical test papers during transportation, which affects the fairness of candidates. Therefore, how to scan the test papers efficiently and reliably during the remote marking process is a problem that needs to be solved urgently.

[0026] The present application provides a solution, which combines the panoramic bird's-eye view of the examination room captured by a panoramic camera with image processing technology to detect the coordinate position of the center point of the target object, thereby determining the rotation angle of the close-up camera and the required field of view angle, and then drives the close-up camera to rotate and zoom accurately, thereby achieving accurate capture of the target object, avoiding the low efficiency of traditional manual scanning of test papers and the possible problems of test paper loss, damage, and replacement, etc., achieving fast and accurate capture of the target object, improving the work efficiency of the invigilators, and ensuring fairness for the candidates, and achieving the effect of efficient and reliable scanning of the test papers in the remote marking process.

[0027] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device that can realize the above functions. The following takes an electronic device as an example to illustrate this embodiment and the following embodiments.

[0028] Based on this, the present application embodiment provides a multi-target capture method in an examination room environment, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the multi-target capture method in the examination environment of this application.

[0029] In this embodiment, the multi-target capture method in the examination room environment is applied to a multi-target capture system, wherein the multi-target capture system includes a binocular camera, the binocular camera includes a panoramic camera and a close-up camera, and the multi-target capture method includes steps S10 to S30: Step S10, detecting the coordinate position of the center point of each target object in the panoramic bird's-eye view of the examination room captured by the panoramic camera; It should be noted that a panoramic camera refers to a camera installed on the top of the examination room that can capture the entire examination room environment or part of the examination room environment. The camera is responsible for capturing a panoramic overhead view of the examination room; a panoramic overhead view of the examination room refers to an image of the entire examination room or part of the examination room captured by the panoramic camera, which contains visual information of all or part of the candidates and test papers in the examination room; the target object can be the test paper in the examination room that needs to be captured separately by the close-up camera, and it is an object that needs to be identified and analyzed during the remote marking process; the center point coordinate position refers to the position coordinates of the center point of each target object (test paper) identified in the panoramic overhead view of the examination room through image processing technology in the image coordinate system.

[0030] It is understandable that, since the traditional marking process requires manual collection of test papers and then manual scanning of the test papers, resulting in low efficiency in the test paper scanning process, performing step S10 can avoid the inefficiency of manually scanning the test papers one by one, and reduce operational errors during manual transportation and scanning, thereby achieving fast and accurate positioning of the test papers in the examination room, and also providing accurate and reliable data support for subsequent capture of the test papers.

[0031] For example, the YOLO model (an object detection system for computer vision tasks) is trained to identify the position of the target object (exam paper) in the panoramic view of the examination room taken by the panoramic camera, obtain the position frame of each exam paper, and use the center point coordinates of each position frame as the center point coordinates of the exam paper. Figure 2 The solid-line frame in the figure is the table location frame detected by the YOLO model, and the dotted-line frame in the solid-line frame is the location frame of each test paper.

[0032] Step S20, for any target object, based on the coordinate position of the center point of the target object, determining the angle to be rotated of the close-up camera and the field of view angle required for the close-up camera to focus on the target object; It should be noted that the close-up camera refers to a camera in the binocular camera that is used in conjunction with the panoramic camera. It can take detailed photos of specific target objects according to instructions and has the functions of changing shooting angles and zooming. The angle to be rotated refers to the angle that the close-up camera needs to be rotated from its current position in order to aim the close-up camera at the target object, including the horizontal and vertical angles. The field of view angle refers to the field of view required by the close-up camera when focusing on the target object, so as to ensure that the target object is complete and clear in the image.

[0033] It can be understood that since in the process of scanning and capturing the target object, it is necessary to accurately control the close-up camera to capture the target object clearly and in detail, performing step S20 can avoid the problem of inaccurate or unclear capture of the target object due to inaccurate shooting angle and focusing, thereby realizing automated and precise target object positioning and capture.

[0034] In a feasible implementation manner, the angle to be rotated includes a horizontal angle to be rotated and a vertical angle to be rotated. The step of determining the angle to be rotated of the close-up camera and the field of view angle required for the close-up camera to focus on the target object based on the coordinate position of the center point of the target object in step S20 may include steps S21-S22: Step S21, calculating the horizontal rotation angle of the close-up camera and the vertical rotation angle of the close-up camera based on the coordinate position of the center point; It should be noted that the horizontal rotation angle refers to the angle that the close-up camera needs to be rotated in the horizontal direction in order to align the shooting direction of the close-up camera with the center point of the target object; the vertical rotation angle refers to the angle that the close-up camera needs to be rotated in the vertical direction in order to align the shooting direction of the close-up camera with the center point of the target object.

[0035] It is understandable that since it is necessary to accurately control the shooting direction of the close-up camera in the process of accurately capturing multiple target objects, step S21 is performed. By calculating the angles that the close-up camera needs to rotate in the horizontal and vertical directions, the problem of captured image deviation caused by inaccurate positioning of the target object can be avoided, and automated and precise camera positioning is achieved, ensuring that the close-up camera can quickly and accurately capture the image of the target object.

[0036] For example, based on the center point coordinate position of the target object ( x,y ), first calculate the horizontal angle between the target object and the center point of the panoramic view of the examination room :

[0037] Then, based on the calculated horizontal angle Calculate the horizontal rotation angle required for the close-up camera, that is, the horizontal rotation angle to be , and the vertical rotation angle required by the close-up camera, i.e. the vertical rotation angle to be :

[0038]

[0039] in, H is the installation height of the binocular camera, that is, the distance from the panoramic camera to the plane where the target object is located, is the vertical field of view of the panoramic camera. Figure 3 , Figure 3 C is a close-up camera, P is a panoramic camera, D is the desktop where the target object is placed, and H is the distance from the panoramic camera to the plane where the target object is located.

[0040] Step S22: converting the center point coordinate position into an actual physical coordinate position, and calculating the field of view angle required for the close-up camera to focus on the target object based on the actual physical coordinate position.

[0041] It should be noted that the actual physical coordinates refer to the conversion of the coordinate position of the center point in the image into the actual distance in the corresponding coordinate system in the real world; the field of view angle refers to the angle range in the horizontal and vertical directions that the camera can cover when focusing on the target object. This value determines the size and range of the target object that can be presented in the close-up view taken by the close-up camera.

[0042] It is understandable that, since in the process of accurately capturing multiple target objects, it is necessary to adjust the focal length of the camera according to the actual distance between the target object and the camera to ensure the clarity of the image, performing step S22 can avoid image blur or incomplete presentation of the target object in the image due to improper focal length, thereby ensuring that the close-up camera can automatically adjust the focal length according to the actual distance between the target object and the camera when capturing, thereby obtaining a clear and complete image and improving the quality and efficiency of image acquisition.

[0043] For example, the center point coordinate position of the target object ( x,y ) is converted to the actual physical coordinate position ( , ), and based on the actual physical coordinate position ( , ) and the distance from the panoramic camera to the plane where the target object is located HCalculate the actual distance from the target object to the panoramic camera d :

[0044] Then, based on the actual distance d The radius of the circumcircle around the test paper (target object) r , calculate the field of view angle required for the close-up camera to focus on the test paper :

[0045] In this embodiment, by accurately calculating the horizontal and vertical rotation angles of the close-up camera, converting the image coordinates into actual physical coordinates and calculating the required field of view angle accordingly, the problems of angle deviation and improper focal length caused by manual adjustment or inaccurate estimation are avoided, and the close-up camera can quickly and accurately focus and position the target object, thereby achieving an automated, efficient and high-definition image capture effect.

[0046] Step S30, adjusting the close-up camera according to the to-be-rotated angle and the field of view angle, and capturing the target object through the adjusted close-up camera.

[0047] It is understandable that since high-quality image acquisition of the test paper is required during the online marking process to ensure that the specific content on the test paper can be clearly viewed during the marking, step S30 can avoid the problem of target missing or image blur due to inaccurate camera positioning or focusing, thereby achieving efficient and high-quality image acquisition and providing clear image data for subsequent marking analysis.

[0048] In a feasible implementation manner, the close-up camera is driven by a motor to rotate, and step S30 may include steps S31 to S33: Step S31, calculating a step value of the motor according to the angle to be rotated and a transmission ratio between the close-up camera and the motor, and executing the step value through the motor to adjust the rotation angle of the close-up camera; It should be noted that the transmission ratio refers to the proportional relationship between the rotation angle of the close-up camera and the step value of the motor that drives its rotation. This proportional relationship is used to convert the rotation requirements of the close-up camera into the step value required by the motor; the step value refers to the number of steps or step angles that the motor needs to execute in order to achieve the target rotation angle of the close-up camera. This value is the basic unit in motor control.

[0049] It is understandable that in order to accurately control the rotation of the close-up camera, step S31 is performed to accurately determine the rotation of the close-up camera through the motor, thereby avoiding the inaccuracy and inefficiency of manual angle adjustment, so that the close-up camera can be accurately aimed at the target object.

[0050] Exemplarily, the angle to be rotated of the close-up camera includes the angle to be rotated in the horizontal direction and the vertical rotation angle , according to the horizontal angle to be rotated and the vertical rotation angle , and the transmission ratio m between the writer and the motor, calculate the step value of the motor in the horizontal direction and the vertical step value :

[0051]

[0052] Then the motor executes the and to adjust the close-up camera's rotation angle.

[0053] Step S32, determining a lens zoom value corresponding to the field of view angle based on a preset functional relationship, and adjusting a zoom ratio of the close-up camera according to the lens zoom value; It should be noted that the preset functional relationship refers to the mathematical relationship between the field of view angle and the lens zoom value that is pre-set according to the physical characteristics of the lens, and is used to calculate the lens zoom values ​​corresponding to different field of view angles; the lens zoom value refers to the focal length value that needs to be adjusted for the close-up camera lens in order to achieve a specific field of view angle. This value determines the size of the target object in the close-up view taken by the close-up camera; the zoom ratio refers to the focal length adjustment ratio of the lens, which is used to control the size and clarity of the target object in the close-up view.

[0054] It should be noted that since the lens focal length, i.e. the zoom ratio, needs to be adjusted according to the size and distance of the target object, performing step S32 can avoid image blur or incomplete presentation of the target object due to improper focal length, thereby achieving clarity and completeness of the captured close-up view.

[0055] Exemplarily, the preset functional relationship used in this embodiment is:

[0056] in, Corresponding lens zoom value (zoom value), Corresponding field of view , a, b, c, d, eare the corresponding coefficients obtained after training. Please refer to Figure 4 The curve in the figure is the functional relationship, the X-axis represents the field of view, and the Y-axis represents the zoom value. Corresponding lens zoom value to adjust the close-up camera zoom based on this value.

[0057] Step S33, taking a snapshot of the target object by using the close-up camera with the adjusted rotation angle and zoom ratio.

[0058] In this embodiment, by using a motor to control the lens rotation and automatic adjustment of the lens zoom, the inaccuracy, inefficiency and possible human errors in adjusting the camera angle and focal length are avoided, and the close-up camera can quickly and accurately focus and position the target object, ensuring high precision and automation in the process of capturing the target object, thereby improving the operational efficiency of the scanning step in the remote marking process, ensuring image clarity and integrity, and thereby improving the overall marking quality.

[0059] The present embodiment provides a multi-target capture method in an examination room environment, which uses a panoramic bird's-eye view of the examination room captured by a panoramic camera and combines it with image processing technology to detect the coordinate position of the center point of the target object, thereby determining the rotation angle of the close-up camera and the required field of view angle, and then drives the close-up camera to rotate and zoom accurately, thereby achieving accurate capture of the target object, avoiding the low efficiency of traditional manual scanning of test papers and the possible problems of test paper loss, damage, and replacement, etc., achieving fast and accurate capture of the target object, improving the work efficiency of the invigilators, and ensuring fairness for the candidates, and achieving the effect of efficient and reliable scanning of the test paper in the remote marking process.

[0060] In a feasible implementation, step S22 may include steps S221 to S223: Step S221, obtaining the maximum field angle of the panoramic camera and the pixel size of the panoramic bird's-eye view of the examination room, and converting the coordinate position of the center point according to the maximum field angle and the pixel size to obtain the actual physical coordinate position; It should be noted that the maximum field of view refers to the maximum angle that the panoramic camera can capture without any zoom. This value determines the field of view that the panoramic camera can cover; the pixel size refers to the number of pixels used to form a panoramic bird's-eye view of the examination room, such as 2560*2560.

[0061] It can be understood that since the determination of the required field of view angle needs to be based on the real-world coordinate system, step S221 is performed to convert the image coordinates, i.e., the center point position coordinates, into real-world coordinates, i.e., the actual physical coordinates, thereby avoiding the problem of inaccurate positioning due to coordinate system mismatch, thereby achieving accurate conversion of image coordinates to actual physical coordinates in the examination environment.

[0062] Exemplarily, the maximum field of view of the panoramic camera is obtained and the pixel size of the panoramic view of the examination room ( w,h ), the center point coordinate position ( x,y ) to convert the actual physical coordinate position ( , ):

[0063]

[0064] in, is the horizontal angle between the target object and the center point of the panoramic bird's-eye view of the examination room, is the vertical angle between the target object and the center point of the panoramic view of the examination room ( ).

[0065] Step S222, calculating the actual distance from the target object to the panoramic camera based on the actual physical coordinate position and the distance from the panoramic camera to the plane where the target object is located; It should be noted that the actual distance refers to the straight-line distance from the panoramic camera to the target object, which is calculated through geometric relationships and actual physical coordinates.

[0066] It can be understood that in order to accurately adjust the field of view angle of the camera according to the distance from the target object, step S222 is performed, which can avoid the problem of mismatch of the adjusted field of view angle due to errors in the actual distance, and provide effective and reliable data support for the precise adjustment of the field of view angle of the close-up camera lens.

[0067] For example, based on the actual physical coordinate position of the target object ( , ) and the distance from the panoramic camera to the plane where the target object is located H , the actual distance from the target object to the panoramic camera is calculated by the following formula: d :

[0068] Step S223, determining the circumscribed circle of the target object, and calculating the field of view angle according to the radius of the circumscribed circle and the actual distance.

[0069] It should be noted that the circumscribed circle refers to a circle that can completely surround the target object, and its radius is the farthest distance from the center point of the target object to its edge.

[0070] It is understandable that, in the process of determining the required field of view angle, the actual size of the target object is often overlooked, resulting in the close-up camera after adjusting the field of view angle may not fully capture the target object. Therefore, step S223 is performed to introduce the circumscribed circle of the target object to effectively include the actual size of the target object, thereby avoiding incomplete image capture or excessive enlargement due to field of view angle mismatch, and realizing precise adjustment of the field of view angle of the close-up camera, ensuring that the target object is complete and clear in the captured image.

[0071] For example, after determining the circumscribed circle of the target object, according to the radius of the circumscribed circle r The actual distance from the target object to the panoramic camera d , calculate the field of view angle required for the close-up camera to focus on the target object :

[0072] In this embodiment, geometric calculations and optical adjustments are performed to avoid capture quality problems caused by mismatch between image coordinates and actual physical coordinates, inaccurate measurement of target object distance, and improper setting of field of view angles. Accurate conversion from image coordinates to actual physical coordinates, accurate calculation of the actual distance between the target object and the camera, and automatic adjustment of the field of view angle according to the size and distance of the target object are achieved, thereby achieving accurate focusing of the target object during capture, efficient capture of high-quality images of the target object, and improving the automation and accuracy of the overall marking process.

[0073] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 5 After step S30, the multi-target capturing method in the examination environment further includes steps S41-S42: Step S41, performing corner cutting detection on the captured target image to obtain a detection result; It should be noted that corner cutting detection refers to a method of analyzing the captured target image (i.e., close-up view) to detect whether there are any missing corners of the test paper in the image.

[0074] It is understandable that after the initial capture, there may still be missing corners in the captured image due to different angles of the test paper image, so step S41 is performed to perform corner cutting detection on the close-up view captured by the close-up camera. This can avoid the problem of obstruction of the marking process due to incomplete capture, and achieve effective identification of quality problems of the captured image, providing an effective judgment basis for subsequent processing of the missing corner cutting problem.

[0075] Step S42, based on the detection result, the rotation angle or zoom ratio of the close-up camera is polynomially adjusted, and based on the polynomially adjusted close-up camera, the step of capturing the target object is returned to be executed.

[0076] It is understandable that since the initial capture may not fully meet the image quality requirements, step S42 is performed to avoid obtaining a close-up view with quality problems after capturing by re-adjusting the rotation angle or zoom ratio of the close-up camera, thereby ensuring that the final image meets the accuracy and quality requirements of the marking.

[0077] In a feasible implementation manner, the step of polyphonically adjusting the rotation angle or zoom ratio of the close-up camera based on the detection result in step S42 may include steps S421-S422: Step S421, when the detection result is that the target image has both upper and lower cut corners and / or left and right cut corners, reducing the zoom ratio of the close-up camera to obtain a polyphonic close-up camera; It can be understood that, since the target image has cut angles in relative directions, it means that the zoom ratio of the close-up camera lens is too large, so that the target object fails to fully enter the field of view of the lens. Therefore, step S421 is performed. By reducing the zoom ratio of the close-up camera, the problem of the target object failing to fully enter the field of view of the lens can be avoided, ensuring that the entire target object can fully enter the field of view of the lens, thereby achieving the effect of fully presenting the target object in the field of view.

[0078] Exemplarily, when the detection result is that the target image has both upper and lower cut corners and / or left and right cut corners, the zoom ratio of the current close-up camera is reduced by n times (n=0.85~0.9) to obtain a polyphonic close-up camera.

[0079] Step S422, when the detection result is that the target image has any one of upper and lower cut angles and / or any one of left and right cut angles, the rotation angle of the close-up camera is adjusted in the direction of the cut angle to obtain a polyphonic close-up camera.

[0080] It can be understood that since the target image does not have cut angles in relative directions at the same time, but only has cut angles in any direction, it means that the rotation direction of the close-up camera cannot meet the current position of the target object, so step S422 is performed. By adjusting the rotation direction of the close-up camera accordingly, it is possible to avoid the problem that the target object fails to fully enter the field of view of the lens, thereby ensuring that the entire target object can fully enter the field of view of the lens, thereby achieving the effect of fully presenting the target object in the field of view.

[0081] Exemplarily, when the detection result is that the target image has an upper cut corner, the rotation angle of the close-up camera is adjusted in the direction of the upper cut corner to obtain a polyphonic close-up camera; when the detection result is that the target image has an upper cut corner and a left cut corner, the rotation angle of the close-up camera is adjusted in the direction of the upper cut corner and the direction of the left cut corner, respectively, to obtain a polyphonic close-up camera.

[0082] In this embodiment, the close-up camera is adjusted differently when different cutting angles exist. That is, when the target image has a cutting angle in a relative direction, the image integrity is ensured by reducing the zoom ratio; when there is a cutting angle in a single direction, the image integrity is ensured by adjusting the rotation angle. This avoids the problem of difficulty in capturing the complete target object, realizes automatic optimization and correction of the image, and achieves the effect of improving the image acquisition quality, ensuring the integrity and accuracy of the image information, and enhancing the automation and efficiency of the remote marking system.

[0083] In this embodiment, by performing quality detection on the captured target image and automatically adjusting the shooting parameters of the close-up camera accordingly based on the detection results, the problem of image loss due to the capture process is avoided, and accurate readjustment of the close-up camera is achieved, thereby ensuring the integrity of the target image finally captured, achieving the effect of improving image acquisition quality, optimizing the marking workflow and enhancing the overall efficiency of the remote marking system.

[0084] In a feasible implementation manner, after step S10, the multi-target capturing method in the examination environment further includes step S101: Step S101 , statistically analyzing the coordinate positions of each center point to obtain a capture order of each target object captured by the close-up camera, so as to capture each target object based on the capture order.

[0085] It should be noted that the capture order refers to the order in which the close-up camera captures multiple target objects based on the statistical analysis results of the coordinate positions of the center points of the target objects.

[0086] It is understandable that, since in the process of automated marking, it is necessary to efficiently capture multiple target objects in sequence, and statistical analysis can optimize the capture path and reduce unnecessary mechanical movement, performing step S101 can avoid the waste of time and inefficiency caused by disordered capture, and achieve efficient and orderly capture of the target objects, thereby improving the efficiency of capturing the target objects.

[0087] For example, please refer to Figure 6 , Figure 6 It represents the order (from 1 to 20) in which the close-up camera captures the 20 test papers in the examination room after statistically analyzing the coordinate positions of the center points of each test paper using a greedy algorithm.

[0088] In this implementation, by statistically analyzing the coordinate positions of each center point, a series of problems such as repeated capture, missed capture, or invalid operation caused by disordered or random capture are avoided, and the capture path of the close-up camera is optimized. Through this optimization, it is ensured that the close-up camera captures each target object in the shortest path and the most efficient order, thereby achieving the effect of improving the automation of the remote marking system, reducing the capture time, and improving the overall work efficiency.

[0089] For example, in order to help understand the implementation process of the multi-target capture method in the examination environment obtained by combining this embodiment with the above-mentioned embodiment 1, please refer to Figure 7 , Figure 7 A brief flowchart of a multi-target capture method in an examination environment is provided, specifically: First, the coordinate position of the center point of each target object in the panoramic bird's-eye view of the examination room taken by the panoramic camera is detected, and the capture order of the close-up camera is determined based on the position. After that, the required rotation angle and field angle of each target object for the close-up camera to capture are calculated in sequence according to the capture order, and the target object is captured based on the calculated rotation angle and field angle. Then, the captured target image is subjected to angle cutting detection. If it is detected that the target image does not have angle cutting, the target image is determined to be an image that can be used by the marking system; if it is detected that the target image has angle cutting, the rotation angle and field angle (scaling ratio) of the close-up camera are polyphonically adjusted, and the target object is captured again based on the polyphonically adjusted close-up camera.

[0090] For further information, please refer to Figure 8 , Figure 8 A schematic flow chart of a multi-target capture method in an examination environment is provided, specifically: First, the main thread and algorithm detection are performed simultaneously. In the main thread, the video stream of the close-up shot and the video stream of the panoramic lens are obtained in a loop. During the algorithm detection process, the test paper frame (i.e., the target object) in the panoramic overhead view of the examination room is detected by the panoramic camera. After detecting that the table and the test paper are normal and the video stream is obtained at this time, it is determined whether the host computer has turned on the capture function. When this function is turned on, the center position (i.e., the center point coordinate position) and the radius r of the circumscribed circle of each test paper are calculated according to the detection frame in the panoramic overhead view of the examination room, and the angles of rotation of the close-up shot in the horizontal and vertical directions (i.e., the horizontal rotation angle and the vertical rotation angle) are calculated according to the center position of each test paper and the camera installation height (i.e., the distance from the panoramic camera to the plane where the target object is located) are calculated. The distance d from the camera to the center of the desktop test paper (i.e., the actual distance from the target object to the panoramic camera) is then calculated by the distance d and the radius r of the circumscribed circle. In addition, the optimal acquisition path (i.e., the capture order) of N tables can be calculated by the greedy algorithm, thereby completing the efficient capture of all table areas. If the capture function is abnormal or interrupted, the task is terminated; if the capture function is normal, the capture task is repeated.

[0091] For further information, please refer to Fig. 9 , Fig. 9 The close-up frame image on the left in the middle is a display of the target image captured by the close-up camera based on the panoramic frame image on the right, and T is the same test paper (dashed frame) on the same desktop (solid frame) photographed by the panoramic camera and the close-up camera.

[0092] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the multi-target capture method in the examination environment of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0093] This application also provides a multi-target capture device in an examination room environment, please refer to Fig.10 The multi-target capture device in the examination room environment is applied to a multi-target capture system, wherein the multi-target capture system includes a binocular camera, the binocular camera includes a panoramic camera and a close-up camera, and the multi-target capture device in the examination room environment includes: The detection module 10 is used to detect the coordinate position of the center point of each target object in the panoramic bird's-eye view of the examination room taken by the panoramic camera; A determination module 20, for determining, for any target object, based on the coordinate position of the center point of the target object, a rotation angle of the close-up camera and a field of view angle required for the close-up camera to focus on the target object; The adjustment module 30 is used to adjust the close-up camera according to the angle to be rotated and the field of view, and to capture the target object through the adjusted close-up camera.

[0094] Optionally, the angle to be rotated includes a horizontal angle to be rotated and a vertical angle to be rotated, and the determination module 20 is further used to: Calculate the horizontal rotation angle of the close-up camera and the vertical rotation angle of the close-up camera based on the coordinate position of the center point; The center point coordinate position is converted into an actual physical coordinate position, and the field of view angle required for the close-up camera to focus on the target object is calculated based on the actual physical coordinate position.

[0095] Optionally, the determining module 20 is further configured to: Acquire the maximum field angle of the panoramic camera and the pixel size of the panoramic bird's-eye view of the examination room, and convert the coordinate position of the center point according to the maximum field angle and the pixel size to obtain the actual physical coordinate position; Calculate the actual distance from the target object to the panoramic camera based on the actual physical coordinate position and the distance from the panoramic camera to the plane where the target object is located; A circumscribed circle of the target object is determined, and the field of view angle is calculated according to the radius of the circumscribed circle and the actual distance.

[0096] Optionally, the adjustment module 30 is further used for: Calculating a step value of the motor according to the angle to be rotated and a transmission ratio between the close-up camera and the motor, and executing the step value through the motor to adjust the rotation angle of the close-up camera; Determining a lens zoom value corresponding to the field of view angle based on a preset functional relationship, and adjusting a zoom ratio of the close-up camera according to the lens zoom value; The target object is captured by a close-up camera with an adjusted rotation angle and zoom ratio.

[0097] Optionally, the adjustment module 30 is further used for: Performing corner cutting detection on the captured target image to obtain the detection result; The rotation angle or zoom ratio of the close-up camera is polyphonically adjusted based on the detection result, and the step of capturing the target object is executed based on the polyphonic close-up camera returning.

[0098] Optionally, the adjustment module 30 is further used for: When the detection result shows that the target image has both upper and lower cut corners and / or left and right cut corners, reducing the zoom ratio of the close-up camera to obtain a polyphonic close-up camera; When the detection result is that the target image has any one of upper and lower cut angles and / or any one of left and right cut angles, the rotation angle of the close-up camera is adjusted in the direction of the cut angle to obtain a polyphonic close-up camera.

[0099] Optionally, the detection module 10 is further used for: The coordinate positions of each center point are statistically analyzed to obtain a capture order in which the close-up camera captures each target object, so as to capture each target object based on the capture order.

[0100] The multi-target capture device in the examination room environment provided by the present application adopts the multi-target capture method in the examination room environment in the above-mentioned embodiment, which can solve the technical problem of how to efficiently and reliably scan the examination paper during the remote marking process. Compared with the prior art, the beneficial effects of the multi-target capture device in the examination room environment provided by the present application are the same as the beneficial effects of the multi-target capture method in the examination room environment provided by the above-mentioned embodiment, and the other technical features of the multi-target capture device in the examination room environment are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0101] The present application provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the multi-target capture method in the examination environment in the above-mentioned embodiment one.

[0102] Reference below Fig.11 , which shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present application. The electronic devices in the embodiments of the present application may include but are not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions: tablet computers), PMPs (Portable Media Players: portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig.11 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0103] like Fig.11As shown, the electronic device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the electronic device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows an electronic device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0104] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0105] The electronic device provided by the present application adopts the multi-target capture method in the examination room environment in the above embodiment, which can solve the technical problem of how to efficiently and reliably scan the examination paper during the remote examination. Compared with the prior art, the beneficial effects of the electronic device provided by the present application are the same as the beneficial effects of the multi-target capture method in the examination room environment provided by the above embodiment, and the other technical features in the electronic device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0106] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0107] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0108] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, the computer-readable program instructions being used to execute the multi-target capturing method in an examination environment in the above-mentioned embodiment.

[0109] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0110] The computer-readable storage medium may be included in the electronic device, or may exist independently without being installed in the electronic device.

[0111] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by an electronic device, the electronic device: detects the center point coordinate position of each target object in the panoramic overhead view of the examination room taken by the panoramic camera; for any target object, based on the center point coordinate position of the target object, determines the rotation angle of the close-up camera and the field of view angle required for the close-up camera to focus on the target object; adjusts the close-up camera according to the rotation angle and the field of view angle, and captures the target object through the adjusted close-up camera.

[0112] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0113] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0114] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0115] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the multi-target capture method in the above-mentioned examination room environment, and can solve the technical problem of how to efficiently and reliably scan the examination paper during the remote examination. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the multi-target capture method in the examination room environment provided by the above-mentioned embodiment, and will not be elaborated here.

[0116] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the multi-target capture method in an examination environment as described above.

[0117] The computer program product provided by the present application can solve the technical problem of how to efficiently and reliably scan the test paper during the remote marking process. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the multi-target capture method in the examination room environment provided by the above embodiment, which will not be elaborated here.

[0118] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A multi-target capture method in an examination environment, characterized in that: Applied to a multi-target capture system, wherein the multi-target capture system includes a binocular camera, the binocular camera includes a panoramic camera and a close-up camera, and the multi-target capture method in the examination room environment includes: Detect the coordinate position of the center point of each target object in the panoramic bird's-eye view of the examination room taken by the panoramic camera; For any target object, based on the coordinate position of the center point of the target object, determine the angle to be rotated of the close-up camera and the field of view angle required for the close-up camera to focus on the target object; The close-up camera is adjusted according to the angle to be rotated and the field of view, and the target object is captured by the adjusted close-up camera.

2. The multi-target capture method in an examination environment as claimed in claim 1, characterized in that: The angle to be rotated includes a horizontal angle to be rotated and a vertical angle to be rotated. The step of determining the angle to be rotated of the close-up camera and the field of view angle required for the close-up camera to focus on the target object based on the coordinate position of the center point of the target object includes: Calculate the horizontal rotation angle of the close-up camera and the vertical rotation angle of the close-up camera based on the coordinate position of the center point; The center point coordinate position is converted into an actual physical coordinate position, and the field of view angle required for the close-up camera to focus on the target object is calculated based on the actual physical coordinate position.

3. The multi-target capture method in an examination room environment as claimed in claim 2, characterized in that: The step of converting the center point coordinate position into an actual physical coordinate position, and calculating the field of view angle required for the close-up camera to focus on the target object based on the actual physical coordinate position comprises: Acquire the maximum field angle of the panoramic camera and the pixel size of the panoramic bird's-eye view of the examination room, and convert the coordinate position of the center point according to the maximum field angle and the pixel size to obtain the actual physical coordinate position; Calculate the actual distance from the target object to the panoramic camera based on the actual physical coordinate position and the distance from the panoramic camera to the plane where the target object is located; A circumscribed circle of the target object is determined, and the field of view angle is calculated according to the radius of the circumscribed circle and the actual distance.

4. The multi-target capture method in an examination environment as claimed in claim 1, characterized in that: The close-up camera is driven by a motor to rotate, and the steps of adjusting the close-up camera according to the to-be-rotated angle and the field of view angle, and capturing the target object by using the adjusted close-up camera include: Calculating a step value of the motor according to the angle to be rotated and a transmission ratio between the close-up camera and the motor, and executing the step value through the motor to adjust the rotation angle of the close-up camera; Determining a lens zoom value corresponding to the field of view angle based on a preset functional relationship, and adjusting a zoom ratio of the close-up camera according to the lens zoom value; The target object is captured by a close-up camera with an adjusted rotation angle and zoom ratio.

5. The multi-target capture method in an examination environment as claimed in claim 1, characterized in that: After the step of capturing the target object by the adjusted close-up camera, the following step is further included: Perform corner cutting detection on the captured target image to obtain the detection result; The rotation angle or zoom ratio of the close-up camera is polyphonically adjusted based on the detection result, and the step of capturing the target object is executed based on the polyphonic close-up camera returning.

6. The multi-target capture method in an examination environment as claimed in claim 5, characterized in that: The step of polynomially adjusting the rotation angle or zoom ratio of the close-up camera based on the detection result comprises: When the detection result shows that the target image has both upper and lower cut corners and / or left and right cut corners, reducing the zoom ratio of the close-up camera to obtain a polyphonic close-up camera; When the detection result is that the target image has any one of upper and lower cut angles and / or any one of left and right cut angles, the rotation angle of the close-up camera is adjusted in the direction of the cut angle to obtain a polyphonic close-up camera.

7. The multi-target capture method in an examination environment as claimed in claim 1, characterized in that: After the step of detecting the coordinate position of the center point of each target object in the panoramic bird's-eye view of the examination room taken by the panoramic camera, the method further includes: The coordinate positions of each center point are statistically analyzed to obtain a capture order in which the close-up camera captures each target object, so as to capture each target object based on the capture order.

8. A multi-target capture device in an examination environment, characterized in that: Applied to a multi-target capture system, wherein the multi-target capture system includes a binocular camera, the binocular camera includes a panoramic camera and a close-up camera, and the multi-target capture device in the examination room environment includes: A detection module is used to detect the coordinate position of the center point of each target object in the panoramic bird's-eye view of the examination room taken by the panoramic camera; A determination module, for determining, for any target object, based on the coordinate position of the center point of the target object, the angle to be rotated of the close-up camera and the field of view angle required for the close-up camera to focus on the target object; The adjustment module is used to adjust the close-up camera according to the angle to be rotated and the field of view, and to capture the target object through the adjusted close-up camera.

9. An electronic device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the multi-target capturing method in an examination environment as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the multi-target capture method in an examination environment as described in any one of claims 1 to 7 are implemented.

Images