Unmanned invigilation examination room examinee positioning method based on multiple cameras

Abstract

The invention provides an unattended invigilation examination room examinee positioning method based on multiple cameras, relates to the technical field of computer vision, and solves the technical problems that in the prior art, unattended invigilation mostly adopts a single-camera scheme and is only limited to single-view-angle image information, so that view angle blind areas, shielding problems and incomplete information occur when examinees are detected. According to the technical scheme, a plurality of monocular cameras at fixed positions are arranged, and all-directional coverage of the viewing angle of an examination room is achieved; according to the invention, three-dimensional positioning of examinees can be accurately realized by combining multiple frames of images with instance segmentation and depth estimation algorithms.

Description

Technical Field

[0001] The present invention relates to the field of computer vision technology, and in particular to a method for positioning examinees in an unmanned examination room based on multiple cameras. Background Art

[0002] In the modern examination environment, ensuring the fairness and security of the examination is an important challenge. Traditional manual proctoring methods have many limitations, such as high labor costs and limited monitoring range. With the development of computer vision technology, unmanned proctoring has become an important means to improve the efficiency and accuracy of examination management.

[0003] Existing unmanned invigilation systems mostly use a single camera solution, which is limited to image information from a single perspective, resulting in blind spots, occlusion problems, and incomplete information when detecting candidates. Especially in complex examination environments and when multiple candidates are taking the exam at the same time, a single camera is difficult to fully and accurately detect all candidates. On the other hand, the depth estimation accuracy of a single camera is limited and it is impossible to achieve three-dimensional positioning of candidates. Summary of the invention

[0004] Therefore, the present invention solves the technical problems that unmanned examination supervision in the prior art mostly adopts a single camera solution, which is limited to image information from a single perspective, resulting in blind spots in perspective, occlusion problems and incomplete information when detecting examinees; the present invention provides a method for positioning examinees in an unmanned examination room based on multiple cameras, which sets up multiple monocular cameras at fixed positions to achieve all-round coverage of the examination room perspective, and can accurately achieve three-dimensional positioning of examinees through multi-frame images combined with instance segmentation and depth estimation algorithms.

[0005] The inventive concept of the present invention is to achieve accurate three-dimensional positioning of the examinee through multiple steps. First, the left and right monocular cameras are fixed, and the intrinsic parameters, extrinsic parameters and relative extrinsic parameters of the camera are obtained through chessboard calibration. Subsequently, the collected images are preprocessed and instance segmented to remove low-confidence and repeated examinee masks to ensure the accuracy of examinee detection. Then, the ZoeDepth algorithm is used to estimate the depth of the examination room image, and the segmented examinee mask is converted into a three-dimensional point cloud. Finally, the examinees under the two cameras are matched through the matrix relationship between the cameras and the three-dimensional coordinates of the examinees are obtained.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical solution: a 3D examinee positioning method based on multiple fields of view in an examination room, comprising the following steps:

[0007] S1: The positions of two monocular cameras (left front and right front) are fixed, and the chessboard is placed in the field of view of the two cameras. The intrinsic parameters, extrinsic parameters and relative extrinsic parameters of the two monocular cameras are obtained by capturing the images of the calibration plate taken at different positions and directions;

[0008] S2: Perform image preprocessing operations on the examination room images captured by the left and right cameras, including image size unification, image pixel normalization and image denoising, converting the pixel value range, for example, converting the pixel value range from 0 to 255 to 0 to 1, and using a three-dimensional block matching filter algorithm for denoising. While retaining the original information of the examination room image, a series of noises (such as blackboard, etc.) in the image are filtered out, so that the processed examination room image is smoother;

[0009] S3: Perform instance segmentation on the examinees in the images captured by the left and right cameras, and perform deduplication processing on the generated examinee masks to achieve examinee identification and segmentation, ensuring the accuracy and uniqueness of the segmentation results;

[0010] S4: Use the ZoeDepth algorithm to estimate the depth of the captured left and right examination room images, and save the generated relative depth map in PFM format;

[0011] S5: Process the obtained examination room depth map and convert the examinees segmented from the left and right images into a three-dimensional point cloud through the camera internal reference;

[0012] S6: Calculate the center position of the point cloud of each examinee segmented from the left and right images, and optimize the center position;

[0013] S7: Convert the point cloud of the right camera to the coordinate system of the left camera, match the point clouds of the examinees under the left and right cameras, and obtain the three-dimensional coordinates of each examinee.

[0014] Furthermore, the specific steps of step S1 are as follows:

[0015] S11: placing a checkerboard in the left front and right front fields of view of the two cameras, and capturing images of the checkerboard from multiple angles to ensure that the checkerboard is clearly visible at different positions and angles;

[0016] S12: read the checkerboard images taken by each camera through the OpenCV computer vision library, detect the corner points (feature points) of the checkerboard in each image, and calculate the intrinsic parameter K, rotation matrix R and translation vector T of each camera;

[0017] S13: Calculate the relative external parameters of the two cameras through a pair of checkerboard images taken by the two cameras to obtain the relative rotation matrix R between the two cameras rel and the relative translation vector T rel .

[0018] Furthermore, the specific steps of step S3 are as follows:

[0019] S31: Read the examination room images captured by the left and right cameras and perform instance segmentation to obtain the mask, label and confidence score of each detected examinee, filter out examinee instances with a confidence score lower than 0.5, and select only examinee masks and corresponding confidence scores from the filtered results to ensure that only examinee instances with higher confidence are retained;

[0020] S32: Use the improved IoU algorithm to calculate the IoU between masks and retain the candidate masks with high confidence and no duplication;

[0021] S33: Create a completely black background of the same size as the original image, superimpose the mask onto the background, and use random colors to display the masked area, then save each individual mask image for individual inspection and verification of each candidate's mask;

[0022] S34: All the deduplicated candidate masks are superimposed on the original image one by one, and different mask areas are distinguished by different colors, so that different detected candidates can be clearly distinguished in the final image.

[0023] Furthermore, the specific steps of step S5 are as follows:

[0024] S51: reading depth data from the obtained relative depth map, and converting the estimated relative depth information into actual depth information by multiplying the scaling factor;

[0025] S52: The depth value of each pixel is converted into three-dimensional point cloud data through the camera internal reference, and the invalid point cloud data is filtered out through the candidate mask segmented by instance segmentation, and only the candidate's point cloud data is retained.

[0026] Furthermore, the specific steps of step S6 are as follows:

[0027] S61: Calculate the spatial position mean of all points in the point cloud corresponding to each candidate, and determine the initial center position of each point cloud;

[0028] S62: Calculate the Euclidean distance from each point in the point set to the center position;

[0029] S63: Find the 20% points with the longest distance and then remove these outliers;

[0030] S64: Repeat the process from S61 to S63 multiple times, and further remove outliers in each iteration;

[0031] S65: Calculate and save the final point cloud center position.

[0032] Furthermore, the specific steps of step S7 are as follows:

[0033] S71: transforming the point cloud of the right camera into the coordinate system of the left camera according to the relative extrinsic parameter matrix calibrated in step S1;

[0034] S72: If the number of point cloud instances of the examinee detected by the left and right cameras is the same, all point clouds in the converted left camera coordinate system are paired, and the average position of the center point of each pair of matched point clouds is calculated through the center point of each point cloud optimized in step S6, and the output is the three-dimensional coordinates of the examinee;

[0035] S73: If the number of candidate point cloud instances detected by the left and right cameras is different, then in the converted left camera coordinate system, for the point cloud in the original left camera coordinate system, find the nearest point cloud from the original right camera point cloud converted to this coordinate system as the matching target, and calculate the average position of the center point of each pair of optimized point clouds, and output it as the three-dimensional coordinates of the candidate.

[0036] Furthermore, the specific steps of step S32 are as follows:

[0037] S321: Calculate the improved IoU, taking into account whether one mask is mostly contained in the other mask;

[0038] S322: Arrange the masks in descending order according to the confidence score of each mask, and then calculate the IoU between each mask and other masks one by one. When the IoU value exceeds a threshold, such as 0.5, these masks are repeated and deduplication is performed.

[0039] Furthermore, the specific steps of step S7 are as follows:

[0040] S71: transforming the point cloud of the right camera into the coordinate system of the left camera according to the relative extrinsic parameter matrix calibrated in step S1;

[0041] S72: When the number of point cloud instances of the examinee detected by the left and right cameras is the same, all point clouds in the converted left camera coordinate system are paired, and the average position of the center point of each pair of matched point clouds is calculated through the center point of each point cloud optimized in step S6, and the output is the three-dimensional coordinates of the examinee;

[0042] S73: When the number of candidate point cloud instances detected by the left and right cameras is different, in the converted left camera coordinate system, for the point cloud in the original left camera coordinate system, find the nearest point cloud from the original right camera point cloud converted to this coordinate system as the matching target, and calculate the average position of the center point of each pair of optimized point clouds, and output it as the three-dimensional coordinates of the candidate.

[0043] Furthermore, the specific process of step S321 is as follows:

[0044] S3211: Calculate the intersection and union between masks:

[0045] The intersection computes the overlapping portion of two masks:

[0046] Intersection=∑(mask1∩mask2)

[0047] Union computes the union of two masks:

[0048] Union=∑(mask1∪mask2)

[0049] The standard IoU calculation formula is:

[0050]

[0051] S3212: Calculate coverage:

[0052] Coverage measures the amount of overlap one mask has within another mask:

[0053] Coverage of mask 1:

[0054]

[0055] Coverage of mask 2:

[0056]

[0057] S3213: When the coverage of a mask is greater than 80%, it means that the mask is mostly contained by another mask. At this time, the value with higher coverage is used as the improved IoU value:

[0058] Improved IoU=max(Coverage1,Coverage2)

[0059] Otherwise, return the standard IoU value:

[0060] Improved IoU=Standard IoU.

[0061] Further, the specific process of step S322 is as follows:

[0062] S3221: Sort masks according to confidence scores;

[0063] S3222: Use the improved IoU algorithm to calculate the IoU value of each mask with other masks. When the IoU exceeds a threshold, such as 0.5, these masks are marked as duplicates and masks with lower confidence are removed.

[0064] S3223: Keep the candidate mask after deduplication.

[0065] Compared with the prior art, the present invention has the following advantages:

[0066] 1. The method for positioning examinees in an unmanned examination room based on multiple cameras provided by the present invention uses an improved IoU algorithm to calculate the IoU value between masks, thereby enhancing the accuracy of examinee detection.

[0067] 2. The method for positioning examinees in an unmanned examination room based on multiple cameras provided by the present invention realizes the matching and positioning of examinees under multiple monocular cameras, thereby improving the intelligence level of the unmanned examination room.

[0068] 3. The method for positioning examinees in an unsupervised examination room based on multiple cameras provided by the present invention solves the problem that a single camera cannot fully detect all examinees, and realizes the precise positioning of examinees in an unsupervised examination room. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0070] Figure 1 The present invention provides a flow chart of a method for positioning examinees in an unsupervised examination room based on multiple cameras. DETAILED DESCRIPTION

[0071] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0072] Example 1

[0073] This embodiment is a specific application of the method for locating examinees in an unmanned examination room based on multiple cameras. Figure 1 As shown, the present invention discloses a method for positioning examinees in an unmanned examination room based on multiple cameras, and the specific steps are as follows:

[0074] Step 1): Place the calibration plate (chessboard) in the field of view of two cameras (front left and front right). To ensure calibration accuracy, the calibration plate should be clearly visible at different positions and angles. The camera captures images of the calibration plate at different angles to capture enough checkerboard feature points. These images are used to calculate the camera's intrinsic parameters, extrinsic parameters, and relative extrinsic parameters;

[0075] Step 2): Use the OpenCV library to read the calibration images taken by each camera and detect the corners (feature points) of the chessboard in each image. This is achieved through the function cv2.findChessboardCorners, which returns the sub-pixel coordinates of each corner point on the chessboard;

[0076] Step 3): Use OpenCV's cv2.calibrateCamera function to read the checkerboard images taken by each camera, detect the corner points (feature points) of the checkerboard in each image, and calculate the intrinsic parameters K, rotation matrix R, and translation vector T of each camera.

[0077] Step 4): Calculate the relative external parameters (relative rotation matrix and relative translation vector) between the two cameras through a pair of checkerboard images taken by the two cameras. These external parameters can be calculated through the rotation and translation relationship between the two cameras. The relative transformation relationship can be expressed as:

[0078] P left =R rel ×P right +T rel

[0079] Among them, P left It represents the three-dimensional point coordinates in the left camera coordinate system, P right It represents the three-dimensional point coordinates in the right camera coordinate system;

[0080] Step 5): Use OpenCV's cv2.resize function to unify the size of the images captured by the left and right cameras to ensure that the subsequent image analysis steps are performed at the same resolution;

[0081] Step 6): Convert the pixel value range from 0 to 255 to 0 to 1 to achieve the purpose of standardizing the input data. The data normalization formula is as follows:

[0082]

[0083] Among them, I represents the original data, I normalized represents the normalized data, min(I) and max(I) represent the minimum and maximum values ​​in data set I, respectively;

[0084] Step 7): Use the three-dimensional block matching filter algorithm to denoise the image, and filter out a series of noises (such as blackboards, trash cans, etc.) in the image while retaining the original information of the examination room image as much as possible. The BM3D algorithm uses the self-similarity of the image to separate noise and real signals, thereby improving the clarity and quality of the image;

[0085] Step 8): Read the examination room images captured by the left and right cameras, perform instance segmentation on the images, and obtain the mask, label, and confidence score of each detected examinee. Filter out instances with confidence scores lower than 0.5 and retain examinee instances with high confidence scores to ensure the reliability and accuracy of the segmentation results;

[0086] Step 9): Use the improved IoU algorithm to calculate the IoU value between masks, remove repeated candidate masks, and retain high-confidence and non-repeated candidate masks. The specific steps are as follows:

[0087] Step 9-1): Calculate the improved IoU, taking into account whether one mask is mostly contained in the other mask. The specific process is as follows:

[0088] Step 9-1-1): Calculate the intersection and union between masks:

[0089] Intersection calculates the overlapping part of two masks:

[0090] Intersection=∑(mask1∩mask2)

[0091] Union computes the union of two masks:

[0092] Union=∑(mask1∪mask2)

[0093] The standard IoU calculation formula is:

[0094]

[0095] Step 9-1-2): Calculate coverage:

[0096] Coverage is used to measure the overlap ratio of one mask in another mask:

[0097] Coverage of mask 1:

[0098]

[0099] Coverage of mask 2:

[0100]

[0101] Step 9-1-3): If the coverage of a mask is greater than 80%, it means that the mask is mostly contained by another mask. At this time, use the value with higher coverage as the improved IoU value:

[0102] ImprovedIoU=max(Coverage1,Coverage2)

[0103] Otherwise, return the standard IoU value:

[0104] ImprovedIoU=StandardIoU

[0105] Step 9-2): According to the confidence score of each mask, they are arranged in descending order, and then their IoU with other masks are calculated one by one. If the IoU exceeds the threshold (0.5), these masks are considered to be duplicates and are removed. The specific process is as follows:

[0106] Step 9-2-1): In order to avoid low-confidence masks covering or interfering with high-confidence masks, the masks are sorted in descending order according to their confidence scores to ensure that masks with high confidence are retained first during the deduplication process.

[0107] Step 9-2-2): Use the improved IoU algorithm to calculate the IoU value of each mask with other masks one by one. If the IoU value of two masks exceeds the preset threshold (0.5), these masks are considered to be highly similar and one of the masks is marked as duplicate for removal;

[0108] Step 9-2-3): Return the candidate mask retained after deduplication. The deduplication mask will reduce the interference of repeated testing and improve the reliability of the overall test results.

[0109] Step 10): Use the ZoeDepth algorithm to estimate the depth of the captured left and right examination room images, and save the generated relative depth map in PFM format. The ZoeDepth algorithm uses the MiDaS encoding-decoding architecture, performs relative depth pre-training through multiple data sets, and learns depth features from images of multiple scenes (indoor and outdoor), but these depths are relative depths, that is, the depth of each pixel is only consistent with the depth of other pixels in the image, and does not have an absolute unit of measurement. Step 11): Convert the obtained relative depth information of the examination room into actual depth information, and convert the examinees segmented from the left and right images into a three-dimensional point cloud through the camera's intrinsic reference. The specific steps are as follows:

[0110] Step 11-1): Read the depth data from the relative depth map obtained by the ZoeDepth algorithm, and convert the estimated relative depth information into actual depth information by multiplying the scaling factor. The formula is as follows:

[0111] D actual =D relative ×scale

[0112] Where D actual is the actual depth, D relative is the relative depth, and scale is the scaling factor.

[0113] Step 11-2): Convert the depth value of each pixel into three-dimensional point cloud data through the camera internal reference, and filter out invalid point cloud data based on the candidate mask segmented by instance segmentation, and only retain the point cloud data of the candidate captured in the left and right screens.

[0114] Step 12): Calculate the point cloud center position of each candidate instance segmented from the left and right images, and continuously optimize the center position. The specific steps are as follows:

[0115] Step 12-1): Calculate the spatial position mean of all points in the point cloud corresponding to each candidate and determine the initial center position of each point cloud;

[0116] Step 12-2): Calculate the distance from each point (x, y, z) in each point cloud to the center position (x center ,y center ,z center ) is calculated as follows:

[0117]

[0118] Step 12-3): Find the 20% of points with the longest distance, and then remove these outliers, leaving only the 80% of points that are closer to the center of the point cloud;

[0119] Step 12-4): Update the point set to remove outliers;

[0120] Step 12-5): Repeat the above process 5 times, further eliminating outliers in each iteration;

[0121] Step 12-6): Calculate and save the final point cloud center position.

[0122] Step 13): Convert the point cloud of the right camera to the coordinate system of the left camera, match the point clouds of the candidates under the left and right cameras, and obtain the three-dimensional coordinates of each candidate. The specific steps are as follows:

[0123] Step 13-1): transform the point cloud of the right camera into the coordinate system of the left camera according to the relative extrinsic parameter matrix calibrated in step 4);

[0124] Step 13-2): If the number of point cloud instances of the examinee detected by the left and right cameras is the same, all point clouds in the converted left camera coordinate system are paired, and the average position of the center point of each pair of matched point clouds is calculated through the center point of each point cloud optimized in step 12), and the output is the three-dimensional coordinates of the examinee;

[0125] Step 13-3): If the number of candidate point cloud instances detected by the left and right cameras is different, then in the converted left camera coordinate system, for the point cloud in the original left camera coordinate system, find the nearest point cloud from the original right camera point cloud converted to this coordinate system as the matching target, and calculate the average position of the center point of each pair of optimized point clouds, and output it as the three-dimensional coordinates of the candidate.

[0126] Obviously, the above embodiments are merely examples for the purpose of clear explanation, and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived therefrom are still within the scope of protection of the invention.

Claims

1. A method for positioning examinees in an unmanned examination room based on multiple cameras, characterized in that: The steps include: S1: The positions of the two monocular cameras are fixed, and the chessboard is placed in the field of view of the two cameras. The intrinsic parameters, extrinsic parameters and relative extrinsic parameters of the two monocular cameras are obtained by capturing the images of the calibration plate taken at different positions and directions; S2: Perform image preprocessing operations on the examination room images captured by the left and right cameras, including image size unification, image pixel normalization and image denoising, converting the pixel value range, and using a three-dimensional block matching filter algorithm for denoising, filtering out a series of noises in the image while retaining the original information of the examination room image; S3: Perform instance segmentation on the examinees in the images captured by the left and right cameras, and perform deduplication processing on the generated examinee masks to achieve examinee recognition and segmentation; S4: Use the ZoeDepth algorithm to estimate the depth of the captured left and right examination room images, and save the generated relative depth map in PFM format; S5: Process the obtained examination room depth map and convert the examinees segmented from the left and right images into a three-dimensional point cloud through the camera internal reference; S6: Calculate the center position of the point cloud of each examinee segmented from the left and right images, and optimize the center position; S7: Convert the point cloud of the right camera to the coordinate system of the left camera, match the point clouds of the examinees under the left and right cameras, and obtain the three-dimensional coordinates of each examinee.

2. The method for positioning examinees in an unmanned examination room based on multiple cameras according to claim 1, characterized in that: The specific steps of step S1 are as follows: S11: placing a checkerboard in the left front and right front fields of view of the two cameras, and capturing images of the checkerboard from multiple angles; S12: read the checkerboard images taken by each camera through the OpenCV computer vision library, detect the corner points of the checkerboard in each image, and calculate the intrinsic parameter K, rotation matrix R and translation vector T of each camera; S13: Calculate the relative external parameters of the two cameras through a pair of checkerboard images taken by the two cameras to obtain the relative rotation matrix R between the two cameras rel and the relative translation vector T rel .

3. The method for positioning examinees in an unmanned examination room based on multiple cameras according to claim 1 is characterized in that: The specific steps of step S3 are as follows: S31: Read the examination room images captured by the left and right cameras and perform instance segmentation to obtain the mask, label and confidence score of each detected examinee, filter out examinee instances with a confidence score lower than 0.5, and select only examinee masks and corresponding confidence scores from the filtered results to ensure that only examinee instances with higher confidence are retained; S32: Use the improved IoU algorithm to calculate the IoU between masks and retain the candidate masks with high confidence and no duplication; S33: Create a completely black background of the same size as the original image, superimpose the mask onto the background, and use random colors to display the masked area, then save each individual mask image for individual inspection and verification of each candidate's mask; S34: All the removed duplicate candidate masks are superimposed on the original image one by one, and different colors are used to distinguish different mask areas.

4. The method for positioning examinees in an unmanned examination room based on multiple cameras according to claim 1 is characterized in that: The specific steps of step S5 are as follows: S51: reading depth data from the obtained relative depth map, and converting the estimated relative depth information into actual depth information by multiplying the scaling factor; S52: The depth value of each pixel is converted into three-dimensional point cloud data through the camera internal reference, and the invalid point cloud data is filtered out through the candidate mask segmented by instance segmentation, and only the candidate's point cloud data is retained.

5. The method for positioning examinees in an unmanned examination room based on multiple cameras according to claim 1 is characterized in that: The specific steps of step S6 are as follows: S61: Calculate the spatial position mean of all points in the point cloud corresponding to each candidate, and determine the initial center position of each point cloud; S62: Calculate the Euclidean distance from each point in the point set to the center position; S63: Find the 20% points with the longest distance and then remove these outliers; S64: Repeat the process from S61 to S63 multiple times, and further remove outliers in each iteration; S65: Calculate and save the final point cloud center position.

6. The method for positioning examinees in an unmanned examination room based on multiple cameras according to claim 1 is characterized in that: The specific steps of step S7 are as follows: S71: transforming the point cloud of the right camera into the coordinate system of the left camera according to the relative extrinsic parameter matrix calibrated in step S1; S72: If the number of point cloud instances of the examinee detected by the left and right cameras is the same, all point clouds in the converted left camera coordinate system are paired, and the average position of the center point of each pair of matched point clouds is calculated through the center point of each point cloud optimized in step S6, and the output is the three-dimensional coordinates of the examinee; S73: If the number of candidate point cloud instances detected by the left and right cameras is different, then in the converted left camera coordinate system, for the point cloud in the original left camera coordinate system, find the nearest point cloud from the original right camera point cloud converted to this coordinate system as the matching target, and calculate the average position of the center point of each pair of optimized point clouds, and output it as the three-dimensional coordinates of the candidate.

7. The method for positioning examinees in an unmanned examination room based on multiple cameras according to claim 2 is characterized in that: The specific steps of step S32 are as follows: S321: Calculate the improved IoU, taking into account whether one mask is mostly contained in the other mask; S322: Arrange the confidence scores of each mask in descending order, and then calculate the IoU between each mask and other masks one by one. When the IoU value exceeds the threshold, these masks are repeated and deduplication is performed.

8. The method for positioning examinees in an unmanned examination room based on multiple cameras according to claim 1 is characterized in that: The specific steps of step S7 are as follows: S71: transforming the point cloud of the right camera into the coordinate system of the left camera according to the relative extrinsic parameter matrix calibrated in step S1; S72: When the number of point cloud instances of the examinee detected by the left and right cameras is the same, all point clouds in the converted left camera coordinate system are paired, and the average position of the center point of each pair of matched point clouds is calculated through the center point of each point cloud optimized in step S6, and the output is the three-dimensional coordinates of the examinee; S73: When the number of candidate point cloud instances detected by the left and right cameras is different, in the converted left camera coordinate system, for the point cloud in the original left camera coordinate system, find the nearest point cloud from the original right camera point cloud converted to this coordinate system as the matching target, and calculate the average position of the center point of each pair of optimized point clouds, and output it as the three-dimensional coordinates of the candidate.

9. The method for positioning examinees in an unmanned examination room based on multiple cameras according to claim 7 is characterized in that: The specific process of step S321 is as follows: S3211: Calculate the intersection and union between masks: The intersection computes the overlapping portion of two masks: Intersection=∑(mask1∩mask2) Union computes the union of two masks: Union=∑(mask1∪mask2) The standard IoU calculation formula is: S3212: Calculate coverage: Coverage measures the amount of overlap one mask has within another mask: Coverage of mask 1: Coverage of mask 2: S3213: When the coverage of a mask is greater than 80%, it means that the mask is mostly contained by another mask. At this time, the value with higher coverage is used as the improved IoU value: Improved IoU=max(Coverage1,Coverage2) Otherwise, return the standard IoU value: Improved IoU=Standard IoU.

10. The method for positioning examinees in an unmanned examination room based on multiple cameras according to claim 7, characterized in that: The specific process of step S322 is as follows: S3221: Sort masks according to confidence scores; S3222: Use the improved IoU algorithm to calculate the IoU value of each mask with other masks. When the IoU exceeds the threshold, these masks are marked as duplicates and masks with lower confidence are removed; S3223: Keep the candidate mask after deduplication.

Images