Intelligent safety helmet wearing detection method and system based on multi-algorithm fusion

Abstract

The invention relates to the technical field of computer vision, in particular to an intelligent safety helmet wearing detection method and system based on multi-algorithm fusion, and the method comprises the steps: obtaining safety helmet wearing image data; performing preprocessing based on the acquired image data, including performing image denoising on the acquired image, enhancing the image through Laplacian sharpening, and adjusting an image pixel value range through normalization; carrying out target detection according to the preprocessed image data, carrying out image feature extraction by using a target detection result, and carrying out helmet wearing correctness judgment based on image feature extraction, including angle calculation, symmetry analysis and wearing gap detection according to the extracted image features; according to the method, the safety helmet wearing correctness is comprehensively judged from the three aspects of angle calculation, symmetry analysis and wearing gap detection, and the accuracy of judging the safety helmet wearing correctness is improved through multi-dimensional judgment.

Description

Technical Field

[0001] The present invention relates to the field of computer vision technology, and in particular to an intelligent helmet wearing detection method and system based on multi-algorithm fusion. Background Art

[0002] In many industrial fields such as construction, mining, and power operations, the safety of construction workers is of vital importance. Safety helmets are important equipment to protect the safety of construction workers' heads, and their correct wearing plays a key role in preventing safety accidents. Traditional safety helmet wearing inspections mainly rely on manual inspections, which have many disadvantages. On the one hand, manual inspections are inefficient and it is difficult to effectively supervise a large number of construction workers in real time. On the other hand, manual inspections are prone to omissions and inaccurate subjective judgments, and it is impossible to ensure that every construction worker wears a safety helmet correctly.

[0003] With the continuous development of science and technology, some sensor-based helmet detection technologies have gradually emerged. However, these technologies also have certain limitations. Sensors may be disturbed by the environment, such as strong vibrations, electromagnetic interference, etc., which will affect the accuracy of detection. Moreover, relying solely on sensors can only detect whether the helmet is worn. The ability to judge whether the helmet is worn correctly, such as whether the chin strap is fastened, whether the helmet is worn correctly, and the fit between the helmet and the head, is limited. In addition, in the field of image recognition technology, although there have been some attempts to apply it to safety monitoring and other aspects, the application of intelligent helmet wearing correctness detection is not mature enough. At present, there is a lack of an effective solution that can comprehensively utilize image recognition technology to accurately judge the correctness of helmet wearing from multiple dimensions. At the same time, in the construction environment, the lighting conditions are complex and changeable, and the movements and postures of construction workers are different, which brings great challenges to the detection of the correctness of helmet wearing. At this stage, a smart helmet wearing detection method and system based on multi-algorithm fusion is needed. Summary of the invention

[0004] In order to solve the problems of low accuracy in traditional helmet wearing detection and the detection method being easily disturbed by the external environment, the present invention provides an intelligent helmet wearing detection method and system based on multi-algorithm fusion.

[0005] In the first aspect, the present invention provides an intelligent helmet wearing detection method based on multi-algorithm fusion, which adopts the following technical solution: An intelligent helmet wearing detection method based on multi-algorithm fusion, comprising: Acquire image data of helmet wearing; Preprocessing is performed based on the acquired image data, including image denoising and image enhancement through Laplace sharpening, and image pixel value range is adjusted through normalization; Perform object detection based on preprocessed image data, including helmet detection using the YOLO and Faster R-CNN fusion algorithm; Using the target detection results to extract image features, including using edge detection algorithms to extract edge features; Judging the correctness of helmet wearing based on image feature extraction, including angle calculation, symmetry analysis and wearing gap detection based on the extracted image features; The result is output based on the correctness judgment.

[0006] Furthermore, the image denoising and Laplace sharpening enhancement of the acquired image include weighted averaging of the image data using Gaussian filtering, determining a neighborhood with each pixel in the image as the center, multiplying the pixel value in the neighborhood with the value of the corresponding position of the Gaussian kernel and summing them to obtain a new value of the pixel, and finally calculating the Laplace operator of the image and adding it to the original image, thereby enhancing the edge of the image.

[0007] Furthermore, the use of the YOLO and Faster R-CNN fusion algorithm to detect the helmet includes using the YOLO algorithm to divide the input image data into multiple grids, predicting a bounding box and a corresponding category probability and confidence based on the grids, calculating a confidence score based on an intersection-and-union ratio of the predicted bounding box to the true bounding box, setting a confidence threshold and determining the area where the helmet is located based on the confidence score.

[0008] Furthermore, the use of the YOLO and Faster R-CNN fusion algorithm to detect the helmet also includes inputting the area where the helmet is located, which is screened by the YOLO algorithm, into the region proposal network of Faster R-CNN to generate a candidate area, and performing classification and bounding box regression according to the candidate area, wherein the classification uses a cross entropy loss function, and the bounding box regression uses a Smooth L1 loss function, and the performance of the classification and bounding box regression is optimized by minimizing the total loss function.

[0009] Furthermore, the method of using the YOLO and Faster R-CNN fusion algorithm to detect the helmet also includes obtaining a confidence score for each detection result from the YOLO and Faster R-CNN algorithms respectively, setting a weight coefficient according to the confidence score, calculating a final confidence score using the weight coefficient, setting a confidence threshold and determining the location of the area where the helmet is located according to the final confidence score.

[0010] Furthermore, the angle calculation, symmetry analysis and wearing gap detection are performed based on the extracted image features, including determining the point coordinates on the edge contour based on the acquired edge features, calculating the second-order moment matrix of the edge contour using the point coordinates, calculating the eigenvalues ​​and eigenvectors based on the matrix, taking the eigenvector with the largest eigenvalue as the main axis direction, and performing angle calculation based on the main axis direction.

[0011] Furthermore, the angle calculation, symmetry analysis and wearing gap detection based on the extracted image features also include dividing the image for determining the position of the helmet area into left and right equal parts, calculating the SSIM values ​​of the left and right parts of the image, determining the symmetry of the left and right parts of the image based on the SSIM values, calculating the shortest distance between the helmet and the head using a distance transformation algorithm, setting a distance threshold and comparing it with the shortest distance.

[0012] In the second aspect, an intelligent helmet wearing detection system based on multi-algorithm fusion includes: The data acquisition module is configured to: acquire image data of helmet wearing; A preprocessing module is configured to: perform preprocessing based on the acquired image data, including image denoising on the acquired image and enhancing the image through Laplace sharpening, and adjusting the image pixel value range through normalization; The detection module is configured to: perform target detection based on the preprocessed image data, including helmet detection using the YOLO and Faster R-CNN fusion algorithm; The feature extraction module is configured to: extract image features using the target detection result, including extracting edge features using an edge detection algorithm; The judgment module is configured to: judge the correctness of wearing the helmet based on image feature extraction, including angle calculation, symmetry analysis and wearing gap detection according to the extracted image features; The output module is configured to output the result according to the correctness judgment.

[0013] In a third aspect, the present invention provides a computer-readable storage medium storing a plurality of instructions, wherein the instructions are suitable for being loaded and executed by a processor of a terminal device, for example, a smart helmet wearing detection method based on multi-algorithm fusion.

[0014] In a fourth aspect, the present invention provides a terminal device comprising a processor and a computer-readable storage medium, wherein the processor is used to implement various instructions; the computer-readable storage medium is used to store multiple instructions, wherein the instructions are suitable for being loaded by the processor and executing the method for detecting the wearing of an intelligent helmet based on multi-algorithm fusion.

[0015] In summary, the present invention has the following beneficial technical effects: 1. The present invention combines the fast detection capability of the YOLO algorithm and the high-precision detection capability of the Faster R-CNN algorithm, which can more accurately identify the helmet and determine its position and size, and reduce false detections and missed detections based on the confidence score and the final confidence score of the fusion algorithm.

[0016] 2. The present invention comprehensively uses a variety of advanced image processing and analysis algorithms, including Gaussian filtering, Laplace sharpening, YOLO and Faster R-CNN fusion algorithms, edge detection algorithms, etc. The combination of these algorithms enables the system to adapt to different image qualities, lighting conditions and construction environments, thereby improving the robustness and adaptability of the system.

[0017] 3. The present invention comprehensively judges the correctness of helmet wearing from three aspects: angle calculation, symmetry analysis and wearing gap detection. The second-order moment calculation of the main axis direction can accurately judge the inclination angle of the helmet; the structural similarity index SSIM can analyze the symmetry of the helmet, and the distance transformation algorithm can detect the gap between the helmet and the head. The multi-dimensional judgment improves the accuracy of the judgment on the correctness of helmet wearing. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a schematic diagram of the overall process of an intelligent helmet wearing detection method based on multi-algorithm fusion according to an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The present invention is further described in detail below in conjunction with the accompanying drawings.

[0020] Example 1 Reference Figure 1 , a smart helmet wearing detection method based on multi-algorithm fusion in this embodiment includes: Acquire image data of helmet wearing; Preprocessing is performed based on the acquired image data, including image denoising and image enhancement through Laplace sharpening, and image pixel value range is adjusted through normalization; Perform object detection based on preprocessed image data, including helmet detection using the YOLO and Faster R-CNN fusion algorithm; Using the target detection results to extract image features, including using edge detection algorithms to extract edge features; Judging the correctness of helmet wearing based on image feature extraction, including angle calculation, symmetry analysis and wearing gap detection based on the extracted image features; The result is output based on the correctness judgment.

[0021] Specifically, a smart helmet wearing detection method based on multi-algorithm fusion includes the following steps: like Figure 1 As shown, S1, obtaining image data of helmet wearing; Install high-definition cameras on the top and sides of the smart helmet to ensure that the shooting angle is a low angle. This installation method can clearly cover the construction workers' head area and fully obtain image information of the construction workers wearing helmets. The camera collects images of the construction workers' heads in real time at a low angle. The low-angle shooting allows the image to simultaneously present the helmet, chin strap and the construction workers' heads, providing rich information for subsequent image processing and analysis.

[0022] S2, performing preprocessing based on the acquired image data, including image denoising on the acquired image and enhancing the image through Laplace sharpening, and adjusting the image pixel value range through normalization; For the acquired helmet wearing image data, Gaussian filtering and denoising are first performed, and the two-dimensional Gaussian function formula is: , in, are pixel coordinates, is the standard deviation, which controls the width of the Gaussian kernel. , the new value after Gaussian filtering: , in, is the original image pixel value, Determines the size of the neighborhood, is the Gaussian kernel in In this way, each pixel in the image is weighted averaged to remove noise interference, and then the Laplace operator of the image is calculated. The discrete form of the Laplace operator can be expressed as: , in, is the pixel in the image The grayscale value of the pixel is obtained by calculating the difference between the grayscale values ​​of the pixel and its four neighboring pixels. The Laplace operator value of the pixel is added to the original image to obtain the image after Laplace sharpening: , in, is the original image pixel value, is the weight coefficient, the weight coefficient Used to control the degree of sharpening. Larger values ​​will result in more pronounced sharpening effects, but may cause the image to appear over-sharpened, with noise and artifacts. The smaller the value, the weaker the sharpening effect. Through Laplace sharpening, the edge information of the image can be enhanced, making the outline of the helmet clearer and the features more obvious. Finally, the normalization operation is performed to change the pixel value range of the original image from Linearly map to the interval [0,1] by subtracting the minimum pixel value , the pixel value range can be shifted to a non-negative interval. Then, the pixel value range is scaled to the [0,1] interval by dividing it by the difference between the maximum pixel value and the minimum pixel value. The normalization process makes different images comparable, thus completing the image preprocessing.

[0023] S3, performing target detection based on the preprocessed image data, including helmet detection using the YOLO and Faster R-CNN fusion algorithm; In order to improve the accuracy and efficiency of helmet detection, the YOLO and Faster R-CNN fusion algorithm is used to detect helmets. The input image data is divided into Each grid is responsible for predicting the target object that is inside it or has a large overlap with it. For each grid, multiple bounding boxes and corresponding category probabilities and confidences are predicted. The bounding box contains information about the location and size of the target object, using the center coordinates of the bounding box , width w and height h, for each bounding box, the confidence score is: , in, Indicates whether there is a target object, i.e. a helmet, in the grid. If it exists, it is 1; if not, it is 0. The intersection-over-union ratio of the predicted bounding box and the true bounding box, that is, the area of ​​the intersection of the two bounding boxes divided by the area of ​​the union, is set. The confidence threshold is set between 0.5 and 0.9. The area where the helmet is located is determined according to the confidence score. If the confidence score of a grid is higher than the threshold, it is considered that there is a helmet in the grid, and it is further processed as a candidate area. The area where the helmet is located filtered out by the YOLO algorithm is input into the region proposal network (RPN) of Faster R-CNN. Faster R-CNN consists of the region proposal network (RPN) and Fast R-CNN. RPN is used to generate candidate areas that may contain targets. Fast R-CNN classifies and regresses these candidate areas. RPN is a fully convolutional network that slides a small window on the input feature map. At each sliding position, RPN simultaneously predicts multiple candidate areas of different scales and proportions. For the candidate areas generated by RPN, classification and bounding box regression are performed. Classification is to determine whether the candidate area contains a helmet and what type of helmet it is. Bounding box regression is to fine-tune the position and size of the candidate area. The bounding box regression uses the Smooth L1 loss function. , the Smooth L1 loss function can be expressed as: , in, are the predicted bounding box parameters (center coordinates x, y, width w and height h), are the true bounding box parameters, , By minimizing the total loss function , to optimize the performance of classification and bounding box regression, where Expressed as a cross entropy loss function, the confidence score of each detection result is obtained from the YOLO and Faster R-CNN algorithms respectively. Assume that the confidence score of YOLO for a certain detection result is , the confidence score of Faster R-CNN is , set the weight coefficient according to the confidence score and , calculate the final confidence score , the location of the area where the helmet is located is determined according to the final confidence score.

[0024] S4, extracting image features using the target detection results, including extracting edge features using an edge detection algorithm; After obtaining the target detection results, the detected helmet area is used as the focus area for subsequent processing. The gradient amplitude and direction of the image are calculated using the first-order partial derivative finite difference. The gradient amplitude reflects the drastic degree of pixel value change in the image, while the gradient direction indicates the direction of pixel value change. By calculating the gradient, it can be determined which areas of the image have large pixel value changes. These areas are likely to be the edges of the object. For each pixel, its gradient amplitude is the square root of the sum of the squares of the horizontal and vertical gradient components, and the gradient direction is the inverse tangent value of the vertical gradient component and the horizontal gradient component. After calculating the gradient amplitude and direction, non-maximum suppression is performed. The purpose of this step is to refine the edge and remove those pixels that are not local maxima. In the gradient direction, the gradient amplitude of the current pixel is compared with that of the adjacent pixel points, only the local maximum is retained, and the non-maximum points are suppressed, which can make the edge clearer and more accurate. Set the high threshold and the low threshold, and determine the pixel points with a gradient amplitude greater than the high threshold as strong edge points, and the pixel points with a gradient amplitude between the high threshold and the low threshold as weak edge points. Then, the final edge image is formed by connecting the strong edge points and the weak edge points adjacent to the strong edge points. This can prevent some weaker but possibly true edge pixels from being completely ignored while retaining the obvious edges. The chin strap can be separated from the background using edge features. Since the chin strap usually has obvious edge features, the position of the chin strap can be easily identified through edge detection. Then, a shape analysis algorithm such as Hough transform is used to identify the shape of the chin strap. If the edge features of the chin strap are clear and the shape conforms to the tightened state, the chin strap can be considered to be tightened.

[0025] S5. Judging the correctness of helmet wearing based on image feature extraction, including angle calculation, symmetry analysis and wearing gap detection according to the extracted image features; By calculating the second-order moment matrix of the edge contour of the helmet in the image, the main axis direction of the helmet is determined, and then the tilt angle of the helmet is obtained. The second-order moment matrix reflects the distribution of points on the edge contour. Its eigenvalues ​​and eigenvectors can reveal the main direction information of the image. First, the edge contour of the helmet in the image is determined, and the point coordinates on the edge contour are set to , calculate the second-order moment matrix: , Each of these items is obtained by summing the coordinates of the points on the edge contour, and then calculating the eigenvalues ​​of the matrix M and , and the corresponding eigenvectors are and The direction determined by the eigenvector with a larger eigenvalue is considered to be the main axis direction. The tilt angle of the helmet can be calculated through the angle between the main axis direction and the horizontal direction.

[0026] Set an angle threshold, such as ±5 degrees. If the calculated tilt angle of the helmet is within this threshold range, it can be considered that the helmet is worn correctly; if it exceeds this range, it is considered that the helmet is not worn correctly.

[0027] After that, a symmetry analysis is performed, dividing the image of the helmet into two parts, and then the similarity of the two parts is measured by calculating the structural similarity index (SSIM). SSIM comprehensively considers the similarity of the image from three aspects: brightness, contrast and structure, and can more accurately judge the symmetry of the helmet.

[0028] Divide the image of the helmet into two parts, left and right, respectively, and calculate the SSIM value: , in, and are the means of image x and y, respectively, reflecting the average brightness of the image, and are the variances of image x and y, respectively, reflecting the degree of brightness change of the image, is the covariance of images x and y, reflecting the correlation between images, , is a constant used to avoid the situation where the denominator is zero. The SSIM values ​​of the left and right parts are calculated. If the SSIM value is high, it means that the left and right parts are highly similar, and it can be considered that the helmet is worn correctly. If the SSIM value is low, it is considered that the helmet is not worn correctly.

[0029] Finally, the fit between the helmet and the head is judged. The helmet and head areas are separated by segmenting the preprocessed image, and then the distance transform algorithm is used to calculate the shortest distance between the helmet and the head to judge the fit between the two. The preprocessed image is segmented to obtain a binary image, and the value of the foreground pixel (helmet or head) is set to 0, and the value of the background pixel is set to infinity.

[0030] For pixel points (i, j) and (x, y), the distance between them is: , Starting from the foreground pixel point, the distance value is gradually propagated to the surrounding background pixel points until all the pixel points are assigned values, and the shortest distance between the helmet and the head is calculated. A distance threshold is set, which is 5 mm in this embodiment. If the calculated distance is less than this threshold, it can be considered that the helmet fits tightly to the head; if the distance is greater than this threshold, it is considered that there is a gap between the helmet and the head.

[0031] S6. Output the result according to the correctness judgment; Through steps S1-S5, including image preprocessing, target detection, image feature extraction and helmet wearing correctness judgment, the correctness judgment result of the helmet wearing is obtained. The smart helmet is equipped with a small speaker, which gives a sound prompt when the helmet is not worn correctly.

[0032] Example 2 The difference between this embodiment and embodiment 1 is that this embodiment provides an intelligent helmet wearing detection system based on multi-algorithm fusion, including: The data acquisition module is configured to: acquire image data of helmet wearing; A preprocessing module is configured to: perform preprocessing based on the acquired image data, including image denoising on the acquired image and enhancing the image through Laplace sharpening, and adjusting the image pixel value range through normalization; The detection module is configured to: perform target detection based on the preprocessed image data, including helmet detection using the YOLO and Faster R-CNN fusion algorithm; The feature extraction module is configured to: extract image features using the target detection result, including extracting edge features using an edge detection algorithm; The judgment module is configured to: judge the correctness of wearing the helmet based on image feature extraction, including angle calculation, symmetry analysis and wearing gap detection according to the extracted image features; The output module is configured to output the result according to the correctness judgment.

[0033] A computer-readable storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded and executed by a processor of a terminal device, for example, a smart helmet wearing detection method based on multi-algorithm fusion.

[0034] A terminal device includes a processor and a computer-readable storage medium, wherein the processor is used to implement various instructions; the computer-readable storage medium is used to store multiple instructions, wherein the instructions are suitable for being loaded and executed by the processor to implement a smart helmet wearing detection method based on multi-algorithm fusion.

[0035] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent helmet wearing detection method based on multi-algorithm fusion, characterized in that: include: Acquire image data of helmet wearing; Preprocessing is performed based on the acquired image data, including image denoising and image enhancement through Laplace sharpening, and image pixel value range is adjusted through normalization; Perform object detection based on preprocessed image data, including helmet detection using the YOLO and Faster R-CNN fusion algorithm; Using the target detection results to extract image features, including using edge detection algorithms to extract edge features; Judging the correctness of helmet wearing based on image feature extraction, including angle calculation, symmetry analysis and wearing gap detection based on the extracted image features; The result is output based on the correctness judgment.

2. According to the method of intelligent helmet wearing detection based on multi-algorithm fusion according to claim 1, it is characterized in that: The method of denoising the acquired image and enhancing the image through Laplace sharpening includes performing weighted averaging on the image data using Gaussian filtering, determining a neighborhood with each pixel in the image as the center, multiplying and summing the pixel values ​​in the neighborhood with the values ​​at the corresponding position of the Gaussian kernel to obtain a new value of the pixel, and finally calculating the Laplace operator of the image and adding it to the original image, thereby enhancing the edge of the image.

3. According to the method of intelligent helmet wearing detection based on multi-algorithm fusion according to claim 2, it is characterized in that: The method uses the YOLO and Faster R-CNN fusion algorithm to detect the helmet, including using the YOLO algorithm to divide the input image data into multiple grids, predicting bounding boxes and corresponding category probabilities and confidences according to the grids, calculating the confidence score according to the intersection and union ratio of the predicted bounding box and the real bounding box, setting the confidence threshold and judging the area where the helmet is located according to the confidence score.

4. According to the method of intelligent helmet wearing detection based on multi-algorithm fusion according to claim 3, it is characterized in that: The method uses the YOLO and Faster R-CNN fusion algorithm to detect the helmet, and also includes inputting the area where the helmet is located, which is screened by the YOLO algorithm, into the region proposal network of Faster R-CNN to generate a candidate area, and performing classification and bounding box regression according to the candidate area, wherein the classification uses a cross entropy loss function, and the bounding box regression uses a Smooth L1 loss function, and the performance of the classification and bounding box regression is optimized by minimizing the total loss function.

5. According to the method of intelligent helmet wearing detection based on multi-algorithm fusion according to claim 4, it is characterized in that: The method of using the YOLO and Faster R-CNN fusion algorithm to detect the helmet also includes obtaining a confidence score for each detection result from the YOLO and Faster R-CNN algorithms respectively, setting a weight coefficient according to the confidence score, calculating a final confidence score using the weight coefficient, setting a confidence threshold and determining the location of the area where the helmet is located according to the final confidence score.

6. The intelligent helmet wearing detection method based on multi-algorithm fusion according to claim 5 is characterized in that: The method performs angle calculation, symmetry analysis and wearing gap detection based on the extracted image features, including determining the point coordinates on the edge contour based on the acquired edge features, calculating the second-order moment matrix of the edge contour using the point coordinates, calculating the eigenvalues ​​and eigenvectors based on the matrix, taking the eigenvector with the largest eigenvalue as the main axis direction, and performing angle calculation based on the main axis direction.

7. The intelligent helmet wearing detection method based on multi-algorithm fusion according to claim 6 is characterized in that: The method performs angle calculation, symmetry analysis and wearing gap detection based on the extracted image features, and also includes dividing the image with the determined helmet area position into left and right equal parts, calculating the SSIM values ​​of the left and right parts of the image, determining the symmetry of the left and right parts of the image based on the SSIM values, calculating the shortest distance between the helmet and the head using a distance transformation algorithm, setting a distance threshold and comparing it with the shortest distance.

8. An intelligent helmet wearing detection system based on multi-algorithm fusion, characterized in that: include: The data acquisition module is configured to: acquire image data of helmet wearing; A preprocessing module is configured to: perform preprocessing based on the acquired image data, including image denoising on the acquired image and enhancing the image through Laplace sharpening, and adjusting the image pixel value range through normalization; The detection module is configured to: perform target detection based on the preprocessed image data, including helmet detection using a YOLO and FasterR-CNN fusion algorithm; The feature extraction module is configured to: extract image features using the target detection result, including extracting edge features using an edge detection algorithm; The judgment module is configured to: judge the correctness of wearing the helmet based on image feature extraction, including angle calculation, symmetry analysis and wearing gap detection according to the extracted image features; The output module is configured to output the result according to the correctness judgment.

9. A computer-readable storage medium storing a plurality of instructions, characterized in that: The instructions are suitable for being loaded by a processor of a terminal device and executing the intelligent helmet wearing detection method based on multi-algorithm fusion as described in claim 1.

10. A terminal device, comprising a processor and a computer-readable storage medium, wherein the processor is used to implement each instruction; and the computer-readable storage medium is used to store multiple instructions, characterized in that: The instructions are suitable for being loaded by a processor and executing the intelligent helmet wearing detection method based on multi-algorithm fusion as described in claim 1.

Images