Safety protector wearing management method and device, equipment and storage medium

Abstract

The invention discloses a wearing management method and device of a safety protector, equipment and a storage medium, and relates to the technical field of electric digital data processing. According to the method, the target detection algorithm is improved, and the human body key point detection algorithm is fused to detect each area with one safety protector, so that compared with the existing computer vision, the target vision detection is only carried out on the detection areas divided by the human body key point detection algorithm; compared with the prior art, all the models do not need to traverse the same whole image, the detection response time is obviously shortened, whether the safety protector is worn or not is judged according to the recognition condition of the sensing chip, misjudgment of existing computer vision on low-quality safety protector images (shielding, unclear, too large, too small and the like) is avoided, and the safety protector detection accuracy is improved. The computer vision is only used for identifying the detection area and is not used for identifying the safety protector, and then the sensing chip is used for matching the monitoring area to achieve the purpose of accurate identification.

Description

Technical Field

[0001] The present application relates to the technical field of electronic digital data processing, and in particular to a method, device, equipment and storage medium for managing the wearing of safety gear. Background Art

[0002] The construction industry is an important material production sector and one of the pillar industries of my country's national economy. It plays an important role in improving living conditions, improving infrastructure, absorbing labor employment, and promoting economic growth. With the continuous advancement of my country's urbanization process, the scale of construction projects will continue to expand. The quality and safety of construction cannot be taken lightly. Operation risks seriously threaten the lives of construction workers, so construction workers are required to wear corresponding safety gear in strict accordance with safety regulations, such as safety helmets and protective clothing.

[0003] Correctly wearing complete safety gear can effectively reduce physical injuries. However, during the actual construction process, some construction workers fail to wear safety gear properly or completely due to negligence or carelessness, which makes the construction workers always have safety hazards during the construction process.

[0004] Mainstream construction site safety supervision is based on manual supervision, which is not only time-consuming and labor-intensive, but also unable to monitor at any time whether construction workers are not wearing their helmets correctly or not wearing them at all, resulting in frequent safety accidents on construction sites. In addition, most construction sites only have clear requirements for wearing safety helmets, thus ignoring the protection of other parts of the construction workers' bodies.

[0005] At present, the computer vision detection method for safety gear is mainly focused on helmets. By embedding electronic tags and sensors on the helmets, real-time positioning and tracking are performed, and physical detection methods such as pressure, infrared beams, and thermals are used to confirm whether the helmet is being worn. This method is inefficient and costly. If it is applied to other safety gear, embedding electronic tags and sensors in other safety gear and establishing fixed data base stations will inevitably lead to high installation and maintenance costs. At the same time, the application method has many inconveniences, which is not conducive to actual large-scale promotion and use. Summary of the invention

[0006] The main purpose of this application is to provide a method, device, equipment and storage medium for managing the wearing of safety gear to solve the problem of difficult supervision of safety gear in the prior art.

[0007] In order to achieve the above objectives, this application provides the following technical solutions:

[0008] A wearing management method based on safety protective gear, the wearing management method is applied to a number of construction workers wearing safety protective gear in a preset construction site, all safety protective gears are embedded with a sensing chip, and the wearing management method comprises:

[0009] Step S1, in response to an entry signal of the construction site, obtaining a person detection frame matching the entry signal;

[0010] Step S2, obtaining the key points of the human body in the person detection frame by using a human body key point detection algorithm;

[0011] Step S3, defining a wearing torso category based on each type of safety gear, and classifying all human key points into all wearing torso categories through a classification algorithm;

[0012] Step S4, obtaining the maximum area enclosed by all key points of the human body in the current wearing torso category, and defining the maximum area as the detection area of ​​the current wearing torso category;

[0013] Step S5, sensing the chip positions and chip numbers of all the sensing chips through the external sensing terminal;

[0014] Step S6, determining whether the number of chips is greater than or equal to the preset number of construction requirements, if the number of chips is greater than or equal to the preset number of construction requirements, executing step S7;

[0015] Step S7, judging whether there is the sensing chip in each detection area according to the positions of all chips;

[0016] Step S8, marking the detection area without the sensing chip as a protective gear missing area;

[0017] Step S9, sending the protective gear missing area to the construction personnel and an external receiving end.

[0018] As a further improvement of the present application, step S1, in response to an entry signal of the construction site, obtaining a person detection frame matching the entry signal, includes:

[0019] Step S11, acquiring image data matching the entry signal through an external camera terminal;

[0020] Step S12, dividing the image data into a plurality of grids on average;

[0021] Step S13, detecting a plurality of prior frames based on all grids through the person detection model;

[0022] Step S14, defining the construction worker as having the highest confidence level;

[0023] Step S15, respectively obtain the confidence of each priori box, obtain the priori box with the largest confidence and mark it as the first-order bounding box;

[0024] Step S16, calculating the intersection-over-union ratio between the first-order bounding box and each other priori box;

[0025] Step S17, selecting a first-order bounding box whose intersection-over-union ratio is greater than or equal to a preset ratio threshold as a second-order bounding box;

[0026] Step S18, obtaining a second-order bounding box with the highest confidence and defining it as the person detection box.

[0027] As a further improvement of the present application, step S2, obtaining the key points of the human body in the person detection frame by using a human key point detection algorithm, includes:

[0028] Step S21, training the VGGNet convolutional network by using the preset OpenPose library to obtain a VGGNet prediction model;

[0029] Step S22, inputting each image data into the VGGNet prediction model to extract human body features;

[0030] Step S23, extracting a plane confidence map of the position of the human body part in the current image data through the first branch of the two-branch CNN model;

[0031] Step S24, extracting the plane affinity vector field of the human body part position in the current image data through the second branch in the two-branch CNN model;

[0032] Step S25, calculating the human body key points of the plane confidence map and the plane affinity vector field of the current image data through bipartite graph matching of the Hungarian algorithm.

[0033] As a further improvement of the present application, in step S3, a wearing torso category is defined based on each type of safety gear, and all key points of the human body are classified into all wearing torso categories through a classification algorithm, including:

[0034] Step S31, define the data set to be classified x={x1, x2, ..., x i ,…,x m}, where x i is the i-th human key point in the data set x to be classified, and m is the number of all human key points;

[0035] Step S32, defining a category set C = {y1, y2, ..., y j ,…,y n}, where y jis the jth wearing torso category in the category set C, and n is the number of all wearing torso categories;

[0036] Step S33, calculate the conditional probability of each human key point in each wearing torso category according to formula (1):

[0037]

[0038] Among them, P(x|y j ) is the conditional probability of the data set x to be classified under the j-th wearing trunk category; P(y j ) is the marginal probability of the j-th wearing torso category; P(x i |y j ) is the conditional probability of the i-th human body key point under the j-th wearing torso category;

[0039] Step S34, classify each human body key point into the wearing torso category with the highest conditional probability.

[0040] As a further improvement of the present application, the safety gear includes a helmet, protective clothing, gloves, protective pants, and protective shoes. Step S4, obtaining the maximum area enclosed by all key points of the human body in the current wearing torso category, and defining the maximum area as the detection area of ​​the current wearing torso category, includes:

[0041] Step S41, using a human key point detection algorithm to detect at least one key point on the head, at least one key point on each shoulder, at least one key point on each hand, at least one key point on each side of the hips, at least one key point on each knee, and at least one key point on each foot in each portrait data;

[0042] Step S42, defining the maximum area enclosed by all key points of the head as the detection area of ​​the helmet;

[0043] Step S43, defining the maximum area enclosed by all shoulder key points and all hip key points as the detection area of ​​the protective clothing;

[0044] Step S44, defining the maximum area enclosed by all the key points of the hand as the detection area of ​​the glove;

[0045] Step S45, defining the maximum area enclosed by all the key points of the hips, all the key points of the knees and all the key points of the feet as the detection area of ​​the protective pants;

[0046] Step S46, defining the maximum area enclosed by all the key points of the foot as the detection area of ​​the protective shoe.

[0047] As a further improvement of the present application, step S7, judging whether there is the sensing chip in each detection area according to the positions of all chips, then includes:

[0048] Step S10, if the sensing chip is present in each detection area, obtaining the entry timestamp information of the entry signal;

[0049] Step S20, loading the entry timestamp information into each sensor chip respectively;

[0050] Step S30, responding to an exit signal of the construction site and acquiring exit timestamp information of the exit signal;

[0051] Step S40, loading the exit timestamp information into each sensor chip respectively;

[0052] Step S50, obtaining the time difference between the exit timestamp information and the entry timestamp information of the current construction personnel;

[0053] Step S60, defining the time difference as the current construction personnel's entry time.

[0054] As a further improvement of the present application, in step S8, the detection area without the sensing chip is marked as a protective gear missing area, and then the following steps are included:

[0055] Step S100, determining whether the protective gear missing area is the detection area of ​​the helmet, if the protective gear missing area is the detection area of ​​the helmet, executing step S200;

[0056] Step S200, generating a helmet missing warning signal;

[0057] Step S300, sending the helmet missing warning signal to the construction worker and an external receiving end.

[0058] In order to achieve the above objectives, this application also provides the following technical solutions:

[0059] A wearing management device for safety gear, the wearing management device for safety gear is applied to the wearing management method as described above, and the wearing management device comprises:

[0060] A person detection frame acquisition module, configured to respond to an entry signal of the construction site and acquire a person detection frame matching the entry signal;

[0061] A human key point acquisition module, used to acquire the human key points in the person detection frame through a human key point detection algorithm;

[0062] The human body key point classification module is used to define a wearing torso category based on each safety protective gear, and classify all human body key points into all wearing torso categories through a classification algorithm;

[0063] A detection area definition module is used to obtain the maximum area enclosed by all key points of the human body in the current wearing torso category, and define the maximum area as the detection area of ​​the current wearing torso category;

[0064] A sensing chip sensing module is used to sense the chip positions and chip numbers of all sensing chips through an external sensing terminal;

[0065] The sensing chip determination module is used to determine whether the number of chips is greater than or equal to the preset number of construction requirements. If the number of chips is greater than or equal to the preset number of construction requirements, step S7 is executed;

[0066] A detection area judgment module, used to judge whether there is the sensing chip in each detection area according to the positions of all chips;

[0067] A protective gear missing area definition module, used to mark the detection area without the sensing chip as a protective gear missing area;

[0068] The protective gear missing area sending module is used to send the protective gear missing area to the construction personnel and an external receiving end.

[0069] In order to achieve the above objectives, this application also provides the following technical solutions:

[0070] An electronic device includes a processor and a memory coupled to the processor, wherein the memory stores program instructions that can be executed by the processor; when the processor executes the program instructions stored in the memory, the wearing management method of the safety gear as described above is implemented.

[0071] To achieve the above objectives, this application also provides the following technical solutions:

[0072] A storage medium stores program instructions, and when the program instructions are executed by a processor, the wearing management method of the safety gear as described above can be implemented.

[0073] The present application obtains a person detection frame that matches the entry signal of the construction site in response to the entry signal; obtains the human key points in the person detection frame through a human key point detection algorithm; defines a wearing torso category based on each type of safety protective gear, and classifies all human key points into all wearing torso categories through a classification algorithm; obtains the maximum area enclosed by all human key points in the current wearing torso category, and defines the maximum area as the detection area of ​​the current wearing torso category; senses the chip positions and chip numbers of all sensing chips through an external sensing end; determines whether the number of chips is greater than or equal to the preset construction requirement number, and if the number of chips is greater than or equal to the preset construction requirement number, determines whether there is a sensing chip in each detection area according to the positions of all chips; marks the detection area without a sensing chip as a protective gear missing area; and sends the protective gear missing area to construction personnel and an external receiving end. The present application improves the target detection algorithm and integrates the human key point detection algorithm to perform separate detection on each area that should have a type of safety protective gear. Compared with the existing computer vision, the present application only performs target visual detection on the detection area divided by the human key point detection algorithm. It does not require all models to traverse the same entire image separately, which significantly shortens the detection response time. At the same time, it determines whether the safety protective gear is worn based on the recognition of the sensing chip, avoiding the existing computer vision from misjudging low-quality safety protective gear images (occluded, unclear, too large, too small, etc.). The computer vision of the present application is only used to identify the detection area, not the safety protective gear, and the sensing chip is used to match the monitoring area to achieve the purpose of accurate identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 A schematic diagram of the process steps of an embodiment of the wearing management method of the safety protective gear of the present application;

[0075] Figure 2 This is a functional module diagram of an embodiment of a wearing management device for safety gear of the present application;

[0076] Figure 3 This is a schematic diagram of the structure of an embodiment of the electronic device of the present application;

[0077] Figure 4 This is a schematic diagram of the structure of an embodiment of the storage medium of the present application. DETAILED DESCRIPTION

[0078] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0079] The terms "first", "second" and "third" in this application are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Thus, the features defined as "first", "second" and "third" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. All directional indications in the embodiments of the present application (such as up, down, left, right, front, back...) are only used to explain the relative position relationship, movement, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication also changes accordingly. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or power device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or power devices.

[0080] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0081] like Figure 1 As shown, this embodiment provides an embodiment of a wearing management method based on safety protective gear. In this embodiment, the wearing management method is applied to a number of construction workers wearing safety protective gear in a preset construction site, and all safety protective gears are embedded with sensing chips.

[0082] Preferably, the sensing chip can be configured as a radio frequency transceiver chip, or as a wireless communication chip.

[0083] Specifically, the wearing management method includes:

[0084] Step S1, in response to an entry signal of a construction site, obtaining a person detection frame matching the entry signal.

[0085] Preferably, the entry signal of the construction site can be generated by checkpoint facilities such as gates, or it can be achieved by installing a positioning module, a wireless communication module, a Bluetooth module, etc. on the sensing chip, or it can be achieved by installing a target detection algorithm on the shooting end. It is existing technology to generate corresponding entry and exit signals for construction personnel entering and exiting the construction site. This embodiment is a conventional application for the aforementioned entry and exit signals, and the specific generation process is not repeated here.

[0086] Step S2, obtaining the key points of the human body in the person detection frame through a human body key point detection algorithm.

[0087] Step S3, defining a wearing torso category based on each type of safety gear, and classifying all human body key points into all wearing torso categories through a classification algorithm.

[0088] Step S4, obtaining the maximum area enclosed by all key points of the human body in the current wearing torso category, and defining the maximum area as the detection area of ​​the current wearing torso category.

[0089] Step S5, sensing the chip positions and chip numbers of all the sensing chips through the external sensing terminal.

[0090] Step S6, determining whether the number of chips is greater than or equal to the preset construction requirement number, if the number of chips is greater than or equal to the preset construction requirement number, executing step S7.

[0091] Step S7, judging whether there is a sensing chip in each detection area according to the positions of all chips.

[0092] Step S8, marking the detection area without the sensing chip as a protective gear missing area.

[0093] Step S9, sending the protective gear missing area to the construction workers and the external receiving end.

[0094] Furthermore, step S1, in response to an entry signal of the construction site, obtaining a person detection frame matching the entry signal, includes:

[0095] Step S11, acquiring image data matching the entry signal through an external camera terminal.

[0096] Step S12, dividing the image data into a plurality of grids on average.

[0097] Preferably, the size of the original picture of the image data may be adjusted to 448×448, and then the resized picture may be evenly divided into S×S (eg, 7×7) grids, and the size of each grid is 64×64.

[0098] Preferably, each grid is used to predict the coordinates and width and height of N detection boxes, as well as the confidence of each detection box, that is, each grid needs to predict N×(4+1) values.

[0099] Step S13, detecting a number of prior frames based on all grids through a person detection model.

[0100] Preferably, if the center of the object is located on a first grid, the grid is responsible for predicting the bounding box of the object.

[0101] Step S14, defining the construction personnel with the highest confidence.

[0102] Step S15, respectively obtain the confidence of each priori box, obtain the priori box with the largest confidence and mark it as the first-order bounding box.

[0103] Step S16, calculating the intersection-over-union ratio between the first-order bounding box and each other priori box.

[0104] Preferably, the intersection-over-union ratio is a ratio obtained by dividing the intersection of the optimal detection box and each bounding box by the union of the optimal detection box and each bounding box.

[0105] Step S17, selecting a first-order bounding box whose intersection-over-union ratio is greater than or equal to a preset ratio threshold as a second-order bounding box.

[0106] Preferably, the preset ratio threshold may be set to 0.5.

[0107] Step S18, obtaining a second-order bounding box with the highest confidence and defining it as a person detection box.

[0108] Preferably, the target detection algorithm can be implemented by target detection algorithms VJ, HOG, DPMDetector; deep learning two-stage target detection algorithms RCNN, SPPNet, FastRCNN, FasterRCNN; target detection trick algorithms FPN, CascadeRCNN; deep learning one-stage target detection algorithms Yolo, X, SSD, RetinaNet; deep learning anchor-free target detection algorithms CornerNet, CenterNet, FCOS; Transformer-based target detection algorithm DETR, etc.

[0109] It can be understood that each grid needs to predict N (x, y, w, h, confidence); where (x, y) is the offset of the center of the detection box relative to the grid, (w, h) is the ratio of the detection box to the above resized image, and (confidence) is the confidence of the grid, which takes a value of 1 or 0.

[0110] Preferably, the confidence level can be understood as whether there is a target in the current grid and the accuracy of the detection box.

[0111] For example: suppose there is an object in a resized image, and the width and height of the resized image are (w a ,h a )but:

[0112] Divide the image into 7×7 (S×S) grids evenly. There is a grid located at the center of the target. The coordinates of the grid are (x i ,y i ), let the coordinates of the center of the target be (x a ,y a ), the above offset (x b ,y b ):

[0113] Preferably, in actual detection, if the predicted detection box and the actual bounding box overlap perfectly, the intersection-and-union ratio is 1. In actual application, the intersection-and-union ratio can generally be set to 0.5 to determine whether the predicted bounding box is correct, and the more accurate the bounding box is, the more positively correlated it is with the intersection-and-union ratio.

[0114] Preferably, the YOLO algorithm also needs to train the detection frame to improve the accuracy of target detection.

[0115] Next, the training model is trained using a preset training set, and the weights and biases of the training model are iteratively adjusted a first preset number of times using a back propagation algorithm to reduce the value of the loss function of the training model.

[0116] Preferably, the loss function is as follows:

[0117]

[0118] in, is the indicator function of whether the j detection box of the i-th grid is responsible for the target, and its value is 1 or 0; x i ,y i 、w i 、h i , C i They correspond to the i-th (x, y, w, h, confidence) prediction value, that is, the N×(4+1) values ​​mentioned above.

[0119] It can be understood that the loss function includes the coordinate value deviation of the detection box, the confidence deviation, and the prediction probability deviation (or category deviation).

[0120] in, is the detection frame midpoint loss in the coordinate value deviation, is the loss of detection box width and height in coordinate value deviation, is the confidence deviation, is the deviation of the predicted probability (or class deviation).

[0121] Among them, λ coord is the positioning error penalty, generally λ coord =5;S 2 That is, the S×S grids mentioned above; B is the number of bounding boxes; and is the estimate of the horizontal and vertical coordinates of the midpoint of the i-th bounding box

[0122] value; and is the estimated value of the width and height of the i-th bounding box; C i is the confidence of the i-th bounding box; is the estimated value of the confidence of the i-th bounding box; noobj is the confidence prediction loss, usually λ noobj =0.5; p i (c) is the category probability of the i-th bounding box; is the estimated value of the category probability of the i-th bounding box; p i (c) with The c in it corresponds to classes.

[0123] It should be noted that since each grid does not necessarily contain a target, if there is no target in the grid, the value of (confidence) will be 0, making the gradient span in the subsequent back propagation algorithm too large, so λ is introduced coord To control the loss of the predicted position of the detection box, and introduce λ noobj Controls the loss of objects not existing in a single grid.

[0124] It should be noted that the meanings of all symbols in the extended content of the above YOLO algorithm are not interchangeable with other symbol meanings.

[0125] Furthermore, step S2, obtaining the key points of the human body in the person detection frame by using a human body key point detection algorithm, includes:

[0126] Step S21, training the VGGNet convolutional network by using the preset OpenPose library to obtain a VGGNet prediction model.

[0127] Step S22, input each image data into the VGGNet prediction model to extract human body features.

[0128] Step S23, extracting a planar confidence map of the position of the human body part in the current image data through the first branch in the two-branch CNN model.

[0129] Step S24, extracting the planar affinity vector field of the human body part position in the current image data through the second branch in the two-branch CNN model.

[0130] Step S25, calculating the human body key points of the plane confidence map and the plane affinity vector field of the current image data through bipartite graph matching of the Hungarian algorithm.

[0131] In simple terms, an image is input, features are extracted through a convolutional network to obtain a set of feature maps, and then it is divided into two branches, using a two-branch CNN network to extract Part Confidence Maps (plane confidence maps) and Part Affinity Fields (plane affinity vector fields); after obtaining the aforementioned PCMs and PAFs, the Part Association (key point set) is obtained through the Bipartite Matching (bipartite graph matching) of the Hungarian algorithm.

[0132] Preferably, the bipartite graph matching of the Hungarian algorithm refers to a directed graph G = (V, E) in which the vertex set V is divided into two independent sets U and And each edge (e = (u, w)) connects one end from U and one end from W, and the process of finding the maximum number of undirected edge pairs makes these edges have no intersections.

[0133] Among them, the bipartite graph matching steps of the Hungarian algorithm are as follows:

[0134] Construct an augmented matrix: Convert the graph into a weighted adjacency matrix, with each row representing a node in U and each column representing a node in W. If there is an edge (u, w), the corresponding matrix element is the weight of the edge; otherwise it is 0.

[0135] Initialization: Set all matches to unmatched and create an initial zero-filled augmented matrix.

[0136] Loop: Perform the following steps until an exact match is found or no more pairs can be found.

[0137] Solve linear programming: Use Huffman coding or the shortest augmenting path algorithm to find a minimum augmenting path, which starts from an unmatched node and follows the edge with smaller weight until another matched node is encountered.

[0138] Update matching: adjust the matching along this path, add a matching edge and delete this path.

[0139] Termination condition: If an augmenting path can be found, continue the next round of search. If not found, it means that the current best match has been found and the algorithm ends.

[0140] Return result: Output the number of maximum matches currently found and the corresponding matching solutions.

[0141] Further, in step S3, a wearing torso category is defined based on each type of safety gear, and all human key points are classified into all wearing torso categories through a classification algorithm, including:

[0142] Step S31, define the data set to be classified x={x1, x2, ..., x i ,…,x m}, where x i is the i-th human key point in the data set x to be classified, and m is the number of all human key points.

[0143] Step S32, define a category set C = {y1, y2, ..., y j ,…,y n}, where y j is the jth wearing torso category in the category set C, and n is the number of all wearing torso categories.

[0144] Step S33, calculate the conditional probability of each human key point in each wearing torso category according to formula (1):

[0145]

[0146] Among them, P(x|y j ) is the conditional probability of the data set x to be classified under the j-th wearing torso category; P(y j ) is the marginal probability of the j-th wearing torso category; P(x i |y j ) is the conditional probability of the i-th human body key point under the j-th wearing torso category.

[0147] Step S34, classify each human body key point into the wearing torso category with the highest conditional probability.

[0148] Preferably, the classification algorithm of this embodiment adopts Bayesian classification to classify each electrical device into the load level with the highest conditional probability, so as to prevent subjective errors in manual classification.

[0149] Specifically, Naive Bayes is defined as follows:

[0150] ① Let x = {a1, a2, a3, ..., an} be an item to be classified, and each a is a feature of x.

[0151] ②There is a category set c = {y1, y2, y3, ..., y m}.

[0152] ③ Calculate P(y1|x), P(y2|x), ..., P(y m |x).

[0153] ④If P(y k |x)=max{P(y1|x),P(y2|x),...,P(y m |x)}, then x∈y k .

[0154] Then calculate the conditional probabilities in step ③ through the following steps:

[0155] Find a set of items to be classified with known classifications. This set is called a training sample set.

[0156] The conditional probability estimates of each feature attribute in each category are obtained by statistics. That is:

[0157] P(a1|y1),P(a2|y1),……,P(a n |y1)

[0158] P(a1|y2),P(a2|y2),……,P(a n |y2);

[0159] …

[0160] P(a1|y m ),P(a2|y m ),……,P(a n |y m );

[0161] Assuming that each feature attribute is conditionally independent, according to the Bayesian principle:

[0162] P(y i |x)=P(x|y i )P(y i ) / p(x).

[0163] Since the denominator is a constant for all categories, we only need to maximize the numerator. And because each feature attribute is conditionally independent, then:

[0164] P(x|y i )P(y i)=P(a1|y i )P(a2|y i )……P(a n |y i )P(y i ).

[0165] It should be noted that the above preferred contents are also explanations of the principles, and the meanings of their symbols are not interchangeable with the meanings of the symbols of other formulas in this embodiment.

[0166] Furthermore, the safety gear includes a helmet, protective clothing, gloves, protective pants, and protective shoes. Step S4, obtaining the maximum area enclosed by all key points of the human body in the current wearing torso category, and defining the maximum area as the detection area of ​​the current wearing torso category, includes:

[0167] Step S41, using a human key point detection algorithm to detect at least one key point on the head, at least one key point on each shoulder, at least one key point on each hand, at least one key point on each side of the hips, at least one key point on each knee, and at least one key point on each foot in each portrait data.

[0168] Step S42, defining the maximum area enclosed by all key points of the head as the detection area of ​​the helmet.

[0169] Step S43, the maximum area enclosed by all shoulder key points and all hip key points is defined as the detection area of ​​the protective clothing.

[0170] Step S44, defining the maximum area enclosed by all the key points of the hand as the detection area of ​​the glove.

[0171] Step S45, defining the maximum area enclosed by all the hip key points, all the knee key points and all the foot key points as the detection area of ​​the protective pants.

[0172] Step S46, defining the maximum area enclosed by all the key points of the foot as the detection area of ​​the protective shoe.

[0173] Preferably, if the number of key points in the wearing torso category is small and insufficient to form an area that meets the size of the corresponding safety gear, the midpoint of all key points in the current wearing torso category can be obtained, and a circular detection area can be formed with the midpoint as the center and the commonly used size of the corresponding safety gear as the radius.

[0174] For example, if the torso category is head, but there are only 1 or 2 to 3 key points in this category, the midpoints of these key points can be obtained, where the midpoint of 1 key point is the key point, the midpoint of 2 key points is the midpoint of the connected line segment, and the midpoint of 3 key points is the midpoint of the triangle formed by the midpoints, and so on. Finally, the detection area is formed with the size of the helmet corresponding to the head as the radius. However, it should be noted that the size here refers to the actual size in the image data, not the metric size of the helmet itself, that is, the scale needs to be considered.

[0175] Further, step S7, judging whether there is a sensing chip in each detection area according to the positions of all chips, then includes:

[0176] Step S10: If there is a sensing chip in each detection area, then the entry timestamp information of the entry signal is obtained.

[0177] Step S20, loading the entry timestamp information into each sensor chip respectively.

[0178] Step S30, responding to an exit signal of the construction site and acquiring exit timestamp information of the exit signal.

[0179] Step S40, loading the exit timestamp information into each sensor chip respectively.

[0180] Step S50, obtaining the time difference between the exit timestamp information and the entry timestamp information of the current construction personnel.

[0181] Step S60, defining the time difference as the current construction personnel's entry time.

[0182] Furthermore, in step S8, the detection area without the sensing chip is marked as a protective gear missing area, and then, the following steps are included:

[0183] Step S100, determining whether the protective gear missing area is the detection area of ​​the helmet, if the protective gear missing area is the detection area of ​​the helmet, executing step S200.

[0184] Step S200, generating a helmet missing warning signal.

[0185] Step S300, sending a helmet missing warning signal to the construction workers and an external receiving end.

[0186] Preferably, the design intention of step S100 to step S300 is to focus on protecting the head safety of construction workers.

[0187] This embodiment obtains a person detection frame that matches the entry signal of the construction site in response to the entry signal; obtains the human key points in the person detection frame through a human key point detection algorithm; defines a wearing torso category based on each type of safety protective gear, and classifies all human key points into all wearing torso categories through a classification algorithm; obtains the maximum area enclosed by all human key points in the current wearing torso category, and defines the maximum area as the detection area of ​​the current wearing torso category; senses the chip positions and chip numbers of all sensing chips through an external sensing end; determines whether the number of chips is greater than or equal to the preset construction requirement number, and if the number of chips is greater than or equal to the preset construction requirement number, determines whether there is a sensing chip in each detection area according to the positions of all chips; marks the detection area without a sensing chip as a protective gear missing area; and sends the protective gear missing area to construction personnel and an external receiving end. This embodiment improves the target detection algorithm and integrates the human key point detection algorithm to respectively detect each area that should have a safety protective gear. Compared with the existing computer vision, this embodiment only performs target visual detection on the detection area divided by the human key point detection algorithm. It is not necessary for all models to traverse the same entire image separately, which significantly shortens the detection response time. At the same time, it determines whether the safety protective gear is worn based on the recognition of the sensing chip, avoiding the existing computer vision from misjudging low-quality safety protective gear images (occluded, unclear, too large, too small, etc.). The computer vision of this embodiment is only used to identify the detection area, not for identifying the safety protective gear, and then the sensing chip is used to match the monitoring area to achieve the purpose of accurate identification.

[0188] like Figure 2 As shown, this embodiment provides an embodiment of a wearing management device for safety gear. In this embodiment, the wearing management device is applied to the wearing management method as in the above embodiment.

[0189] Specifically, the wearing management device includes a person detection frame acquisition module 1, a human body key point acquisition module 2, a human body key point classification module 3, a detection area definition module 4, a sensing chip sensing module 5, a sensing chip judgment module 6, a detection area judgment module 7, a protective gear missing area definition module 8, and a protective gear missing area sending module 9, which are electrically connected in sequence.

[0190] Among them, the person detection frame acquisition module 1 is used to respond to the entry signal of the construction site and obtain the person detection frame matching the entry signal; the human body key point acquisition module 2 is used to obtain the human body key points in the person detection frame through the human body key point detection algorithm; the human body key point classification module 3 is used to define a wearing torso category based on each type of safety protective gear, and classify all human body key points into all wearing torso categories through the classification algorithm; the detection area definition module 4 is used to obtain the maximum area enclosed by all human body key points in the current wearing torso category, and define the maximum area as the detection area of ​​the current wearing torso category; the sensor chip sensing module 5 is used to sense the chip position and chip number of all sensor chips through the external sensing end; the sensor chip judgment module 6 is used to judge whether the number of chips is greater than or equal to the preset construction requirement number; the detection area judgment module 7 is used to judge whether there is a sensor chip in each detection area according to the positions of all chips if the number of chips is greater than or equal to the preset construction requirement number; the protective gear missing area definition module 8 is used to mark the detection area without a sensor chip as a protective gear missing area; the protective gear missing area sending module 9 is used to send the protective gear missing area to the construction personnel and the external receiving end.

[0191] Furthermore, the person detection frame acquisition module 1 specifically includes a first person detection frame acquisition submodule, a second person detection frame acquisition submodule, a third person detection frame acquisition submodule, a fourth person detection frame acquisition submodule, a fifth person detection frame acquisition submodule, a sixth person detection frame acquisition submodule, a seventh person detection frame acquisition submodule, and an eighth person detection frame acquisition submodule, which are electrically connected in sequence; the eighth person detection frame acquisition submodule is electrically connected to the human body key point acquisition module 2.

[0192] Among them, the first person detection frame acquisition submodule is used to acquire image data matching the entry signal through an external camera terminal; the second person detection frame acquisition submodule is used to divide the image data into several grids evenly; the third person detection frame acquisition submodule is used to detect several prior frames through the person detection model based on all grids; the fourth person detection frame acquisition submodule is used to define the construction personnel with the highest confidence; the fifth person detection frame acquisition submodule is used to acquire the confidence of each prior frame respectively, and acquire the prior frame with the largest confidence and mark it as the first-order bounding frame; the sixth person detection frame acquisition submodule is used to calculate the intersection and union ratio of the first-order bounding frame with each other prior frame respectively; the seventh person detection frame acquisition submodule is used to select the first-order bounding frame whose intersection and union ratio is greater than or equal to the preset ratio threshold as the second-order bounding frame; the eighth person detection frame acquisition submodule is used to acquire the second-order bounding frame with the highest confidence and define it as the person detection frame.

[0193] Furthermore, the human body key point acquisition module 2 specifically includes a first human body key point acquisition submodule, a second human body key point acquisition submodule, a third human body key point acquisition submodule, a fourth human body key point acquisition submodule, and a fifth human body key point acquisition submodule, which are electrically connected in sequence; the first human body key point acquisition submodule is electrically connected to the eighth person detection frame acquisition submodule, and the fifth human body key point acquisition submodule is electrically connected to the human body key point classification module 3.

[0194] Among them, the first human key point acquisition submodule is used to train the VGGNet convolutional network through the preset OpenPose library to obtain the VGGNet prediction model; the second human key point acquisition submodule is used to input each image data into the VGGNet prediction model respectively to extract human features; the third human key point acquisition submodule is used to extract the plane confidence map of the human body part position in the current image data through the first branch in the two-branch CNN model; the fourth human key point acquisition submodule is used to extract the plane affinity vector field of the human body part position in the current image data through the second branch in the two-branch CNN model; the fifth human key point acquisition submodule is used to calculate the human key points of the plane confidence map and the plane affinity vector field of the current image data through the bipartite graph matching of the Hungarian algorithm.

[0195] Furthermore, the human body key point classification module 3 specifically includes a first human body key point classification submodule, a second human body key point classification submodule, a third human body key point classification submodule, and a fourth human body key point classification submodule, which are electrically connected in sequence; the first human body key point classification submodule is electrically connected to the fifth human body key point acquisition submodule, and the fourth human body key point classification submodule is electrically connected to the detection area definition module 4.

[0196] The first human key point classification submodule is used to define a to-be-classified data set x={x1, x2,…, x i ,…,x m}, where x i is the i-th human key point in the data set x to be classified, and m is the number of all human key points.

[0197] The second human key point classification submodule is used to define a category set C = {y1, y2, ..., y j ,…,y n}, where y j is the jth wearing torso category in the category set C, and n is the number of all wearing torso categories.

[0198] The third human key point classification submodule is used to calculate the conditional probability of each human key point in each wearing torso category according to formula (1):

[0199]

[0200] Among them, P(x|y j ) is the conditional probability of the data set x to be classified under the j-th wearing torso category; P(y j ) is the marginal probability of the j-th wearing torso category; P(x i |y j ) is the conditional probability of the i-th human body key point under the j-th wearing torso category.

[0201] The fourth human body key point classification submodule is used to classify each human body key point into the wearing torso category with the highest conditional probability.

[0202] Furthermore, the detection area definition module 4 specifically includes a first detection area definition submodule, a second detection area definition submodule, a third detection area definition submodule, a fourth detection area definition submodule, a fifth detection area definition submodule, and a sixth detection area definition submodule, which are electrically connected in sequence; the first detection area definition submodule is electrically connected to the fourth human body key point classification submodule, and the sixth detection area definition submodule is electrically connected to the sensing chip sensing module 5.

[0203] Among them, the first detection area definition submodule is used to detect at least one key point on the head, at least one key point on each shoulder, at least one key point on each hand, at least one key point on each side of the hip, at least one key point on each knee, and at least one key point on each foot in each portrait data through a human key point detection algorithm; the second detection area definition submodule is used to define the maximum area enclosed by all head key points as the detection area of ​​the helmet; the third detection area definition submodule is used to define the maximum area enclosed by all shoulder key points and all hip key points as the detection area of ​​the protective clothing; the fourth detection area definition submodule is used to define the maximum area enclosed by all hand key points as the detection area of ​​the gloves; the fifth detection area definition submodule is used to define the maximum area enclosed by all hip key points, all knee key points and all foot key points as the detection area of ​​the protective pants; the sixth detection area definition submodule is used to define the maximum area enclosed by all foot key points as the detection area of ​​the protective shoes.

[0204] Furthermore, the wearing management device also includes an entry timestamp information acquisition module, an entry timestamp information loading module, an exit timestamp information acquisition module, an exit timestamp information loading module, and a time difference acquisition module, which are electrically connected in sequence; the entry timestamp information acquisition module is electrically connected to the detection area judgment module 7.

[0205] Among them, the entry timestamp information acquisition module is used to obtain the entry timestamp information of the entry signal if there is a sensing chip in each detection area; the entry timestamp information loading module is used to load the entry timestamp information into each sensing chip respectively; the exit timestamp information acquisition module is used to respond to the exit signal of the construction site and obtain the exit timestamp information of the exit signal; the exit timestamp information loading module is used to load the exit timestamp information into each sensing chip respectively; the time difference acquisition module is used to obtain the time difference between the exit timestamp information and the entry timestamp information of the current construction personnel; the time difference sending module is used to define the time difference as the entry time of the current construction personnel.

[0206] Furthermore, the wearing management device also includes a helmet detection area judgment module, a helmet missing warning signal generation module, and a helmet missing warning signal sending module, which are electrically connected in sequence; the helmet detection area judgment module is electrically connected to the protective gear missing area definition module 8.

[0207] Among them, the safety helmet detection area judgment module is used to judge whether the protective gear missing area is the detection area of ​​the safety helmet; the safety helmet missing warning signal generation module is used to generate a safety helmet missing warning signal if the protective gear missing area is the detection area of ​​the safety helmet; the safety helmet missing warning signal sending module is used to send the safety helmet missing warning signal to the construction personnel and the external receiving end.

[0208] It should be noted that this embodiment is a functional module item embodiment based on the above method embodiment. For additional contents such as the optimization, expansion, and example illustration of this embodiment, please refer to the above method embodiment, and this embodiment will not be repeated.

[0209] This embodiment obtains a person detection frame that matches the entry signal of the construction site in response to the entry signal; obtains the human key points in the person detection frame through a human key point detection algorithm; defines a wearing torso category based on each type of safety protective gear, and classifies all human key points into all wearing torso categories through a classification algorithm; obtains the maximum area enclosed by all human key points in the current wearing torso category, and defines the maximum area as the detection area of ​​the current wearing torso category; senses the chip positions and chip numbers of all sensing chips through an external sensing end; determines whether the number of chips is greater than or equal to the preset construction requirement number, and if the number of chips is greater than or equal to the preset construction requirement number, determines whether there is a sensing chip in each detection area according to the positions of all chips; marks the detection area without a sensing chip as a protective gear missing area; and sends the protective gear missing area to construction personnel and an external receiving end. This embodiment improves the target detection algorithm and integrates the human key point detection algorithm to respectively detect each area that should have a safety protective gear. Compared with the existing computer vision, this embodiment only performs target visual detection on the detection area divided by the human key point detection algorithm. It is not necessary for all models to traverse the same entire image separately, which significantly shortens the detection response time. At the same time, it determines whether the safety protective gear is worn based on the recognition of the sensing chip, avoiding the existing computer vision from misjudging low-quality safety protective gear images (occluded, unclear, too large, too small, etc.). The computer vision of this embodiment is only used to identify the detection area, not for identifying the safety protective gear, and then the sensing chip is used to match the monitoring area to achieve the purpose of accurate identification.

[0210] Figure 3 An embodiment of the electronic device of the present application is shown, see Figure 3 The electronic device 10 includes a processor 101 and a memory 102 coupled to the processor 101 .

[0211] The memory 102 stores program instructions for implementing the safety gear wearing management method of any of the above embodiments.

[0212] The processor 101 is used to execute the program instructions stored in the memory 102 to manage the wearing of the safety gear.

[0213] The processor 101 may also be referred to as a CPU (Central Processing Unit). The processor 101 may be an integrated circuit chip having signal processing capabilities. The processor 101 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0214] Further, Figure 4 This is a schematic diagram of the structure of a storage medium according to an embodiment of the present application. Figure 4 The storage medium 11 of the embodiment of the present application stores program instructions 111 that can implement all the above methods, wherein the program instructions 111 can be stored in the above storage medium in the form of a software product, including several instructions for enabling a computer power device (which can be a personal computer, server, or network power device, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or terminal power devices such as a computer, a server, a mobile phone, and a tablet.

[0215] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0216] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. The above is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the specification and drawings of this application, or directly or indirectly used in other related technical fields, is also included in the patent protection scope of the present application.

[0217] The specific implementation methods of the invention are described in detail above, but they are only examples, and the present application is not limited to the specific implementation methods described above. For those skilled in the art, any equivalent modification or substitution of the invention is also within the scope of the present application, and therefore, the equalization, modification, and improvement made without departing from the spirit and principle of the present application should be included in the scope of the present application.

Claims

1. A wearing management method based on safety protective gear, the wearing management method is applied to a number of construction workers wearing safety protective gear in a preset construction site, all safety protective gears are embedded with a sensing chip, and the characteristics are as follows: The wearing management method comprises: Step S1, in response to an entry signal of the construction site, obtaining a person detection frame matching the entry signal; Step S2, obtaining the key points of the human body in the person detection frame by using a human body key point detection algorithm; Step S3, defining a wearing torso category based on each type of safety gear, and classifying all human key points into all wearing torso categories through a classification algorithm; Step S4, obtaining the maximum area enclosed by all key points of the human body in the current wearing torso category, and defining the maximum area as the detection area of ​​the current wearing torso category; Step S5, sensing the chip positions and chip numbers of all the sensing chips through the external sensing terminal; Step S6, determining whether the number of chips is greater than or equal to the preset number of construction requirements, if the number of chips is greater than or equal to the preset number of construction requirements, executing step S7; Step S7, judging whether there is the sensing chip in each detection area according to the positions of all chips; Step S8, marking the detection area without the sensing chip as a protective gear missing area; Step S9, sending the protective gear missing area to the construction personnel and an external receiving end.

2. The wearing management method according to claim 1, characterized in that: Step S1, in response to an entry signal of the construction site, obtaining a person detection frame matching the entry signal, including: Step S11, acquiring image data matching the entry signal through an external camera terminal; Step S12, dividing the image data into a plurality of grids on average; Step S13, detecting a plurality of prior frames based on all grids through the person detection model; Step S14, defining the construction worker as having the highest confidence level; Step S15, respectively obtain the confidence of each priori box, obtain the priori box with the largest confidence and mark it as the first-order bounding box; Step S16, calculating the intersection-over-union ratio between the first-order bounding box and each other priori box; Step S17, selecting a first-order bounding box whose intersection-over-union ratio is greater than or equal to a preset ratio threshold as a second-order bounding box; Step S18, obtaining a second-order bounding box with the highest confidence and defining it as the person detection box.

3. The wearing management method according to claim 1, characterized in that: Step S2, obtaining the key points of the human body in the person detection frame by using a human body key point detection algorithm, comprises: Step S21, training the VGGNet convolutional network by using the preset OpenPose library to obtain a VGGNet prediction model; Step S22, inputting each image data into the VGGNet prediction model to extract human body features; Step S23, extracting a plane confidence map of the position of the human body part in the current image data through the first branch of the two-branch CNN model; Step S24, extracting the plane affinity vector field of the human body part position in the current image data through the second branch in the two-branch CNN model; Step S25, calculating the human body key points of the plane confidence map and the plane affinity vector field of the current image data through bipartite graph matching of the Hungarian algorithm.

4. The wearing management method according to claim 1, characterized in that: Step S3, defining a wearing torso category based on each type of safety gear, and classifying all human key points into all wearing torso categories through a classification algorithm, including: Step S31, define the data set to be classified x={x1, x2, ..., x i ,…,x m }, where x i is the i-th human key point in the data set x to be classified, and m is the number of all human key points; Step S32, defining a category set C = {y1, y2, ..., y j ,…,y n }, where y j is the jth wearing torso category in the category set C, and n is the number of all wearing torso categories; Step S33, calculate the conditional probability of each human key point in each wearing torso category according to formula (1): Among them, P(xy j ) is the conditional probability of the data set x to be classified under the jth wearing torso category; P(yj) is the marginal probability of the jth wearing torso category; P(xiyj) is the conditional probability of the i-th human body key point under the j-th wearing torso category; Step S34, classify each human body key point into the wearing torso category with the highest conditional probability.

5. The wearing management method according to claim 1, wherein the safety gear comprises a helmet, protective clothing, gloves, protective pants, and protective shoes, characterized in that: Step S4, obtaining the maximum area enclosed by all key points of the human body in the current wearing torso category, and defining the maximum area as the detection area of ​​the current wearing torso category, including: Step S41, using a human key point detection algorithm to detect at least one key point on the head, at least one key point on each shoulder, at least one key point on each hand, at least one key point on each side of the hips, at least one key point on each knee, and at least one key point on each foot in each portrait data; Step S42, defining the maximum area enclosed by all key points of the head as the detection area of ​​the helmet; Step S43, defining the maximum area enclosed by all shoulder key points and all hip key points as the detection area of ​​the protective clothing; Step S44, defining the maximum area enclosed by all the key points of the hand as the detection area of ​​the glove; Step S45, defining the maximum area enclosed by all the key points of the hips, all the key points of the knees and all the key points of the feet as the detection area of ​​the protective pants; Step S46, defining the maximum area enclosed by all the key points of the foot as the detection area of ​​the protective shoe.

6. The wearing management method according to claim 1, characterized in that: Step S7, judging whether there is the sensing chip in each detection area according to the positions of all chips, and then comprising: Step S10, if the sensing chip is present in each detection area, obtaining the entry timestamp information of the entry signal; Step S20, loading the entry timestamp information into each sensor chip respectively; Step S30, responding to an exit signal of the construction site and acquiring exit timestamp information of the exit signal; Step S40, loading the exit timestamp information into each sensor chip respectively; Step S50, obtaining the time difference between the exit timestamp information and the entry timestamp information of the current construction personnel; Step S60, defining the time difference as the current construction personnel's entry time.

7. The wearing management method according to claim 5, characterized in that: Step S8, marking the detection area without the sensing chip as a protective gear missing area, and then comprising: Step S100, determining whether the protective gear missing area is the detection area of ​​the helmet, if the protective gear missing area is the detection area of ​​the helmet, executing step S200; Step S200, generating a helmet missing warning signal; Step S300, sending the helmet missing warning signal to the construction worker and an external receiving end.

8. A wearing management device for safety gear, the wearing management device for safety gear being applied to the wearing management method according to any one of claims 1 to 7, characterized in that: The wearing management device comprises: A person detection frame acquisition module, configured to respond to an entry signal of the construction site and acquire a person detection frame matching the entry signal; A human key point acquisition module, used to acquire the human key points in the person detection frame through a human key point detection algorithm; The human body key point classification module is used to define a wearing torso category based on each safety protective gear, and classify all human body key points into all wearing torso categories through a classification algorithm; A detection area definition module is used to obtain the maximum area enclosed by all key points of the human body in the current wearing torso category, and define the maximum area as the detection area of ​​the current wearing torso category; A sensing chip sensing module is used to sense the chip positions and chip numbers of all sensing chips through an external sensing terminal; The sensing chip determination module is used to determine whether the number of chips is greater than or equal to the preset number of construction requirements. If the number of chips is greater than or equal to the preset number of construction requirements, step S7 is executed; A detection area judgment module, used to judge whether there is the sensing chip in each detection area according to the positions of all chips; A protective gear missing area definition module, used to mark the detection area without the sensing chip as a protective gear missing area; The protective gear missing area sending module is used to send the protective gear missing area to the construction personnel and an external receiving end.

9. An electronic device, characterized in that: It comprises a processor and a memory coupled to the processor, wherein the memory stores program instructions executable by the processor; when the processor executes the program instructions stored in the memory, the wearing management method of the safety gear as described in any one of claims 1 to 7 is implemented.

10. A storage medium, characterized in that: The storage medium stores program instructions, and when the program instructions are executed by the processor, the wearing management method of the safety gear according to any one of claims 1 to 7 can be implemented.

Images