Operation site safety detection method and system

Abstract

The invention provides a working site safety detection method and system, and the method comprises the steps: obtaining an image of a working site, and carrying out the face recognition of a worker at the working site, and obtaining a face recognition result; based on the image of the operation site, performing dressing safety identification on the worker passing the face identification to obtain a dressing safety identification result; based on the image of the working site, performing tool safety identification on tools on the working site to obtain a tool safety identification result; and sending the face recognition result, the dressing safety recognition result and the tool safety recognition result to a specified terminal device, and receiving an operation group obtained by matching a guardian and an operator and sent by the terminal device, and safety suggestions and operation tasks for the operation group. According to the invention, face recognition, dressing safety recognition and tool safety recognition are carried out on the operation site based on the artificial intelligence technology, and the efficiency and accuracy of safety detection of the operation site are improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of job site safety detection, and in particular to a job site safety detection method and system. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the disclosure that are recited in the claims. No description herein is admitted to be prior art by inclusion in this section.

[0003] The work site referred to in this disclosure includes small-scale work sites for power grid marketing such as emergency repairs, meter installation and power connection, which involve a variety of work locations and types, including switch stations, user-side distribution rooms, transformers on box transformer poles, household meters in buildings, etc. Since such work is usually done in a relatively scattered time and involves risks in multiple aspects such as safety, service and public opinion, it is difficult for safety inspectors to conduct comprehensive and real-time inspections of small-scale work sites, making safety briefings at marketing small-scale work sites extremely difficult.

[0004] In the related technology, the following on-site safety inspection method is usually adopted: the on-site work supervisor reads the safety briefing book, checks the identities of the team members by name and assigns the combination of supervisors and operators, and visually observes whether the tools are qualified (including screwdrivers, goggles, electrician testers, pliers). After all are qualified, all personnel sign and start to execute the subsequent work process.

[0005] However, the above-mentioned work site safety detection method that relies on manual implementation has poor accuracy and low efficiency. Summary of the invention

[0006] In view of this, the purpose of the present disclosure is to propose a work site safety detection method and system to at least solve one of the technical problems in the related art to a certain extent.

[0007] Based on the above purpose, the first aspect of the exemplary embodiment of the present disclosure provides a work site safety detection method, including:

[0008] Acquire an image of the work site, perform facial recognition on personnel at the work site based on the image of the work site, obtain a facial recognition result, and determine the staff member who passes the facial recognition;

[0009] Based on the image of the work site, the worker who has passed the face recognition is subjected to clothing safety recognition to obtain a clothing safety recognition result, and the identity category of the worker is determined based on the clothing safety recognition result, wherein the identity category includes a guardian and an operator;

[0010] Performing tool safety identification on tools at the work site based on the image of the work site to obtain a tool safety identification result;

[0011] The face recognition result, the clothing safety recognition result and the tool safety recognition result are sent to a designated terminal device, and the terminal device sends a work group obtained by matching the guardian and the operator, as well as safety recommendations and work tasks for the work group.

[0012] In some exemplary embodiments, performing face recognition on personnel at the work site based on the image of the work site, obtaining face recognition results, and determining the staff member who passes the face recognition includes:

[0013] Inputting the image of the work site into a pre-trained face recognition model, extracting facial features in the image of the work site through the face recognition model, matching the facial features with a pre-configured face feature library, and obtaining a face recognition result output by the face recognition model;

[0014] The face recognition result includes the staff members who passed the face recognition and their vacancy status.

[0015] In some exemplary embodiments, performing clothing safety identification on the worker who has passed face recognition based on the image of the work site to obtain a clothing safety identification result includes:

[0016] Based on the image of the work site, the worker who has passed the face recognition is identified in terms of a safety helmet, work clothes, vest, insulating gloves and insulating shoes to obtain the clothing safety identification result.

[0017] In some exemplary embodiments, performing safety helmet recognition on the worker through face recognition based on the image of the work site includes:

[0018] Input the image of the work site into a pre-trained helmet recognition model, extract features of different levels of the image of the work site through the helmet recognition model, fuse the features of different levels to obtain feature maps of different scales, and identify whether the worker who has passed face recognition is wearing a helmet based on the feature maps of different scales to obtain whether the helmet is worn;

[0019] In response to determining that the worker who has passed the face recognition is wearing a safety helmet, identifying whether the color of the safety helmet meets the preset safety helmet color, and obtaining whether the color of the safety helmet is correct;

[0020] The helmet recognition result includes whether the helmet is worn and whether the helmet is of the correct color;

[0021] Then, the clothing safety identification result includes the helmet identification result.

[0022] In some exemplary embodiments, the work clothes of the worker who has passed the face recognition are recognized based on the image of the work site, including:

[0023] Inputting the image of the work site into a pre-trained work clothes recognition model, performing human body position recognition on the image of the work site through the work clothes recognition model to obtain a human body position recognition result, cropping the image of the work site based on the human body position recognition result to obtain a human body range image, classifying and distinguishing the human body image in the human body range image to obtain a work clothes recognition result, wherein the work clothes recognition result includes whether the work clothes are worn and whether the work clothes are worn in a standard manner;

[0024] Then, the clothing safety identification result includes the work clothes identification result.

[0025] In some exemplary embodiments, performing vest recognition on the worker who has passed face recognition based on the image of the work site includes:

[0026] Inputting the image of the work site into a pre-trained vest recognition model, performing personnel target detection on the image of the work site through the vest recognition model to obtain a personnel target, performing personnel attribute recognition on the personnel target to obtain a vest recognition result, wherein the vest recognition result includes whether the vest is worn;

[0027] Then, the clothing safety identification result includes the vest identification result, and the identity category of the staff member is determined based on the clothing safety identification result, and the identity category includes a guardian and an operator, including:

[0028] The staff member wearing a vest is determined to be the guardian, and the staff member not wearing a vest is determined to be the operator.

[0029] In some exemplary embodiments, performing insulating glove recognition on the worker through face recognition based on the image of the work site includes:

[0030] Inputting the image of the work site into a pre-trained insulating glove recognition model, performing human posture recognition on the image of the work site through the insulating glove recognition model to obtain a human posture recognition result, extracting a hand area from the human posture recognition result, performing insulating glove recognition on the hand area, and obtaining an insulating glove recognition result;

[0031] Then, the clothing safety identification result includes the insulating gloves identification result.

[0032] In some exemplary embodiments, the insulating shoes of the worker who has passed the face recognition are identified based on the image of the work site, including:

[0033] Inputting the image of the work site into a pre-trained insulating shoe recognition model, performing insulating shoe recognition on the image of the work site through the insulating shoe recognition model, and obtaining an insulating shoe recognition result;

[0034] Then, the clothing safety identification result includes the insulating shoe identification result.

[0035] In some exemplary embodiments, performing tool safety identification on tools at the work site based on the image of the work site to obtain a tool safety identification result includes:

[0036] The image of the work site is input into a pre-trained tool safety recognition model, and the tool safety recognition model is used to detect whether there are preset types of safety tools in the image of the work site to obtain a tool safety recognition result.

[0037] Based on the same inventive concept, the second aspect of the exemplary embodiment of the present disclosure provides a work site safety detection system, including:

[0038] A face recognition module is configured to obtain an image of the work site, perform face recognition on personnel at the work site based on the image of the work site, obtain a face recognition result, and determine a staff member who passes the face recognition;

[0039] a clothing safety identification module, configured to perform clothing safety identification on the worker who has passed face recognition based on the image of the work site, obtain a clothing safety identification result, and determine the identity category of the worker based on the clothing safety identification result, wherein the identity category includes a guardian and an operator;

[0040] A tool safety identification module is configured to perform tool safety identification on the tools at the work site based on the image of the work site to obtain a tool safety identification result;

[0041] The recognition result, safety suggestion and work task transmission module is configured to send the face recognition result, the clothing safety recognition result and the tool safety recognition result to a designated terminal device, and receive the work group obtained by matching the guardian and the operator, as well as the safety suggestions and work tasks for the work group, sent by the terminal device.

[0042] From the above, it can be seen that the method and system for detecting safety at work site provided by the embodiment of the present disclosure include: obtaining an image of the work site, performing face recognition on the personnel at the work site based on the image of the work site, obtaining face recognition results, and determining the staff member who has passed face recognition; performing clothing safety recognition on the staff member who has passed face recognition based on the image of the work site, obtaining clothing safety recognition results, and determining the identity category of the staff member based on the clothing safety recognition results, the identity category including guardians and operators; performing tool safety recognition on the tools at the work site based on the image of the work site, obtaining tool safety recognition results; sending the face recognition results, the clothing safety recognition results, and the tool safety recognition results to a designated terminal device, and receiving the work group obtained by matching the guardian and the operator, as well as the safety suggestions and work tasks for the work group, sent by the terminal device. The present disclosure performs face recognition, clothing safety recognition, and tool safety recognition on the work site based on artificial intelligence technology, thereby improving the efficiency and accuracy of safety detection at the work site. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the present disclosure or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0044] Figure 1 A schematic diagram of an application scenario of a work site safety detection method provided by an exemplary embodiment of the present disclosure;

[0045] Figure 2 A schematic diagram of a process flow of a work site safety detection method provided by an exemplary embodiment of the present disclosure;

[0046] Figure 3 Another schematic flow chart of a work site safety detection method provided by an exemplary embodiment of the present disclosure;

[0047] Figure 4 A structural schematic diagram of a work site safety detection system provided by an exemplary embodiment of the present disclosure;

[0048] Figure 5 A schematic structural diagram of an electronic device provided by an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0049] It is understandable that before using the technical solutions disclosed in the embodiments of this application, the type, scope of use, usage scenarios, etc. of the personal information involved in this application should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0050] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present application according to the prompt message.

[0051] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0052] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation method of the present application. Other methods that meet the relevant laws and regulations may also be applied to the implementation method of the present application.

[0053] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0054] In order to make the purpose, technical solutions and advantages of the present disclosure more clear, the principles and spirit of the present disclosure will be described with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present disclosure, and are not intended to limit the scope of the present disclosure in any way. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0055] It should be understood herein that any number of elements in the drawings is for illustration rather than limitation, and any naming is only for distinction rather than having any limiting meaning.

[0056] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present disclosure should be understood by people with ordinary skills in the field to which the present disclosure belongs. The "first", "second" and similar words used in the embodiments of the present disclosure do not represent any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing in front of the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connecting" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly. The article "one" or "a" before an element does not exclude the existence of multiple such elements.

[0057] The principle and spirit of the present disclosure are explained in detail below with reference to several representative embodiments of the present disclosure.

[0058] As described in the background technology, the current small-scale grid marketing operations such as emergency repairs, meter installation and power connection involve a variety of work locations and types, including switch stations, user-side distribution rooms, transformers on box transformer poles, household meters in buildings, etc. Since such operations are usually scattered in time and involve risks in multiple aspects such as safety, service and public opinion, it is difficult for safety inspectors to conduct comprehensive and real-time inspections of small-scale operation sites, making safety briefings at marketing small-scale operation sites extremely difficult.

[0059] In the related technology, the following on-site safety inspection method is usually adopted: the on-site work supervisor reads the safety briefing book, checks the identities of the team members by name and assigns the combination of supervisors and operators, and visually observes whether the tools are qualified (including screwdrivers, goggles, electrician testers, pliers). After all are qualified, all personnel sign and start to execute the subsequent work process.

[0060] However, the inventors of the present disclosure have discovered that the roll-call method for verifying the identities of team members has the following disadvantages: first, it is time-consuming, and especially inefficient when there are a large number of people; second, the roll-call method relies on manual memory and verbal confirmation, which is prone to errors, such as false alarms and missed reports; third, it lacks objectivity, and it is difficult to ensure the accuracy and fairness of the verification.

[0061] There are the following disadvantages in using the naked eye to observe whether tools are qualified: first, the resolution of the human eye is limited, and it is difficult to accurately capture tiny defects or dimensional changes in tools; second, naked eye observation is easily affected by factors such as light, observer fatigue and subjective judgment, resulting in inconsistent observation results and lack of objectivity; third, naked eye observation cannot record and analyze data, limiting the possibility of subsequent processing and improvement.

[0062] In order to solve the above problems, the present disclosure provides a work site safety detection solution, which specifically includes: acquiring an image of the work site, performing face recognition on personnel at the work site based on the image of the work site, obtaining face recognition results, and determining the staff who pass the face recognition; performing clothing safety recognition on the staff who pass the face recognition based on the image of the work site, obtaining clothing safety recognition results, and determining the identity category of the staff based on the clothing safety recognition results, the identity categories including supervisors and operators; performing tool safety recognition on tools at the work site based on the image of the work site, obtaining tool safety recognition results; sending the face recognition results, the clothing safety recognition results, and the tool safety recognition results to a designated terminal device, and receiving the work group obtained by matching the supervisor and the operator, as well as safety recommendations and work tasks for the work group, sent by the terminal device.

[0063] The present invention discloses face recognition, clothing safety recognition and tool safety recognition at the work site based on artificial intelligence technology, thereby improving the efficiency and accuracy of safety detection at the work site.

[0064] After introducing the basic principles of the present disclosure, various non-limiting embodiments of the present disclosure are described in detail below.

[0065] refer to Figure 1 , which is a schematic diagram of an application scenario of the work site safety detection method provided by the exemplary embodiment of the present disclosure.

[0066] This application scenario includes a terminal device 101, a server 102, and a data storage system 103. The terminal device 101, the server 102, and the data storage system 103 may be connected via a wired or wireless communication network to achieve data interaction.

[0067] The terminal device 101 may be an electronic device with data transmission and multimedia input / output functions close to the user side, including but not limited to a desktop computer, a mobile phone, a mobile computer, a tablet computer, a media player, a smart wearable device, a personal digital assistant (PDA) or other electronic devices capable of realizing the above functions. The electronic device may include a processor and a display screen with a touch input function, the display screen is used to present a graphical user interface, the graphical user interface can display an application interface, and the processor is used to process application data, generate a graphical user interface, and control the display of the graphical user interface on the display screen.

[0068] Server 102 and data storage system 103 can both be independent physical servers, or a server cluster or distributed system composed of multiple physical servers. They can also be cloud servers that provide basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), as well as big data and artificial intelligence platforms.

[0069] In some exemplary embodiments, the work site safety detection method can be run on the terminal device 101 and the server 102.

[0070] The terminal device 101 is installed with a client that communicates with the server 102 . The terminal device 101 is set at the work site. The terminal device 101 obtains images of the work site through the camera module set thereon, and the client sends the images of the work site to the server 102 .

[0071] The server 102 is used to provide a work site safety detection service to the user of the terminal device 101. The server 102 obtains the image of the work site sent by the terminal device 101, performs face recognition on the personnel at the work site based on the image of the work site, obtains the face recognition result, and determines the staff member who has passed the face recognition; performs clothing safety recognition on the staff member who has passed the face recognition based on the image of the work site, obtains the clothing safety recognition result, and determines the identity category of the staff member based on the clothing safety recognition result, and the identity category includes the guardian and the operator; performs tool safety recognition on the tools at the work site based on the image of the work site, and obtains the tool safety recognition result; sends the face recognition result, the clothing safety recognition result, and the tool safety recognition result to the designated terminal device, and receives the work group obtained by matching the guardian and the operator, as well as the safety suggestions and work tasks for the work group sent by the terminal device. Among them, the designated terminal device can be the terminal device 101 set at the work site.

[0072] The server 102 sends the operation group, the safety recommendations and the operation tasks for the operation group to the terminal device 101 .

[0073] The terminal device 101 displays the operation group and the safety suggestions and operation tasks for the operation group to the user through the client to help the user make safety rectification and execute the operation.

[0074] A large amount of training data is stored in the data storage system 103. The server 102 can train models for face recognition, clothing safety recognition, and tool safety recognition based on the large amount of training data, so that the model can recognize the input images of the work site. The source of the training data includes but is not limited to existing databases, data crawled from the Internet, or data uploaded by users when using the client. When the accuracy of the model output reaches a certain requirement, the server 102 can provide users with work site safety detection services based on the model. At the same time, the server 102 can also continuously optimize the model based on the newly added training data.

[0075] Combine the following Figure 1 The application scenario is used to describe the work site safety detection method according to the exemplary embodiment of the present disclosure. It should be noted that the above application scenario is only shown to facilitate understanding of the spirit and principle of the present disclosure, and the embodiments of the present disclosure are not limited in this respect. On the contrary, the embodiments of the present disclosure can be applied to any applicable scenario.

[0076] refer to Figure 2 , which is a flow chart of a work site safety detection method provided by an exemplary embodiment of the present disclosure.

[0077] The method for safety detection at the work site includes the following steps:

[0078] Step S210: Acquire an image of the work site, perform face recognition on personnel at the work site based on the image of the work site, obtain face recognition results, and determine the staff members who pass the face recognition.

[0079] In some exemplary embodiments, performing face recognition on personnel at the work site based on the image of the work site, obtaining face recognition results, and determining the staff member who passes the face recognition includes:

[0080] Inputting the image of the work site into a pre-trained face recognition model, extracting facial features in the image of the work site through the face recognition model, matching the facial features with a pre-configured face feature library, and obtaining a face recognition result output by the face recognition model;

[0081] The face recognition result includes the staff members who passed the face recognition and their vacancy status.

[0082] During the specific implementation, a face recognition model is established. The face recognition model is used to identify the identity of the staff and effectively identify the identity of the user through analysis and comparison of facial features.

[0083] The face recognition technology based on the GANs model is adopted, and the GAN dynamic game is used to improve the image classification accuracy of the convolutional neural network.

[0084] GANs consists of a pair of neural networks, a generative network and a discriminative network. Through adversarial training, the generative network can generate facial images with diversity and realism, and the discriminative network can accurately distinguish between real facial images and generated facial images.

[0085] Step S220: Based on the image of the work site, clothing safety identification is performed on the staff member who has passed face recognition to obtain a clothing safety identification result, and the identity category of the staff member is determined based on the clothing safety identification result, and the identity category includes a guardian and an operator.

[0086] refer to Figure 3 In some exemplary embodiments, the performing of clothing safety identification on the worker through face recognition based on the image of the work site to obtain the clothing safety identification result includes:

[0087] Based on the image of the work site, the worker who has passed the face recognition is identified in terms of a safety helmet, work clothes, vest, insulating gloves and insulating shoes to obtain the clothing safety identification result.

[0088] In some exemplary embodiments, performing safety helmet recognition on the worker through face recognition based on the image of the work site includes:

[0089] Input the image of the work site into a pre-trained helmet recognition model, extract features of different levels of the image of the work site through the helmet recognition model, fuse the features of different levels to obtain feature maps of different scales, and identify whether the worker who has passed face recognition is wearing a helmet based on the feature maps of different scales to obtain whether the helmet is worn;

[0090] In response to determining that the worker who has passed the face recognition is wearing a safety helmet, identifying whether the color of the safety helmet meets the preset safety helmet color, and obtaining whether the color of the safety helmet is correct;

[0091] The helmet recognition result includes whether the helmet is worn and whether the helmet is of the correct color;

[0092] Then, the clothing safety identification result includes the helmet identification result.

[0093] During the specific implementation, a safety helmet recognition model is established to detect whether the safety helmet is worn. The safety helmet recognition algorithm is used to automatically identify whether the workers at the power construction or maintenance work site are wearing safety helmets as required.

[0094] Based on the YOLOv5 model, the prediction accuracy is improved while maintaining the speed advantage.

[0095] Adopting the image pyramid structure, the features at different levels are integrated to obtain feature maps of different scales for position and category prediction;

[0096] During the training process, multi-size images are used for training so that the model can adapt to images of different resolutions;

[0097] By color filtering the test results, helmets of different colors can be distinguished more accurately.

[0098] In some exemplary embodiments, the work clothes of the worker who has passed the face recognition are recognized based on the image of the work site, including:

[0099] Inputting the image of the work site into a pre-trained work clothes recognition model, performing human body position recognition on the image of the work site through the work clothes recognition model to obtain a human body position recognition result, cropping the image of the work site based on the human body position recognition result to obtain a human body range image, classifying and distinguishing the human body image in the human body range image to obtain a work clothes recognition result, wherein the work clothes recognition result includes whether the work clothes are worn and whether the work clothes are worn in a standard manner;

[0100] Then, the clothing safety identification result includes the work clothes identification result.

[0101] In the specific implementation, a work clothes recognition model is established to detect whether the sleeves are rolled up, whether the sleeves are short, and whether the zipper is zipped. The work clothes recognition first uses the long-sleeved and long-trousers features as the basis for determining work clothes, that is, short-sleeved and shorts are detected as non-work clothes, and long-sleeved and long-trousers are work clothes. Secondly, whether the sleeves are rolled up and whether the zipper is zipped is used as the basis for judging whether the clothes are worn correctly.

[0102] Use the YOLOv5 model to quickly identify the coordinates of the human body;

[0103] The human body area is cut out from the original image and sent to the classification network for recognition;

[0104] The detected human body is classified and identified through the Resnet50 model to determine whether it is short-sleeved, whether the sleeves are rolled up, and whether the zipper is zipped.

[0105] In some exemplary embodiments, performing vest recognition on the worker who has passed face recognition based on the image of the work site includes:

[0106] Inputting the image of the work site into a pre-trained vest recognition model, performing personnel target detection on the image of the work site through the vest recognition model to obtain a personnel target, performing personnel attribute recognition on the personnel target to obtain a vest recognition result, wherein the vest recognition result includes whether the vest is worn;

[0107] Then, the clothing safety identification result includes the vest identification result, and the identity category of the staff member is determined based on the clothing safety identification result, and the identity category includes a guardian and an operator, including:

[0108] The staff member wearing a vest is determined to be the guardian, and the staff member not wearing a vest is determined to be the operator.

[0109] During the specific implementation, a vest recognition model is established, and on-site personnel targets are captured through video cameras. The information on whether the personnel are wearing a vest is obtained through the attributes of the personnel's clothing, so as to distinguish between on-site supervisors and operators.

[0110] It uses a combination of YOLOv5 video target detection and RCNN target attribute recognition;

[0111] YOLOv5 is used to detect moving human targets in the video stream. After obtaining the human targets, RCNN is used to identify the target attributes.

[0112] RCNN is used to train and classify multiple personnel attributes. Through sample collection, vest is used as the personnel clothing attribute. If the corresponding attribute is detected, it will be displayed as yes, otherwise it will be displayed as no.

[0113] In some exemplary embodiments, performing insulating glove recognition on the worker through face recognition based on the image of the work site includes:

[0114] Inputting the image of the work site into a pre-trained insulating glove recognition model, performing human posture recognition on the image of the work site through the insulating glove recognition model to obtain a human posture recognition result, extracting a hand area from the human posture recognition result, performing insulating glove recognition on the hand area, and obtaining an insulating glove recognition result;

[0115] Then, the clothing safety identification result includes the insulating gloves identification result.

[0116] During specific implementation, an insulating glove recognition model is established, in which the insulating glove detection algorithm is used to automatically identify whether the workers at the power construction or maintenance work site are wearing insulating gloves as required.

[0117] Real-time multi-person 2D posture estimation algorithm based on PAF (Part Affinity Fields) for human posture recognition, which can realize posture estimation of human movements, facial expressions, finger movements, etc.

[0118] Extract the hand area in complex scenes, and then use the SSD model to identify insulating gloves, while further improving the detection speed;

[0119] When developing the model, a detection algorithm based on SSD-MobileNet is used, and the feature extraction network VGG16 of the SSD algorithm is replaced with the MobileNet network to enhance the real-time performance of insulating gloves detection.

[0120] In some exemplary embodiments, the insulating shoes of the worker who has passed the face recognition are identified based on the image of the work site, including:

[0121] Inputting the image of the work site into a pre-trained insulating shoe recognition model, performing insulating shoe recognition on the image of the work site through the insulating shoe recognition model, and obtaining an insulating shoe recognition result;

[0122] Then, the clothing safety identification result includes the insulating shoe identification result.

[0123] During specific implementation, an insulating shoe recognition model is established, in which the insulating shoe detection algorithm is used to automatically identify whether the workers at the power construction or maintenance work site are wearing insulating shoes as required.

[0124] Because there are many types of insulating shoes and model fitting is relatively difficult, this algorithm uses a target detection model based on cascade-rcnn to achieve better detection results by increasing the number of model parameters.

[0125] Step S230: Perform tool safety identification on tools at the work site based on the image of the work site to obtain tool safety identification results.

[0126] In some exemplary embodiments, performing tool safety identification on tools at the work site based on the image of the work site to obtain a tool safety identification result includes:

[0127] The image of the work site is input into a pre-trained tool safety recognition model, and the tool safety recognition model is used to detect whether there are preset types of safety tools in the image of the work site to obtain a tool safety recognition result.

[0128] refer to Figure 3 In the specific implementation, a safety tool recognition model is established to detect whether there are four types of safety tools in the picture: screwdriver, goggles, electrician's pen, and pliers. The safety tool recognition algorithm is implemented through the target detection algorithm. Considering that the characteristics of safety tools are more obvious under the premise of standardized placement, the YOLOR model that emphasizes speed is used to quickly identify the coordinate positions of various tools and whether the tools are compliant.

[0129] Step S240, sending the face recognition result, the clothing safety recognition result and the tool safety recognition result to a designated terminal device, and receiving the work group obtained by matching the guardian and the operator, as well as safety recommendations and work tasks for the work group, sent by the terminal device.

[0130] During specific implementation, the face recognition results, the clothing safety recognition results and the tool safety recognition results can be sent to a designated terminal device for early warning. The person holding the terminal device can further make safety suggestions based on the safety issues therein, and can also match the guardian and the operator to obtain a work group, and assign work tasks to the work group.

[0131] During specific implementation, the face recognition result, the clothing safety recognition result and the tool safety recognition result may also be sent to corresponding personnel at the work site for early warning.

[0132] As can be seen from the above, the work site safety detection method provided by the embodiment of the present disclosure includes: acquiring an image of the work site, performing face recognition on the personnel at the work site based on the image of the work site to obtain a face recognition result, and determining the staff member who has passed the face recognition; performing clothing safety recognition on the staff member who has passed the face recognition based on the image of the work site to obtain a clothing safety recognition result, and determining the identity category of the staff member based on the clothing safety recognition result, the identity category including a supervisor and an operator; performing tool safety recognition on the tools at the work site based on the image of the work site to obtain a tool safety recognition result; sending the face recognition result, the clothing safety recognition result and the tool safety recognition result to a designated terminal device, and receiving the work group obtained by matching the supervisor and the operator and the safety recommendations and work tasks for the work group sent by the terminal device.

[0133] The present invention discloses face recognition, clothing safety recognition and tool safety recognition at the work site based on artificial intelligence technology, thereby improving the efficiency and accuracy of safety detection at the work site.

[0134] Furthermore, since the efficiency and accuracy of safety inspections at the work site are improved and the safety inspection results are sent to a preset terminal device for early warning, the safety risks of the operation are reduced and safety is improved.

[0135] It should be noted that the method of the embodiment of the present disclosure can be performed by a single device, such as a computer or a server. The method of the present embodiment can also be applied in a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present disclosure, and the multiple devices will interact with each other to complete the described method.

[0136] It should be noted that the above describes some embodiments of the present disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0137] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present disclosure also provides a work site safety detection system.

[0138] refer to Figure 4 , the work site safety detection system includes the following modules:

[0139] The face recognition module 410 is configured to obtain an image of the work site, perform face recognition on personnel at the work site based on the image of the work site, obtain a face recognition result, and determine the staff member who passes the face recognition;

[0140] A clothing safety identification module 420 is configured to perform clothing safety identification on the worker who has passed face recognition based on the image of the work site, obtain a clothing safety identification result, and determine the identity category of the worker based on the clothing safety identification result, wherein the identity category includes a guardian and an operator;

[0141] A tool safety identification module 430 is configured to perform tool safety identification on the tools at the work site based on the image of the work site to obtain a tool safety identification result;

[0142] The recognition result, safety suggestion and work task transmission module 440 is configured to send the face recognition result, the clothing safety recognition result and the tool safety recognition result to a designated terminal device, and receive the work group obtained by matching the supervisor and the operator, as well as the safety suggestions and work tasks for the work group, sent by the terminal device.

[0143] In some exemplary embodiments, the face recognition module 410 is specifically configured as follows:

[0144] Inputting the image of the work site into a pre-trained face recognition model, extracting facial features in the image of the work site through the face recognition model, matching the facial features with a pre-configured face feature library, and obtaining a face recognition result output by the face recognition model;

[0145] The face recognition result includes the staff members who passed the face recognition and their vacancy status.

[0146] In some exemplary embodiments, the clothing safety identification module 420 is specifically configured to:

[0147] Based on the image of the work site, the worker who has passed the face recognition is identified in terms of a safety helmet, work clothes, vest, insulating gloves and insulating shoes to obtain the clothing safety identification result.

[0148] In some exemplary embodiments, the clothing safety identification module 420 is specifically configured to:

[0149] Input the image of the work site into a pre-trained helmet recognition model, extract features of different levels of the image of the work site through the helmet recognition model, fuse the features of different levels to obtain feature maps of different scales, and identify whether the worker who has passed face recognition is wearing a helmet based on the feature maps of different scales to obtain whether the helmet is worn;

[0150] In response to determining that the worker who has passed the face recognition is wearing a safety helmet, identifying whether the color of the safety helmet meets the preset safety helmet color, and obtaining whether the color of the safety helmet is correct;

[0151] The helmet recognition result includes whether the helmet is worn and whether the helmet is of the correct color;

[0152] Then, the clothing safety identification result includes the helmet identification result.

[0153] In some exemplary embodiments, the clothing safety identification module 420 is specifically configured to:

[0154] Inputting the image of the work site into a pre-trained work clothes recognition model, performing human body position recognition on the image of the work site through the work clothes recognition model to obtain a human body position recognition result, cropping the image of the work site based on the human body position recognition result to obtain a human body range image, classifying and distinguishing the human body image in the human body range image to obtain a work clothes recognition result, wherein the work clothes recognition result includes whether the work clothes are worn and whether the work clothes are worn in a standard manner;

[0155] Then, the clothing safety identification result includes the work clothes identification result.

[0156] In some exemplary embodiments, the clothing safety identification module 420 is specifically configured to:

[0157] Inputting the image of the work site into a pre-trained vest recognition model, performing personnel target detection on the image of the work site through the vest recognition model to obtain a personnel target, performing personnel attribute recognition on the personnel target to obtain a vest recognition result, wherein the vest recognition result includes whether the vest is worn;

[0158] Then, the clothing safety identification result includes the vest identification result, and the identity category of the staff member is determined based on the clothing safety identification result, and the identity category includes a guardian and an operator, including:

[0159] The staff member wearing a vest is determined to be the guardian, and the staff member not wearing a vest is determined to be the operator.

[0160] In some exemplary embodiments, the clothing safety identification module 420 is specifically configured to:

[0161] Inputting the image of the work site into a pre-trained insulating glove recognition model, performing human posture recognition on the image of the work site through the insulating glove recognition model to obtain a human posture recognition result, extracting a hand area from the human posture recognition result, performing insulating glove recognition on the hand area, and obtaining an insulating glove recognition result;

[0162] Then, the clothing safety identification result includes the insulating gloves identification result.

[0163] In some exemplary embodiments, the clothing safety identification module 420 is specifically configured to:

[0164] Inputting the image of the work site into a pre-trained insulating shoe recognition model, performing insulating shoe recognition on the image of the work site through the insulating shoe recognition model, and obtaining an insulating shoe recognition result;

[0165] Then, the clothing safety identification result includes the insulating shoe identification result.

[0166] In some exemplary embodiments, the tool safety identification module 430 is specifically configured to:

[0167] The image of the work site is input into a pre-trained tool safety recognition model, and the tool safety recognition model is used to detect whether there are preset types of safety tools in the image of the work site to obtain a tool safety recognition result.

[0168] For the convenience of description, the above system is described by dividing the functions into various modules. Of course, when implementing the present disclosure, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0169] The system of the above-mentioned embodiment is used to implement the corresponding work site safety detection method in any of the above-mentioned embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0170] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments, the present disclosure also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the work site safety detection method described in any of the above embodiments is implemented.

[0171] Figure 5 A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are connected to each other through the bus 1050 in the device.

[0172] The processor 1010 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0173] The memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0174] The input / output interface 1030 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0175] The communication interface 1040 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WIFI, Bluetooth, etc.).

[0176] The bus 1050 includes a path that transmits information between the various components of the device (eg, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0177] It should be noted that, although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040 and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0178] The electronic device of the above-mentioned embodiment is used to implement the corresponding work site safety detection method in any of the above-mentioned embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0179] The memory 1020 stores machine-readable instructions executable by the processor 1010. When the electronic device is running, the processor 1010 communicates with the memory 1020 via the bus 1030, so that the processor 1010 executes the following instructions when running:

[0180] Acquire an image of the work site, perform facial recognition on personnel at the work site based on the image of the work site, obtain a facial recognition result, and determine the staff member who passes the facial recognition;

[0181] Based on the image of the work site, the worker who has passed the face recognition is subjected to clothing safety recognition to obtain a clothing safety recognition result, and the identity category of the worker is determined based on the clothing safety recognition result, wherein the identity category includes a guardian and an operator;

[0182] Performing tool safety identification on tools at the work site based on the image of the work site to obtain a tool safety identification result;

[0183] The face recognition result, the clothing safety recognition result and the tool safety recognition result are sent to a designated terminal device, and the terminal device sends a work group obtained by matching the guardian and the operator, as well as safety recommendations and work tasks for the work group.

[0184] In a possible implementation, in the instructions executed by the processor 1010, performing face recognition on personnel at the work site based on the image of the work site, obtaining face recognition results, and determining the staff member who passed the face recognition includes:

[0185] Inputting the image of the work site into a pre-trained face recognition model, extracting facial features in the image of the work site through the face recognition model, matching the facial features with a pre-configured face feature library, and obtaining a face recognition result output by the face recognition model;

[0186] The face recognition result includes the staff members who passed the face recognition and their vacancy status.

[0187] In a possible implementation, in the instructions executed by the processor 1010, performing clothing safety identification on the worker who has passed face recognition based on the image of the work site to obtain a clothing safety identification result includes:

[0188] Based on the image of the work site, the worker who has passed the face recognition is identified in terms of a safety helmet, work clothes, vest, insulating gloves and insulating shoes to obtain the clothing safety identification result.

[0189] In a possible implementation, the instructions executed by the processor 1010 include performing safety helmet recognition on the worker who has passed face recognition based on the image of the work site, including:

[0190] Input the image of the work site into a pre-trained helmet recognition model, extract features of different levels of the image of the work site through the helmet recognition model, fuse the features of different levels to obtain feature maps of different scales, and identify whether the worker who has passed face recognition is wearing a helmet based on the feature maps of different scales to obtain whether the helmet is worn;

[0191] In response to determining that the worker who has passed the face recognition is wearing a safety helmet, identifying whether the color of the safety helmet meets the preset safety helmet color, and obtaining whether the color of the safety helmet is correct;

[0192] The helmet recognition result includes whether the helmet is worn and whether the helmet is of the correct color;

[0193] Then, the clothing safety identification result includes the helmet identification result.

[0194] In a possible implementation, the instructions executed by the processor 1010 include performing work clothes recognition on the worker who has passed face recognition based on the image of the work site, including:

[0195] Inputting the image of the work site into a pre-trained work clothes recognition model, performing human body position recognition on the image of the work site through the work clothes recognition model to obtain a human body position recognition result, cropping the image of the work site based on the human body position recognition result to obtain a human body range image, classifying and distinguishing the human body image in the human body range image to obtain a work clothes recognition result, wherein the work clothes recognition result includes whether the work clothes are worn and whether the work clothes are worn in a standard manner;

[0196] Then, the clothing safety identification result includes the work clothes identification result.

[0197] In a possible implementation, the instructions executed by the processor 1010 include performing vest recognition on the worker who has passed face recognition based on the image of the work site, including:

[0198] Inputting the image of the work site into a pre-trained vest recognition model, performing personnel target detection on the image of the work site through the vest recognition model to obtain a personnel target, performing personnel attribute recognition on the personnel target to obtain a vest recognition result, wherein the vest recognition result includes whether the vest is worn;

[0199] Then, the clothing safety identification result includes the vest identification result, and the identity category of the staff member is determined based on the clothing safety identification result, and the identity category includes a guardian and an operator, including:

[0200] The staff member wearing a vest is determined to be the guardian, and the staff member not wearing a vest is determined to be the operator.

[0201] In a possible implementation, the instructions executed by the processor 1010 include performing insulating glove recognition on the worker who has passed face recognition based on the image of the work site, including:

[0202] Inputting the image of the work site into a pre-trained insulating glove recognition model, performing human posture recognition on the image of the work site through the insulating glove recognition model to obtain a human posture recognition result, extracting a hand area from the human posture recognition result, performing insulating glove recognition on the hand area, and obtaining an insulating glove recognition result;

[0203] Then, the clothing safety identification result includes the insulating gloves identification result.

[0204] In a possible implementation, the instructions executed by the processor 1010 include identifying insulating shoes of the worker who has passed face recognition based on the image of the work site, including:

[0205] Inputting the image of the work site into a pre-trained insulating shoe recognition model, performing insulating shoe recognition on the image of the work site through the insulating shoe recognition model, and obtaining an insulating shoe recognition result;

[0206] Then, the clothing safety identification result includes the insulating shoe identification result.

[0207] In a possible implementation manner, in the instructions executed by the processor 1010, performing tool safety identification on tools at the work site based on the image of the work site to obtain a tool safety identification result includes:

[0208] The image of the work site is input into a pre-trained tool safety recognition model, and the tool safety recognition model is used to detect whether there are preset types of safety tools in the image of the work site to obtain a tool safety recognition result.

[0209] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present disclosure also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the work site safety detection method described in any of the above embodiments.

[0210] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0211] The above-mentioned non-transitory computer-readable storage medium can be any available medium or data storage device that can be accessed by a computer, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (such as CD, DVD, BD, HVD, etc.), and semiconductor storage (such as ROM, EPROM, EEPROM, non-volatile memory (NAND FLASH), solid-state drive (SSD)), etc.

[0212] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the work site safety detection method described in any embodiment in the above exemplary method part, and have the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0213] Based on the same inventive concept, corresponding to the work site safety detection method described in any of the above embodiments, the present disclosure also provides a computer program product, which includes computer program instructions. In some embodiments, the computer program instructions can be executed by one or more processors of a computer so that the computer and / or the processor execute the work site safety detection method. Corresponding to the execution subject corresponding to each step in each embodiment of the work site safety detection method, the processor that executes the corresponding step can belong to the corresponding execution subject.

[0214] The computer program product of the above embodiment is used to enable the computer and / or the processor to execute the work site safety detection method described in any of the above embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0215] Those skilled in the art will appreciate that the embodiments of the present disclosure may be implemented as a system, method, or computer program product. Therefore, the present disclosure may be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." In addition, in some embodiments, the present disclosure may also be implemented in the form of a computer program product in one or more computer-readable media, which contains computer-readable program code.

[0216] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive examples) of computer-readable storage media may include, for example: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device.

[0217] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0218] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0219] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0220] It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine, and these computer program instructions are executed by a computer or other programmable data processing device to produce a device that implements the functions / operations specified in the boxes in the flowchart and / or block diagram.

[0221] These computer program instructions may also be stored in a computer-readable medium that enables a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable medium produce a product that includes an instruction device that implements the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0222] Computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby enabling the instructions executed on the computer or other programmable device to provide a process for implementing the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0223] In addition, although the operations of the disclosed method are described in a particular order in the accompanying drawings, this does not require or imply that the operations must be performed in this particular order, or that all the operations shown must be performed to achieve the desired results. On the contrary, the steps depicted in the flow chart can be performed in a different order. Additionally or alternatively, some steps can be omitted, multiple steps can be combined into one step, and / or one step can be decomposed into multiple steps.

[0224] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0225] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0226] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application (including the claims) is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0227] In addition, to simplify the description and discussion, and in order not to make the embodiments of the present application difficult to understand, the known power supply / ground connection with the integrated circuit (IC) chip and other components may or may not be shown in the provided drawings. In addition, the device can be shown in the form of a block diagram to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform to be implemented in the embodiments of the present application (that is, these details should be fully within the scope of understanding of those skilled in the art). In the case of elaborating specific details (e.g., circuits) to describe exemplary embodiments of the present application, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details or when these specific details are changed. Therefore, these descriptions should be considered to be illustrative rather than restrictive.

[0228] Although the present application has been described in conjunction with specific embodiments of the present application, many replacements, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.

[0229] The embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the scope of protection of the present application.

[0230] Although the spirit and principle of the present disclosure have been described with reference to several specific embodiments, it should be understood that the present disclosure is not limited to the disclosed specific embodiments, and the division of various aspects does not mean that the features in these aspects cannot be combined to benefit, and such division is only for the convenience of expression. The present disclosure is intended to cover various modifications and equivalent arrangements included in the spirit and scope of the attached claims. The scope of the attached claims conforms to the broadest interpretation, thereby including all such modifications and equivalent structures and functions.

Claims

1. A method for safety detection at a work site, characterized in that: include: Acquire an image of the work site, perform facial recognition on personnel at the work site based on the image of the work site, obtain a facial recognition result, and determine the staff member who passes the facial recognition; Based on the image of the work site, the worker who has passed the face recognition is subjected to clothing safety recognition to obtain a clothing safety recognition result, and the identity category of the worker is determined based on the clothing safety recognition result, wherein the identity category includes a guardian and an operator; Performing tool safety identification on tools at the work site based on the image of the work site to obtain a tool safety identification result; The face recognition result, the clothing safety recognition result and the tool safety recognition result are sent to a designated terminal device, and the terminal device sends a work group obtained by matching the guardian and the operator, as well as safety recommendations and work tasks for the work group.

2. The method according to claim 1, characterized in that The performing face recognition on the personnel at the work site based on the image of the work site, obtaining face recognition results, and determining the staff member who passes the face recognition, includes: Inputting the image of the work site into a pre-trained face recognition model, extracting facial features in the image of the work site through the face recognition model, matching the facial features with a pre-configured face feature library, and obtaining a face recognition result output by the face recognition model; The face recognition result includes the staff members who passed the face recognition and their vacancy status.

3. The method according to claim 1, characterized in that The performing clothing safety identification on the worker who has passed the face recognition based on the image of the work site to obtain the clothing safety identification result includes: Based on the image of the work site, the worker who has passed the face recognition is identified in terms of a safety helmet, work clothes, vest, insulating gloves and insulating shoes to obtain the clothing safety identification result.

4. The method according to claim 3, characterized in that: Performing helmet recognition on the worker who has passed face recognition based on the image of the work site includes: Inputting the image of the work site into a pre-trained helmet recognition model, extracting features of different levels of the image of the work site through the helmet recognition model, fusing the features of different levels to obtain feature maps of different scales, and identifying whether the worker who has passed face recognition is wearing a helmet based on the feature maps of different scales to obtain whether the helmet is worn; In response to determining that the worker who has passed the face recognition is wearing a safety helmet, identifying whether the color of the safety helmet meets the preset safety helmet color, and obtaining whether the color of the safety helmet is correct; The helmet recognition result includes whether the helmet is worn and whether the helmet is of the correct color; Then, the clothing safety identification result includes the helmet identification result.

5. The method according to claim 3, characterized in that: Based on the image of the work site, the work clothes of the worker who has passed the face recognition are recognized, including: Inputting the image of the work site into a pre-trained work clothes recognition model, performing human body position recognition on the image of the work site through the work clothes recognition model to obtain a human body position recognition result, cropping the image of the work site based on the human body position recognition result to obtain a human body range image, classifying and distinguishing the human body image in the human body range image to obtain a work clothes recognition result, wherein the work clothes recognition result includes whether the work clothes are worn and whether the work clothes are worn in a standard manner; Then, the clothing safety identification result includes the work clothes identification result.

6. The method according to claim 3, characterized in that Performing vest recognition on the worker who has passed face recognition based on the image of the work site includes: Inputting the image of the work site into a pre-trained vest recognition model, performing personnel target detection on the image of the work site through the vest recognition model to obtain a personnel target, performing personnel attribute recognition on the personnel target to obtain a vest recognition result, wherein the vest recognition result includes whether the vest is worn; Then, the clothing safety identification result includes the vest identification result, and the identity category of the staff member is determined based on the clothing safety identification result, and the identity category includes a guardian and an operator, including: The staff member wearing a vest is determined to be the guardian, and the staff member not wearing a vest is determined to be the operator.

7. The method according to claim 3, characterized in that Based on the image of the work site, the insulating gloves of the worker who has passed the face recognition are identified, including: Inputting the image of the work site into a pre-trained insulating glove recognition model, performing human posture recognition on the image of the work site through the insulating glove recognition model to obtain a human posture recognition result, extracting a hand area from the human posture recognition result, performing insulating glove recognition on the hand area, and obtaining an insulating glove recognition result; Then, the clothing safety identification result includes the insulating gloves identification result.

8. The method according to claim 3, characterized in that Based on the image of the work site, the insulating shoes of the worker who has passed the face recognition are identified, including: Inputting the image of the work site into a pre-trained insulating shoe recognition model, performing insulating shoe recognition on the image of the work site through the insulating shoe recognition model, and obtaining an insulating shoe recognition result; Then, the clothing safety identification result includes the insulating shoe identification result.

9. The method according to claim 1, characterized in that: The performing tool safety identification on the tools at the work site based on the image of the work site to obtain a tool safety identification result includes: The image of the work site is input into a pre-trained tool safety recognition model, and the tool safety recognition model is used to detect whether there are preset types of safety tools in the image of the work site to obtain a tool safety recognition result.

10. A work site safety detection system, characterized in that: include: A face recognition module is configured to obtain an image of the work site, perform face recognition on personnel at the work site based on the image of the work site, obtain a face recognition result, and determine a staff member who passes the face recognition; a clothing safety identification module, configured to perform clothing safety identification on the worker who has passed face recognition based on the image of the work site, obtain a clothing safety identification result, and determine the identity category of the worker based on the clothing safety identification result, wherein the identity category includes a guardian and an operator; A tool safety identification module is configured to perform tool safety identification on the tools at the work site based on the image of the work site to obtain a tool safety identification result; The recognition result, safety suggestion and work task transmission module is configured to send the face recognition result, the clothing safety recognition result and the tool safety recognition result to a designated terminal device, and receive the work group obtained by matching the guardian and the operator, as well as the safety suggestions and work tasks for the work group, sent by the terminal device.

Images