A personal safety wearable identification method and system

Abstract

The present application discloses a method for identifying personal safety wear. By analyzing the video captured by the camera, the moving target is determined based on the multi-target motion detection technology. The moving target is scanned for facial recognition based on the face recognition technology to screen out human targets. Finally, the protective equipment identification library is used to perform feature recognition of the protective equipment of the human targets. The present application also discloses a personal safety wear identification system. The captured video image is sent to a motion detection module, a face recognition module, and a protective equipment identification module. The motion detection module is used to identify the moving target in the video image, the face recognition module is used to screen out human targets, and the protective equipment identification module is used to identify the protective equipment of the human target. This not only saves the workload of the security inspectors, but also eliminates the problem of inspection gaps and can continuously monitor the safety of the staff wearing protective equipment.

Description

Technical Field

[0001] The present invention relates to the field of safety supervision technology, and in particular to a personal safety wear identification method and system. Background Art

[0002] For many production jobs, production activities are dangerous. In order to ensure the personal safety of workers, they are usually required to wear various protective equipment, such as safety helmets and safety belts. However, in the actual production process, due to the inconvenience of human supervision, workers will take the opportunity to remove protective equipment for reasons such as comfort. This behavior poses a huge threat to the personal safety of the workers themselves.

[0003] In order to solve the above problems, the existing technology adopts the scheme of setting up safety inspectors at the access control points of the production site or having safety inspectors patrol the production site to complete the supervision of the staff wearing protective equipment. This method is relatively wasteful of manpower and it is easy for the staff to remove the safety equipment during the inspection by the safety inspectors. In order to avoid the above problems, there is an urgent need for a method or system that can monitor the staff wearing safety equipment in real time. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system capable of monitoring in real time whether workers are wearing safety equipment.

[0005] Therefore, the present invention discloses a personal safety wear identification method, which uses a display module, and the method includes:

[0006] Obtain the video image captured by the camera and determine the moving target based on the multi-target motion detection technology;

[0007] Performing facial recognition scanning on the moving target based on face recognition technology to screen out human targets;

[0008] According to a preset protective equipment identification library, scanning and determining whether there are identification features of protective equipment on the human target;

[0009] If no identification feature of the protective gear is scanned on the human target and the duration is greater than a preset value, it is determined that the human target is not wearing protective gear, and the display module is marked.

[0010] In some embodiments of the present application, the contents of the protective equipment identification library are disclosed, and based on the contents of the protective equipment identification library, a method for determining whether the protective equipment is present on the human target is disclosed. The method for determining whether the protective equipment is present on the human target includes:

[0011] The protective gear identification library includes: protective gear color feature information, protective gear position information and protective gear size feature information;

[0012] Scanning a corresponding position on the human body target according to the protective gear position information, analyzing and determining a protective gear block, so that a color feature of the protective gear block conforms to the color feature information of the protective gear;

[0013] The area of the protective gear block is determined based on the ratio of the protective gear block to the human target. If the difference between the area of the protective gear block and the equivalent amount in the size characteristic information of the protective gear is less than a preset value, it is determined that the protective gear exists on the human target.

[0014] In some embodiments of the present application, another content of the protective equipment identification library is disclosed, and based on the content of the protective equipment identification library, another method for determining whether the protective equipment is present on the human target based on the content of the protective equipment identification library is disclosed. The method for determining whether the protective equipment is present on the human target includes:

[0015] The protective gear identification library includes: protective gear position information and protective gear edge structure information;

[0016] intercepting a regional image of the human target, and performing edge segmentation on the regional image of the human target according to an image edge detection technology to generate a first edge information value;

[0017] According to the protective equipment position information, intercepting the protective equipment block corresponding to the position of the human target;

[0018] Performing edge segmentation on the protective gear block according to an image edge detection technology to generate a second edge information value, and comparing the second edge information value with the first edge information value;

[0019] If the difference between the second edge information value and the first edge information value is smaller than a preset value, it is determined that the protective equipment exists on the human target.

[0020] The present application discloses a method for identifying personal safety wear. By analyzing the video captured by the camera, the moving target is determined based on the multi-target motion detection technology. The moving target is scanned for face recognition based on the face recognition technology to screen out the human target. Finally, the protective equipment of the human target is feature-recognized based on the protective equipment recognition library, and then it is determined whether the human target is wearing protective equipment. The method no longer requires safety inspectors to frequently conduct on-site inspections, thereby reducing the workload of safety inspectors.

[0021] A personal safety wearable identification system, the system comprising:

[0022] A camera module for capturing the scene;

[0023] A display module, configured to display the video image captured by the camera module;

[0024] A motion detection module, configured to identify moving objects within the video image;

[0025] A face recognition module is used to perform face recognition scanning on the moving target to screen out human targets;

[0026] A protective gear identification module scans and determines whether there are identification features of protective gear on the human target based on a preset protective gear identification library; if no identification features of protective gear are scanned on the human target and the duration is greater than a preset value, it is determined that the human target is not wearing protective gear, and the display module displays a mark.

[0027] In some embodiments of the present application, a specific identification hole content of the protective gear is disclosed, and a method for determining whether the human target is wearing the protective gear based on the content of the protective gear identification library is also disclosed, wherein the content of the protective gear identification library includes: protective gear color feature information, protective gear position information, and protective gear size feature information;

[0028] The protective gear identification module determines the position of scanning the human target according to the protective gear position information;

[0029] The protective gear recognition module intercepts the protective gear block in the video image according to the protective gear color feature information;

[0030] The protective gear identification module compares the size feature information of the protective gear with the protective gear block, and determines whether the protective gear exists on the human target based on the comparison result.

[0031] In some embodiments of the present application, in order to determine the comparison result between the size feature information of the protective gear and the protective gear block, a method for comparing the size feature information of the protective gear and the protective gear block is disclosed. The protective gear identification module compares the size feature information of the protective gear with the protective gear block. The method includes:

[0032] The protective gear identification module determines the area of the protective gear block based on the ratio of the protective gear block to the human target. If the difference between the area of the protective gear block and the equivalent amount in the size feature information of the protective gear is less than a preset value, it is determined that the protective gear is present on the human target.

[0033] In some embodiments of the present application, a method for determining whether the protective gear is present on the human target is disclosed. Therefore, the system is improved. The system further includes an image edge recognition module. The method of using the image edge recognition module to determine whether the protective gear is present on the human target includes:

[0034] The protective gear identification library includes: protective gear position information and protective gear edge structure information;

[0035] The image edge recognition module intercepts the regional image of the human target and performs edge segmentation on the regional image of the human target according to an image edge detection technology to generate a first edge information value;

[0036] The protective gear identification module intercepts the protective gear block corresponding to the position of the human target according to the protective gear position information;

[0037] The image edge recognition module divides the edge of the protective equipment block according to the image edge detection technology to generate a second edge information value, and compares the second edge information value with the first edge information value. If the difference between the second edge information value and the first edge information value is less than a preset value, it is determined that the protective equipment is present on the human target.

[0038] In some embodiments of the present application, in order to enable safety supervisors to promptly identify persons who are not properly wearing safety gear, a method is disclosed for enabling the display module to mark and display persons who are not properly wearing safety gear. The method for the display module to mark and display the human target who is not wearing protective gear includes:

[0039] The motion monitoring module determines the moving target according to the multi-target monitoring technology and generates target coordinates for the moving target;

[0040] If the protective gear recognition module determines that the human target is not wearing protective gear, the display module is driven to generate a marking frame at the position of the target coordinates according to the target coordinates;

[0041] The marking frame is adjusted according to the size of the human target so that the marking frame is displayed corresponding to the human target.

[0042] The present application discloses a personal safety wear identification system, which shoots a scene through a camera module and sends the shot video image to a motion detection module, a face recognition module and a protective equipment recognition module. The motion detection module is used to identify moving targets in the video image, the face recognition module is used to screen human targets, and the protective equipment recognition module is used to identify the protective equipment of human targets. This realizes real-time safety monitoring of the protective equipment worn by on-site personnel, which not only saves the workload of safety inspectors, but also eliminates the problem of inspection gaps, and can continuously monitor the safety of protective equipment worn by staff. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A conceptual diagram of steps for constructing a personal safety wearable identification system in the implementation of this application;

[0044] Figure 2 This is a step diagram of a method for determining whether protective gear is worn on a personal target in an embodiment of the present application;

[0045] Figure 3 This is another method step diagram for determining whether protective gear is on a personal target in an embodiment of the present application. DETAILED DESCRIPTION

[0046] The technical solution of the present invention is further described below with reference to the accompanying drawings and embodiments.

[0047] Unless otherwise defined, the technical or scientific terms used in the present invention shall have the usual meanings understood by persons of ordinary skill in the field to which the present invention belongs. The words "first", "second" and similar terms used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. Words such as "include" or "comprise" mean that the elements or objects preceding the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Words such as "connect" or "connected" are not limited to physical or mechanical connections, but may 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 object being described changes, the relative positional relationship may also change accordingly.

[0048] Example:

[0049] The purpose of the present invention is to provide a method and system capable of monitoring in real time whether workers are wearing safety equipment.

[0050] Therefore, the present invention discloses a personal safety wear identification method, which uses a display module, and the method includes:

[0051] Step 1: Obtain the video image captured by the camera and determine the moving target based on the multi-target motion detection technology.

[0052] Step 2: Perform face recognition scanning on the moving target based on face recognition technology to screen out human targets.

[0053] Step 3: Scan and determine whether there are identification features of protective gear on the human target according to the preset protective gear identification library. If no identification features of protective gear are scanned on the human target and the duration is greater than a preset value, it is determined that the human target is not wearing protective gear, and the display module mark is displayed.

[0054] In step 2, an image of the protective gear is obtained and preprocessed, such as normalization and wavelet decomposition. The preprocessed image retains the most essential part of the protective gear that is most beneficial for feature extraction, and filters out some external interference, such as light. Then, a feature extraction algorithm is selected to extract features from the preprocessed image, thereby forming feature information of the protective gear.

[0055] In some embodiments of the present application, in order to implement the determination of the identification features of the protective gear on the human target in step 3, the contents of the protective gear identification library are disclosed. Based on the contents of the protective gear identification library, a method for determining whether the protective gear is present on the human target is disclosed. The method for determining whether the protective gear is present on the human target includes:

[0056] The content of the protective gear identification library includes: protective gear color feature information, protective gear position information and protective gear size feature information.

[0057] a. According to the protective gear position information, the corresponding position on the human target is scanned, and the protective gear block is determined by analysis so that the color characteristics of the protective gear block conform to the color characteristic information of the protective gear.

[0058] b. Determine the area of the protective gear block based on the ratio of the protective gear block to the human target. If the difference between the area of the protective gear block and the equivalent amount in the dimensional characteristic information of the protective gear is less than a preset value, it is determined that the protective gear is present on the human target.

[0059] In some embodiments of the present application, in order to implement the determination of the identification features of the protective gear on the human target in step 3, another content of the protective gear identification library is disclosed, and based on the content of the protective gear identification library, another method for determining whether the protective gear is present on the human target based on the content of the protective gear identification library is disclosed. The method for determining whether the protective gear is present on the human target includes:

[0060] The content of the protective equipment identification library includes: protective equipment position information and protective equipment edge structure information.

[0061] c. intercepting a regional image of the human target, and performing edge segmentation on the regional image of the human target according to an image edge detection technique to generate a first edge information value.

[0062] d. According to the protective equipment position information, intercept the protective equipment block corresponding to the position of the human target.

[0063] e. Performing edge segmentation on the protective gear block according to image edge detection technology to generate a second edge information value, and comparing the second edge information value with the first edge information value.

[0064] f. If the difference between the second edge information value and the first edge information value is less than a preset value, it is determined that the protective equipment is present on the human target.

[0065] The present application discloses a method for identifying personal safety wear. By analyzing the video captured by the camera, the moving target is determined based on the multi-target motion detection technology. The moving target is scanned for face recognition based on the face recognition technology to screen out the human target. Finally, the protective equipment of the human target is feature-recognized based on the protective equipment recognition library, and then it is determined whether the human target is wearing protective equipment. The method no longer requires safety inspectors to frequently conduct on-site inspections, thereby reducing the workload of safety inspectors.

[0066] In order to further illustrate the technical solution of the present application, a conceptual step for constructing a personal wearable wear identification system is now disclosed.

[0067] The system is required to be able to conduct video surveillance of the site, identify whether the staff are wearing protective equipment through system automation, and continuously monitor the staff.

[0068] like Figure 1 , the method steps include:

[0069] S101, obtaining a video image captured by a camera, and determining a moving target based on a multi-target motion detection technology.

[0070] S102, performing face recognition scanning on the moving target based on face recognition technology to screen out human targets.

[0071] S103, according to a preset protective equipment identification library, scanning to determine whether there are identification features of protective equipment on the human body target.

[0072] S104: If no identification feature of the protective gear is scanned on the human target and the duration is greater than a preset value, it is determined that the human target is not wearing protective gear, and the display module displays a mark.

[0073] In S103, the content of the protective gear identification library includes color feature information of the protective gear, position information of the protective gear, and size feature information of the protective gear.

[0074] like Figure 2 The method of using the content of the protective equipment identification library to determine whether the protective equipment is on the human target includes:

[0075] S105 , scanning a corresponding position on the human body target according to the protective gear position information, analyzing and determining a protective gear block, so that a color feature of the protective gear block conforms to the color feature information of the protective gear.

[0076] S106: Determine the area of the protective gear block according to the ratio of the protective gear block to the human body target.

[0077] S107: If the difference between the area of the protective gear block and the equivalent amount in the size characteristic information of the protective gear is less than a preset value, it is determined that the protective gear exists on the human target.

[0078] Another protective gear identification library is also provided, which includes protective gear position information and protective gear edge structure information, such as Figure 3 ,The method of using this protective equipment recognition library to determine whether a human target is wearing protective equipment includes:

[0079] S201, intercepting a region image of the human target, and performing edge segmentation on the region image of the human target according to an image edge detection technology to generate a first edge information value;

[0080] S202: According to the protective equipment position information, intercept a protective equipment block corresponding to the position of the human body target.

[0081] S203 , performing edge segmentation on the protective gear block according to an image edge detection technology to generate a second edge information value, and comparing the second edge information value with the first edge information value.

[0082] S204: If the difference between the second edge information value and the first edge information value is smaller than a preset value, it is determined that the protective equipment exists on the human body target.

[0083] In some embodiments of the present application, a personal safety wear identification system is also disclosed, which includes a camera module, a display module, a motion detection module, a face recognition module and a protective equipment recognition module.

[0084] The camera module is used to shoot the scene; the display module is used to display the video image shot by the camera module; the motion detection module is used to identify the moving targets in the video image; the face recognition module is used to perform face recognition scanning on the moving targets to screen out human targets.

[0085] A protective gear identification module scans and determines whether there are identification features of protective gear on the human target based on a preset protective gear identification library; if no identification features of protective gear are scanned on the human target and the duration is greater than a preset value, it is determined that the human target is not wearing protective gear, and the display module displays a mark.

[0086] In some embodiments of the present application, a specific identification hole content of the protective gear is disclosed, and a method for judging whether the human target is wearing the protective gear based on the content of the protective gear identification library is also disclosed, wherein the content of the protective gear identification library includes: protective gear color feature information, protective gear position information and protective gear size feature information.

[0087] The protective equipment identification module determines a position for scanning the human target according to the protective equipment position information.

[0088] The protective gear recognition module intercepts the protective gear block in the video image according to the protective gear color feature information.

[0089] The protective gear identification module compares the size feature information of the protective gear with the protective gear block, and determines whether the protective gear exists on the human target based on the comparison result.

[0090] In some embodiments of the present application, in order to determine the comparison result between the size feature information of the protective gear and the protective gear block, a method for comparing the size feature information of the protective gear and the protective gear block is disclosed. The protective gear identification module compares the size feature information of the protective gear with the protective gear block. The method includes:

[0091] The protective gear identification module determines the area of the protective gear block based on the ratio of the protective gear block to the human target. If the difference between the area of the protective gear block and the equivalent amount in the size feature information of the protective gear is less than a preset value, it is determined that the protective gear is present on the human target.

[0092] In some embodiments of the present application, a method for determining whether the protective gear is present on the human target is disclosed. Therefore, the system is improved. The system further includes an image edge recognition module. The method of using the image edge recognition module to determine whether the protective gear is present on the human target includes:

[0093] The content of the protective equipment identification library includes: protective equipment position information and protective equipment edge structure information.

[0094] The image edge recognition module intercepts the regional image of the human target and performs edge division on the regional image of the human target according to an image edge detection technology to generate a first edge information value.

[0095] The protective equipment identification module intercepts the protective equipment block corresponding to the position of the human target according to the protective equipment position information.

[0096] The image edge recognition module divides the edge of the protective equipment block according to the image edge detection technology to generate a second edge information value, and compares the second edge information value with the first edge information value. If the difference between the second edge information value and the first edge information value is less than a preset value, it is determined that the protective equipment is present on the human target.

[0097] In some embodiments of the present application, in order to enable safety supervisors to promptly identify persons who are not properly wearing safety gear, a method is disclosed for enabling the display module to mark and display persons who are not properly wearing safety gear. The method for the display module to mark and display the human target who is not wearing protective gear includes:

[0098] The motion monitoring module determines the moving target according to the multi-target monitoring technology and generates target coordinates for the moving target.

[0099] If the protective gear recognition module determines that the human target is not wearing protective gear, the display module is driven to generate a marking frame at the position of the target coordinates according to the target coordinates;

[0100] The marking frame is adjusted according to the size of the human target so that the marking frame is displayed corresponding to the human target.

[0101] The present application discloses a personal safety wear identification system, which shoots a scene through a camera module and sends the shot video image to a motion detection module, a face recognition module and a protective equipment recognition module. The motion detection module is used to identify moving targets in the video image, the face recognition module is used to screen human targets, and the protective equipment recognition module is used to identify the protective equipment of human targets. This realizes real-time safety monitoring of the protective equipment worn by on-site personnel, which not only saves the workload of safety inspectors, but also eliminates the problem of inspection gaps, and can continuously monitor the safety of protective equipment worn by staff.

[0102] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit the same. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solutions of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A personal safety wear identification method, characterized in that: The application has a display module, and the method includes: Obtain the video image captured by the camera and determine the moving target based on the multi-target motion detection technology; Performing facial recognition scanning on the moving target based on face recognition technology to screen out human targets; According to a preset protective equipment identification library, scanning and determining whether the identification features of the protective equipment exist on the human target; If no identification feature of the protective gear is scanned on the human target and the duration is greater than a preset value, it is determined that the human target is not wearing protective gear, and the display module displays a mark; The method for determining whether the protective gear exists on the human target includes: The protective gear identification library includes: protective gear color feature information, protective gear position information and protective gear size feature information; Scanning a corresponding position on the human body target according to the protective gear position information, analyzing and determining a protective gear block, so that a color feature of the protective gear block conforms to the color feature information of the protective gear; Determining the area of the protective gear block based on the ratio of the protective gear block to the human target; and determining that the protective gear is present on the human target if a difference between the area of the protective gear block and an equivalent amount in the dimensional characteristic information of the protective gear is less than a preset value; The method for determining whether the protective gear exists on the human target includes: The protective gear identification library includes: protective gear position information and protective gear edge structure information; intercepting a regional image of the human target, and performing edge segmentation on the regional image of the human target according to an image edge detection technology to generate a first edge information value; According to the protective equipment position information, intercepting the protective equipment block corresponding to the position of the human target; Performing edge segmentation on the protective gear block according to an image edge detection technology to generate a second edge information value, and comparing the second edge information value with the first edge information value; If the difference between the second edge information value and the first edge information value is less than a preset value, it is determined that the protective equipment exists on the human target; The method for the display module to mark and display the human target without wearing protective equipment includes: The motion monitoring module determines the moving target according to the multi-target monitoring technology and generates target coordinates for the moving target; If the protective gear recognition module determines that the human target is not wearing protective gear, the display module is driven according to the target coordinates to generate a marking frame at the position of the target coordinates; The marking frame is adjusted according to the size of the human target so that the marking frame is displayed corresponding to the human target.

2. A personal safety wear identification system, characterized in that: The system comprises: A camera module for capturing the scene; A display module, configured to display the video image captured by the camera module; A motion detection module, configured to identify moving objects within the video image; A face recognition module is used to perform face recognition scanning on the moving target to screen out human targets; a protective gear identification module, which scans and determines whether there is an identification feature of protective gear on the human target based on a preset protective gear identification library; if no identification feature of protective gear is scanned on the human target and the duration is greater than a preset value, it is determined that the human target is not wearing protective gear, and the display module displays a mark; The content of the protective gear identification library includes: protective gear color feature information, protective gear position information and protective gear size feature information; The protective gear identification module determines the position of scanning the human target according to the protective gear position information; The protective gear recognition module intercepts the protective gear block in the video image according to the protective gear color feature information; The protective gear identification module compares the size feature information of the protective gear with the protective gear block, and determines whether the protective gear is on the human target based on the comparison result; The protective gear identification module compares the size feature information of the protective gear with the protective gear block in a method including: The protective gear identification module determines the area of the protective gear block based on the ratio of the protective gear block to the human target, and determines that the protective gear is present on the human target if the difference between the area of the protective gear block and the equivalent amount in the size characteristic information of the protective gear is less than a preset value; The system further includes an image edge recognition module, and a method for applying the image edge recognition module to determine whether the protective gear exists on the human target includes: The protective gear identification library includes: protective gear position information and protective gear edge structure information; The image edge recognition module intercepts the regional image of the human target and performs edge segmentation on the regional image of the human target according to an image edge detection technology to generate a first edge information value; The protective gear identification module intercepts the protective gear block corresponding to the position of the human target according to the protective gear position information; The image edge recognition module divides the protective gear block into edges according to the image edge detection technology to generate a second edge information value, and compares the second edge information value with the first edge information value. If the difference between the second edge information value and the first edge information value is less than a preset value, it is determined that the protective gear is present on the human target; The method for the display module to mark and display the human target without wearing protective equipment includes: The motion monitoring module determines the moving target according to the multi-target monitoring technology and generates target coordinates for the moving target; If the protective gear recognition module determines that the human target is not wearing protective gear, the display module is driven to generate a marking frame at the position of the target coordinates according to the target coordinates; The marking frame is adjusted according to the size of the human target so that the marking frame is displayed corresponding to the human target.

Images