System and method for detecting hand washing and dust removing behaviors of factory workshop workers

Abstract

The invention relates to the field of computer vision, and discloses a system and method for detecting hand washing and dust removal behaviors of factory workshop workers, and the system comprises a QT interactive main control system, a monitoring camera, a server, access control equipment, an image acquisition and processing module, a sending module, and a data storage and alarm module. The image acquisition and processing module, the sending module and the data storage and alarm module are all connected with the QT interactive master control system; the QT interactive master control system is used for controlling the whole process, data interaction of each module and implementation of an algorithm; according to the invention, the hand washing or dust removal condition of the related personnel is monitored by judging the hand washing duration or dust removal duration of the related personnel by utilizing the target detection and face recognition technologies, so that the workload of manually checking the hand washing or dust removal condition is reduced, the hand washing or dust removal checking efficiency is improved, and the sanitation and safety of a workshop are ensured.

Description

Technical Field

[0001] The present invention relates to the field of computer vision, and in particular to a system and method for detecting hand washing and dust removal behaviors of factory workshop workers. Background Art

[0002] As an item that comes into direct or indirect contact with food, the sanitary conditions during the production process of plastic straws directly affect the safety of the final product. Food safety regulations and international quality management system standards (such as ISO 22000, HACCP, etc.) have set strict hygiene requirements for the production of food contact materials. Unwashed hands may carry various microorganisms, such as bacteria and viruses, and dust and impurities on the body may also contain harmful substances. If these pollutants are brought into the production environment, it is very easy to cause direct or cross-contamination of plastic straws, reduce the sanitary quality of the product, and may even turn the product into a food safety hazard, posing a threat to consumer health. In addition, if staff do not perform necessary hand washing and dust removal, they increase the risk of contact with and inhalation of harmful substances. Being in such an environment for a long time may induce or aggravate occupational health problems such as respiratory diseases and skin diseases.

[0003] Currently, the hand washing and dust removal behaviors of factory workshop workers are mainly checked manually. This method requires additional human resources to perform these tasks, which increases the operating costs of enterprises and makes it difficult to achieve continuous monitoring of the workshop around the clock and throughout the entire process. In addition, manual inspections rely heavily on the subjective judgment of inspectors, which may lead to inconsistent inspection results. Summary of the invention

[0004] The purpose of the present invention is to propose a system and method for detecting the hand washing and dust removal behavior of factory workshop workers, so as to solve the technical problem that the existing technology still uses manual monitoring of the hand washing of factory workshop workers, which leads to increased enterprise operating costs.

[0005] Specifically, the present invention provides a system for detecting the hand washing and dust removal behavior of factory workshop workers, including: a QT interactive main control system, a surveillance camera, a server, an access control device, an image acquisition and processing module, a sending module, and a data storage and alarm module;

[0006] The image acquisition and processing module, the sending module, the data storage and alarm module are all connected to the QT interactive main control system; the QT interactive main control system is used to control the overall process, the data interaction of each module and the implementation of the algorithm.

[0007] A method for detecting hand washing and dust removal behavior of factory workshop workers, applied to the system, characterized in that the method comprises the following steps:

[0008] S1, the image acquisition and processing module selects the corresponding model parameters and sets the frame rate through the mode selection unit according to the area where the retrieved camera is located, the image preprocessing unit resizes, normalizes and enhances the collected original image, the target detection algorithm unit performs target detection on the water flow or the person holding the roller in the preprocessed image, and the face recognition unit performs face recognition on the image detected with hand washing or dust removal behavior to obtain the identity information of the person;

[0009] S2, the sending object address selection unit of the sending module selects the sending object by setting the IP address and the port number, and the JSON format information sending unit sends a POST request containing JSON data to the sending object, wherein the JSON data contains the identity information of the person, the situation and time of the hand washing or dust removal behavior;

[0010] S3. After the data storage and alarm module receives the JSON format information sent by the sending module on the server, the personnel hand washing and dust removal situation recording unit modifies the hand washing and dust removal situation and time of the corresponding personnel according to the content in the JSON format information, and the alarm and historical information storage module performs alarm operations and records the personnel who do not wash their hands or dust remove according to the personnel hand washing and dust removal situation recording unit.

[0011] A storage medium stores instructions and data for implementing a method for detecting hand washing and dust removal behavior of factory workshop workers.

[0012] A device for detecting hand washing of factory workshop workers comprises: a processor and a storage medium; the processor loads and executes instructions and data in the storage medium to implement a method for detecting hand washing and dust removal behavior of factory workshop workers.

[0013] The beneficial effect provided by the present invention is that the present invention automatically detects the hand washing and dust removal behaviors of factory workshop workers through target detection and face recognition technology, saves human resources and the operating costs of the enterprise, and ensures the strict hygiene and safety of the production of food contact materials. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a schematic diagram of the system structure of the present invention;

[0015] Figure 2 It is a detailed flow chart of the method of the present invention;

[0016] Figure 3 It is a schematic diagram of the working of the hardware device of an embodiment of the present invention. DETAILED DESCRIPTION

[0017] To make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be further described below with reference to the accompanying drawings.

[0018] Before formally describing the present invention, the scheme of the present invention is first generally described for easy understanding.

[0019] Please refer to Figure 1 , a system for detecting hand washing and dust removal behavior of factory workshop workers provided by the present invention includes: a QT interactive main control system, a monitoring camera, a server, an access control device, an image acquisition and processing module, a sending module, a data storage and alarm module;

[0020] The image acquisition and processing module, the sending module, the data storage and alarm module are all connected to the QT interactive main control system; the QT interactive main control system is used to control the overall process, the data interaction of each module and the implementation of the algorithm.

[0021] It should be noted that the image acquisition and processing module includes a mode selection unit, an image preprocessing unit, a target detection algorithm unit, and a face recognition unit; the mode selection unit includes model loading and frame number setting.

[0022] It should be noted that the sending module includes a sending object address selection unit and a JSON format information sending unit.

[0023] It should be noted that the data storage and alarm module includes a storage unit for key feature values ​​of the faces of workshop staff, a unit for recording hand washing and dust removal conditions, and an alarm and historical information storage unit.

[0024] Optionally, the alarm and history information storage module further includes: an intrusion alarm module, configured to issue an alarm message when the person is not an authorized person.

[0025] The system also includes an access control device, which includes: a second camera acquisition module, used to collect video images of the workshop entrance area; a second face recognition module, used to identify the identity information of the personnel at the workshop entrance; a second sending module, used to send the identity information of the staff entering the workshop and the time of entering the workshop to the server.

[0026] A method for detecting hand washing and dust removal behavior of factory workshop workers, applied to the system, comprises the following steps:

[0027] S1, the image acquisition and processing module selects the corresponding model parameters and sets the frame rate through the mode selection unit according to the area where the retrieved camera is located, the image preprocessing unit resizes, normalizes and enhances the collected original image, the target detection algorithm unit performs target detection on the water flow or the person holding the roller in the preprocessed image, and the face recognition unit performs face recognition on the image detected with hand washing or dust removal behavior to obtain the identity information of the person;

[0028] S2, the sending object address selection unit of the sending module selects the sending object by setting the IP address and the port number, and the JSON format information sending unit sends a POST request containing JSON data to the sending object, wherein the JSON data contains the identity information of the person, the situation and time of the hand washing or dust removal behavior;

[0029] S3. After the data storage and alarm module receives the JSON format information sent by the sending module on the server, the personnel hand washing and dust removal situation recording unit modifies the hand washing and dust removal situation and time of the corresponding personnel according to the content in the JSON format information, and the alarm and historical information storage module performs alarm operations and records the personnel who do not wash their hands or dust remove according to the personnel hand washing and dust removal situation recording unit.

[0030] It should be noted that the specific working process of the target detection algorithm unit is as follows:

[0031] Determine whether a person has entered the hand washing or dust removal area based on changes in the two frames before and after the video image;

[0032] If the two frames before and after the video image change, then detect the water flow or the person holding the roller in the current video image, and count the number of frames in which the water flow or the person holding the roller is detected;

[0033] When the number of frames in which the water flow or the person holding the roller is detected reaches the set threshold, it is determined that there are people who currently meet the hand washing or dust removal standards, otherwise, they do not meet the standards.

[0034] For those who meet the criteria, facial recognition is performed on the persons to obtain their identity information.

[0035] It should be noted that after the access control device sends the identity information of the staff entering the workshop and the time of entry to the server, it also includes: querying whether the staff has washed their hands and removed dust within a certain period of time before entering the workshop. If the staff has not washed their hands or removed dust, an alarm message is issued.

[0036] Please refer to Figure 2 , Figure 2 It is a detailed flow chart of the method of the present invention.

[0037] As an embodiment, the overall detailed process of the method of the present invention is as follows:

[0038] S1. Collect a video image of a hand washing or dust removal area, and determine whether two frames before and after the image in the video image have changed.

[0039] Step S1 further comprises:

[0040] S11, the image acquisition and processing module selects corresponding model parameters and sets a suitable frame rate through a mode selection unit according to the area where the retrieved camera is located.

[0041] S12, convert the current frame into a grayscale image, then divide the difference image into foreground and background through threshold binarization processing, and then use the dilation operation to fill the holes and connect the adjacent areas, and determine whether there is a contour greater than the set threshold pixel by finding the contour. If there is, it means that a change is detected between the previous and next frames of the camera image.

[0042] S2. If the two frames before and after the video image change, detect the water flow or the person holding the roller in the current video image, and count the number of frames in which the water flow or the person holding the roller is detected.

[0043] Step S2 further comprises:

[0044] S21, the image preprocessing unit adjusts the size of the collected original image to a set value, and normalizes the pixel value of the image to a range of 0-1, so as to improve the processing efficiency and stability of the algorithm for the image.

[0045] S22. Perform brightness adjustment and contrast enhancement operations on the image to increase the robustness of the algorithm to objects under different lighting, background and other conditions.

[0046] S23, the target detection algorithm unit performs target detection on the water flow or the person holding the roller in the preprocessed image, selects the target with a confidence level greater than a set threshold, and removes redundant candidate bounding boxes through maximum value suppression to obtain the final detection result.

[0047] S3. When the number of frames of people detected with water flow or hand-held rollers reaches a set threshold, it is determined that there are people who meet the hand washing or dust removal standards, and face recognition is performed on the people to obtain their identity information.

[0048] Step S3 further comprises:

[0049] S31. The face recognition unit uses a deep learning-based face model to perform face detection and find the face position in the input image.

[0050] S32, the face recognition unit detects key points of the face, such as the positions of the eyes, nose, mouth, etc., and calculates a feature vector of the detected face using the key points and shape information of the face.

[0051] S33, calculating the Euclidean distance between the feature vector and the feature vector in the staff member's face key point feature value storage unit to measure the similarity between them.

[0052] S34, judging whether the calculated minimum Euclidean distance is less than a set threshold. If it is less than the threshold, the identity information of the corresponding workshop staff is output; if it is greater than the threshold, the illegal intrusion information of the stranger is output.

[0053] S4. After determining that a person is washing hands or removing dust, the identity information of the person who is washing hands or removing dust and the time when the person completes the washing hands or removing dust are sent to the server.

[0054] Step S4 further comprises:

[0055] S41. The sending module sends the personnel identity information, the behavior type (hand washing or dust removal), and the time of the hand washing or dust removal behavior to the server in JSON format.

[0056] S42. After receiving the information in JSON format, the server modifies the behavior identification bit (hand washing or dust removal) of the person in the person hand washing and dust removal situation recording unit, and records the time information.

[0057] S5. The access control device sends the identity information of the staff entering the workshop and the time of entry to the server. The data storage and alarm module inquires whether the staff has washed their hands and removed dust within a certain period of time before entering the workshop. If the staff has not washed their hands or removed dust, an alarm message is issued.

[0058] Step S5 further comprises:

[0059] S51. The access control device identifies the identity and time information of the person who is about to enter the workshop, and sends it to the server through the sending module.

[0060] S52: After receiving the identity and time information of the person who wants to enter the workshop, the server queries the personnel hand washing and dust removal completion status of the person within the set time before the time in the personnel hand washing and dust removal status recording unit.

[0061] S53. If the person has completed both hand washing and dust removal, the system controls the door to open to allow the person to pass; or if at least one of the hand washing and dust removal is not completed, an alarm message is issued and recorded.

[0062] See also Figure 3 , Figure 3 4 is a schematic diagram of the working of the hardware device of an embodiment of the present invention, and the hardware device specifically includes: a device 401 for detecting hand washing of factory workshop staff, a processor 402 and a storage medium 403.

[0063] A device 401 for detecting hand washing of factory workshop staff: The device 401 for detecting hand washing of factory workshop staff implements a method for detecting hand washing and dust removal behavior of factory workshop staff.

[0064] Processor 402: The processor 402 loads and executes the instructions and data in the storage medium 403 to implement the method for detecting the hand washing and dust removal behavior of factory workshop workers.

[0065] Storage medium 403: The storage medium 403 stores instructions and data; the storage medium 403 is used to implement the method for detecting hand washing and dust removal behavior of factory workshop workers.

[0066] The beneficial effect of the present invention is: using target detection and face recognition technology, judging whether someone has entered the hand washing or dust removal area by whether there is a change between the two frames before and after the video, and then using the target detection algorithm to detect the hand washing and dust removal behavior. The facial information of the person who has completed the hand washing or dust removal behavior is synchronously sent to the server, and only those who have passed the hand washing and dust removal can pass the workshop access control facilities. The labor cost of manually checking the hand washing and dust removal situation is reduced, the inspection efficiency is improved, and the hygiene and safety of the workshop is ensured.

[0067] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A system for detecting hand washing and dust removal behavior of factory workshop workers, characterized by: include: QT interactive main control system, surveillance camera, server, access control equipment, image acquisition and processing module, transmission module, data storage and alarm module; The image acquisition and processing module, the sending module, the data storage and alarm module are all connected to the QT interactive main control system; the QT interactive main control system is used to control the overall process, the data interaction of each module and the implementation of the algorithm.

2. A system for detecting hand washing and dust removal behavior of factory workshop workers as claimed in claim 1, characterized in that: The image acquisition and processing module includes a mode selection unit, an image preprocessing unit, a target detection algorithm unit, and a face recognition unit; the mode selection unit includes model loading and frame number setting.

3. A system for detecting hand washing and dust removal behavior of factory workshop workers as claimed in claim 1, characterized in that: The sending module includes a sending object address selection unit and a JSON format information sending unit.

4. A system for detecting hand washing and dust removal behavior of factory workshop workers as claimed in claim 1, characterized in that: The data storage and alarm module includes a storage unit for key feature values ​​of faces of workshop staff, a unit for recording hand washing and dust removal conditions of staff, and an alarm and historical information storage unit.

5. A method for detecting the hand washing and dust removal behavior of factory workshop workers, applied to the system, characterized in that: The method comprises the following steps: S1, the image acquisition and processing module selects the corresponding model parameters and sets the frame rate through the mode selection unit according to the area where the retrieved camera is located, the image preprocessing unit resizes, normalizes and enhances the collected original image, the target detection algorithm unit performs target detection on the water flow or the person holding the roller in the preprocessed image, and the face recognition unit performs face recognition on the image detected with hand washing or dust removal behavior to obtain the identity information of the person; S2, the sending object address selection unit of the sending module selects the sending object by setting the IP address and the port number, and the JSON format information sending unit sends a POST request containing JSON data to the sending object, wherein the JSON data contains the identity information of the person, the situation and time of the hand washing or dust removal behavior; S3. After the data storage and alarm module receives the JSON format information sent by the sending module on the server, the personnel hand washing and dust removal situation recording unit modifies the hand washing and dust removal situation and time of the corresponding personnel according to the content in the JSON format information, and the alarm and historical information storage module performs alarm operations and records the personnel who do not wash their hands or dust remove according to the personnel hand washing and dust removal situation recording unit.

6. A method for detecting hand washing and dust removal behavior of factory workshop workers as claimed in claim 5, characterized in that: The specific working process of the target detection algorithm unit is as follows: Determine whether a person has entered the hand washing or dust removal area based on changes in the two frames before and after the video image; If the two frames before and after the video image change, then detect the water flow or the person holding the roller in the current video image, and count the number of frames in which the water flow or the person holding the roller is detected; When the number of frames in which the water flow or the person holding the roller is detected reaches the set threshold, it is determined that there are people who currently meet the hand washing or dust removal standards, otherwise, they do not meet the standards.

7. A storage medium, characterized in that: The storage medium stores instructions and data for implementing a method for detecting hand washing and dust removal behavior of factory workshop workers as described in any one of claims 5 to 6.

8. A hand washing device for testing factory workshop workers, characterized by: include: Processor and storage medium; the processor loads and executes instructions and data in the storage medium to implement a method for detecting hand washing and dust removal behavior of factory workshop workers as described in any one of claims 5 to 6.

Images