Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Automatic detection method and system for normative wearing of field personnel epidemic prevention mask

An on-site personnel, automatic detection technology, applied in neural learning methods, instruments, biological neural network models, etc., can solve the problem of high detection speed and accuracy requirements, strict requirements for video shooting angles, lighting conditions, and difficulty in obtaining useful information. and other problems, to achieve the effect of fast and accurate detection results, less interference from background, and improved detection efficiency

Inactive Publication Date: 2021-01-05
XI AN JIAOTONG UNIV
View PDF1 Cites 30 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, on the one hand, with the continuous expansion of the monitoring system scale, massive video data makes it more and more difficult to obtain useful information from it, the search efficiency is low, the workload is heavy, and it is difficult to meet the needs of monitoring system video anomaly detection
On the other hand, the existing conventional video processing technology has strict requirements on the shooting angle and lighting conditions of the video, and can only be analyzed for a specific scene, and cannot be extended to various scenes.
For complex scenes such as target occlusion, dense crowds, small-scale target detection, etc., the speed and accuracy of detection are high, and the results of traditional machine learning detection methods are not ideal.
In addition, there are very few detection methods for standard wearing of masks, while traditional detection methods have problems such as low precision, slow speed, and poor robustness.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Automatic detection method and system for normative wearing of field personnel epidemic prevention mask
  • Automatic detection method and system for normative wearing of field personnel epidemic prevention mask
  • Automatic detection method and system for normative wearing of field personnel epidemic prevention mask

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049]The main contents of the automatic detection method for the standardized wearing of anti-epidemic masks for on-site personnel of the present invention are as follows:

[0050]Face mask target detection adopts the face mask target detection model to solve the problems of occlusion, dense crowds, and small-scale targets in the face mask detection task in complex scenes. Combine the cross-stage local network to improve the DarkNet53 network and reduce the memory Consumption improves the calculation speed at the same time; introduces a spatial pyramid pooling structure in the detection network, builds a multi-scale prediction network based on bottom-up and top-down feature fusion strategies, and achieves feature enhancement; uses better performance CIoU loss function , Fully consider the center point distance between the target and the detection frame, overlap ratio and aspect ratio information to improve the accuracy of the detection model.

[0051]Based on the YCrCb ellipse skin color...

Embodiment 2

[0093]On the basis of the above-mentioned embodiments and based on the same inventive concept, the embodiments of this application provide an automatic detection device for the standardized wearing of anti-epidemic masks.Picture 10 The automatic detection device 200 for standard wearing of anti-epidemic masks provided in this embodiment is shown, including: a video image extraction module 201, a deep learning module 202, a first judgment module 203, a detection module 204, a second judgment module 205, and an output module 206.

[0094]Specifically, the video image extraction module 201 is configured to collect a video by a camera, obtain a video frame image from the video stream, and perform preprocessing based on the image;

[0095]The deep learning module 202 is configured to perform face mask positioning detection on the image to be detected to obtain a first detection result;

[0096]The first judgment module 203 is configured to judge whether the first detection result meets the condit...

Embodiment 3

[0110]Based on the same inventive concept, the embodiments of this application provide a cloud platform system for automatic detection of the standardized wearing of anti-epidemic masks, seePicture 11, The platform 300 is an independent server or a server group composed of multiple servers. 300 includes: a cloud service platform 301, one or more GPUs 302 connected by a bus 304, a read only memory (ROM) 303, a random access memory (RAM) 304, and an I / O interface 306. The I / O interface 306 is connected to multiple modules in the cloud platform system, including: an input unit 308, a storage unit 309, an output unit 310, and a communication unit 3110.

[0111]Specifically, the cloud service platform 302 is used for centralized and unified operation management of computing, network, and storage, efficiently stores and retrieves data during the operation of a large number of devices, and has unlimited expansion to provide data storage, computing, and network services. In one embodiment, the...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

An automatic detection method for normative wearing of a field personnel epidemic prevention mask comprises the steps that (1) a human face mask data set for normative wearing of the mask is collected, and the data set is marked and preprocessed; 2) a face mask target detection model is constructed, and the model is trained by adopting the marked face mask data set to obtain model parameters; 3) ato-be-detected video is inputted into the trained target detection model for positioning and classification, and whether to wear a mask or not is judged; and 4) whether to standardize the wearing ofthe mask or not is judged based on the YCrCb elliptical skin color model for the condition of judging the wearing of the mask. The invention further provides a corresponding detection device and a GPUcloud platform system. By adopting the method and the system, the detection precision and the detection speed of normative mask wearing of the human face can be effectively improved in complex scenessuch as target occlusion, dense crowds and small-scale detection, the detection method is simple, and engineering application landing conversion is easy.

Description

Technical field[0001]The invention belongs to the technical field of machine vision, and in particular relates to an automatic detection method and system for standardized wearing of anti-epidemic masks by on-site personnel.Background technique[0002]Standardizing the wearing of masks when traveling is one of the most effective measures to prevent infectious diseases, especially in public places with a large number of people. Standard wearing masks can greatly reduce the spread and spread of the virus. Therefore, whether to wear a mask and whether It is necessary to regulate the detection of wearing masks. Manual detection of whether to wear a mask is not only time-consuming and labor-intensive, but also in places with a large flow of people, there is also a problem of missed detection and false detection of whether to wear a mask in a standard manner, and may increase the risk of infection of the detection personnel. Therefore, the advantages of non-contact and high safety factor of...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/00G06K9/32G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/161G06V40/172G06V20/41G06V10/25G06V10/44G06V2201/07G06N3/045G06F18/23G06F18/253
Inventor 张新曼彭羽瑞寇杰王静静毛乙舒程昭晖陆罩陈悦陈星宇江水云
Owner XI AN JIAOTONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com