Method for detecting construction worker safety clothing in image based on neural network

A neural network and detection method technology, applied in instruments, computing, character and pattern recognition, etc., can solve the problems of high computational overhead and complex process, and achieve the requirements of low cost, small computing resources and storage space, and hardware saving. Effect

Inactive Publication Date: 2019-08-06
合肥海赛信息科技有限公司
View PDF13 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although this method can successfully extract the key point information of the human body, the process is complicated and the calculation cost is relatively large.

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
  • Method for detecting construction worker safety clothing in image based on neural network
  • Method for detecting construction worker safety clothing in image based on neural network
  • Method for detecting construction worker safety clothing in image based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0058] refer to figure 1 As shown, the present invention discloses a neural network-based method for detecting safety clothing of construction workers in an image, comprising the following steps:

[0059] S1, get n key points of the body of the person in the frame {P 1 ,P 2 ,P 3 …P n}, and express their coordinate values ​​as:

[0060] {P 1 =(x 1 ,y 1 ),P 2 =(x 2 ,y 2 ),P 3 =(x 3 ,y 3 ),…P n =(x n ,y n )}.

[0061] S2, extract the detection area of ​​clothing according to the key points, the extraction method is:

[0062] a, For a non-centrosymmetric detection area centered on the human spine, if the detection area is the key point P n-2 itself, the center point of its detection area is the key point, and the height H n-2 and width W n-2 They are:

[0063] h n-2 =|P n-2 -P n |*A 1

[0064] W n-2 =|P n-2 -P n |*A 2

[0065] Among them, P n is the key point P n-2 Adjacent keypoints, A 1 and A 2 are constants not greater than 1;

[0066] b. For...

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

The invention discloses a method for detecting construction worker safety clothing in an image based on a neural network. The method comprises the following steps: S1, acquiring n key points of a bodyof an intra-frame worker; S2, extracting a detection area of clothes according to the key points; S3, judging the characteristics of the clothes in the detection area, and if the characteristics in the detection area accord with the characteristics of the clothes, judging that the clothes are correctly worn; if not, judging that the wearer is mistakenly worn; and S4, carrying out early warning processing after staggered frame screening, ignoring the processing mode is that wrong wearing of continuous frames with the number smaller than L, and sending out early warning for wrong wearing of continuous frames with the number not smaller than L. Whether a person correctly wears the safe clothes or not can be conveniently and quickly judged, occupied computing resources and storage space are small, and cost is low.

Description

technical field [0001] The invention relates to a clothing detection method, in particular to a method for detecting safety clothing of construction workers in an image based on a neural network. Background technique [0002] In construction scenarios, whether construction personnel wear construction clothing correctly is an important part of construction safety, such as hard hats, insulating boots, safety gloves, etc. In order to ensure that personnel always wear safety clothing correctly during the construction process, the most traditional method is personnel inspection, but it is a waste of manpower. [0003] In addition, there are some ways to install relevant hardware on the clothing that needs to be detected, and judge it through sensors, such as the Chinese patent "CN107647490A A smart clothing with recognition function". This invention uses the acquisition device on the clothing to collect target images and ranging operations. This method has requirements on the c...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00
CPCG06V40/10G06V20/40
Inventor 胡静远袁媛杨娇娇
Owner 合肥海赛信息科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap