Hydraulic construction personnel safety helmet wearing detection algorithm based on STA-YOLOv5

doi:10.11835/j.issn.1000.582X.2023.09.014

Home > Archive>Volume 46, Issue 9, 2023 >142-152. DOI:10.11835/j.issn.1000.582X.2023.09.014

Hydraulic construction personnel safety helmet wearing detection algorithm based on STA-YOLOv5
DOI:
                        10.11835/j.issn.1000.582X.2023.09.014
                    
CSTR:
                        [cstr]
                    
Author:
                        LI Shunxiang1LI Shunxiang
Chongqing Western Water Resources Development Co., Ltd., Chongqing 401329, P. R. China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site
JIANG Haiyang2JIANG Haiyang
College of Automation, Chongqing University, Chongqing 400030, P. R. China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site
XIONG Ling1XIONG Ling
Chongqing Western Water Resources Development Co., Ltd., Chongqing 401329, P. R. China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site
HUANG Caisheng1HUANG Caisheng
Chongqing Western Water Resources Development Co., Ltd., Chongqing 401329, P. R. China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site
JIANG Yougao1JIANG Yougao
Chongqing Western Water Resources Development Co., Ltd., Chongqing 401329, P. R. China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site
DENG Xi3DENG Xi
China Academy of Building Research, Beijing 100013, P. R. China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site
WANG Kai2WANG Kai
College of Automation, Chongqing University, Chongqing 400030, P. R. China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site
ZHANG Peng2ZHANG Peng
College of Automation, Chongqing University, Chongqing 400030, P. R. China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site

                    
Affiliation:1.Chongqing Western Water Resources Development Co., Ltd., Chongqing 401329, P. R. China;2.College of Automation, Chongqing University, Chongqing 400030, P. R. China;3.China Academy of Building Research, Beijing 100013, P. R. China
Clc Number:
Fund Project:Supported by Chongqing Water Science and Technology Project (No.19, Shuisiwen [2021], West Chongqing) and the Technology Innovation & Application Development Projects of Chongqing（cstc2021jscx-gksbX0032）.

Article

Figures

Metrics

Reference

Cited by

Materials

Comments

Abstract:

At the site of large-scale water conservancy construction projects, there are problems such as falling objects, tower crane rotation, wall collapse, which pose a great threat to the personal safety of construction personnel. Wearing safety helmets is an effective measure to protect construction personnel. Therefore, it is necessary for construction personnel to carry out accurate detection of helmet wearing as a safety management in engineering operations. Aiming at the problems of missing detection and low detection accuracy of small and dense helmet targets in large-scale hydraulic construction scenarios, a helmet wearing detection algorithm based on STA-YOLOv5 is proposed, which introduces Swin Transformer and attention mechanism into YOLOv5 algorithm to improve the identification ability of the model to the helmet. The experimental results show that the STA-YOLOv5 algorithm has more accurate detection results, and the recognition accuracy reaches 91.6%, which is significantly improved compared with the original YOLOv5 algorithm.

Key words:water conservancy construction;helmet wearing detection;STA-YOLOv5;Swin Transformer;attention mechanism

Get Citation

李顺祥,蒋海洋,熊伶,黄才生,蒋有高,邓曦,王楷,张鹏.基于STA-YOLOv5的水利建造人员安全帽佩戴检测算法[J].重庆大学学报,2023,46(9):142~152

Copy

Article Metrics

Abstract:
PDF:
HTML:
Cited by:

History

Received:May 12,2023
Revised:
Adopted:
Online: September 25,2023
Published:

Home

Get Citation

Share

Article Metrics

History

Article QR Code