Safety Helmet Detection Based on YOLOv5 Driven by Super-Resolution Reconstruction
High-resolution image transmission is required in safety helmet detection problems in the construction industry, which makes it difficult for existing image detection methods to achieve high-speed detection. To overcome this problem, a novel super-resolution (SR) reconstruction module is designed to...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-02-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/23/4/1822 |
_version_ | 1797618319980756992 |
---|---|
author | Ju Han Yicheng Liu Zhipeng Li Yan Liu Bixiong Zhan |
author_facet | Ju Han Yicheng Liu Zhipeng Li Yan Liu Bixiong Zhan |
author_sort | Ju Han |
collection | DOAJ |
description | High-resolution image transmission is required in safety helmet detection problems in the construction industry, which makes it difficult for existing image detection methods to achieve high-speed detection. To overcome this problem, a novel super-resolution (SR) reconstruction module is designed to improve the resolution of images before the detection module. In the super-resolution reconstruction module, the multichannel attention mechanism module is used to improve the breadth of feature capture. Furthermore, a novel CSP (Cross Stage Partial) module of YOLO (You Only Look Once) v5 is presented to reduce information loss and gradient confusion. Experiments are performed to validate the proposed algorithm. The PSNR (peak signal-to-noise ratio) of the proposed module is 29.420, and the SSIM (structural similarity) reaches 0.855. These results show that the proposed model works well for safety helmet detection in construction industries. |
first_indexed | 2024-03-11T08:11:50Z |
format | Article |
id | doaj.art-6d259428db5640baa13304523014b289 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-11T08:11:50Z |
publishDate | 2023-02-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-6d259428db5640baa13304523014b2892023-11-16T23:06:36ZengMDPI AGSensors1424-82202023-02-01234182210.3390/s23041822Safety Helmet Detection Based on YOLOv5 Driven by Super-Resolution ReconstructionJu Han0Yicheng Liu1Zhipeng Li2Yan Liu3Bixiong Zhan4China Construction First Group Construction & Development Co., Ltd., Beijing 100102, ChinaCollege of Electrical Engineering, Sichuan University, Chengdu 610065, ChinaCollege of Electrical Engineering, Sichuan University, Chengdu 610065, ChinaCollege of Electrical Engineering, Sichuan University, Chengdu 610065, ChinaChina Construction First Group Construction & Development Co., Ltd., Beijing 100102, ChinaHigh-resolution image transmission is required in safety helmet detection problems in the construction industry, which makes it difficult for existing image detection methods to achieve high-speed detection. To overcome this problem, a novel super-resolution (SR) reconstruction module is designed to improve the resolution of images before the detection module. In the super-resolution reconstruction module, the multichannel attention mechanism module is used to improve the breadth of feature capture. Furthermore, a novel CSP (Cross Stage Partial) module of YOLO (You Only Look Once) v5 is presented to reduce information loss and gradient confusion. Experiments are performed to validate the proposed algorithm. The PSNR (peak signal-to-noise ratio) of the proposed module is 29.420, and the SSIM (structural similarity) reaches 0.855. These results show that the proposed model works well for safety helmet detection in construction industries.https://www.mdpi.com/1424-8220/23/4/1822deep learningreal-time detectionsafety helmet detectionsuper-resolution reconstructionYOLOv5 |
spellingShingle | Ju Han Yicheng Liu Zhipeng Li Yan Liu Bixiong Zhan Safety Helmet Detection Based on YOLOv5 Driven by Super-Resolution Reconstruction Sensors deep learning real-time detection safety helmet detection super-resolution reconstruction YOLOv5 |
title | Safety Helmet Detection Based on YOLOv5 Driven by Super-Resolution Reconstruction |
title_full | Safety Helmet Detection Based on YOLOv5 Driven by Super-Resolution Reconstruction |
title_fullStr | Safety Helmet Detection Based on YOLOv5 Driven by Super-Resolution Reconstruction |
title_full_unstemmed | Safety Helmet Detection Based on YOLOv5 Driven by Super-Resolution Reconstruction |
title_short | Safety Helmet Detection Based on YOLOv5 Driven by Super-Resolution Reconstruction |
title_sort | safety helmet detection based on yolov5 driven by super resolution reconstruction |
topic | deep learning real-time detection safety helmet detection super-resolution reconstruction YOLOv5 |
url | https://www.mdpi.com/1424-8220/23/4/1822 |
work_keys_str_mv | AT juhan safetyhelmetdetectionbasedonyolov5drivenbysuperresolutionreconstruction AT yichengliu safetyhelmetdetectionbasedonyolov5drivenbysuperresolutionreconstruction AT zhipengli safetyhelmetdetectionbasedonyolov5drivenbysuperresolutionreconstruction AT yanliu safetyhelmetdetectionbasedonyolov5drivenbysuperresolutionreconstruction AT bixiongzhan safetyhelmetdetectionbasedonyolov5drivenbysuperresolutionreconstruction |