Fast personal protective equipment detection for real construction sites using deep learning approaches

Simple item page
dc.contributor.authorWang, Zijian
dc.contributor.authorWu, Yimin
dc.contributor.authorYang, Lichao
dc.contributor.authorThirunavukarasu, Arjun
dc.contributor.authorEvison, Colin
dc.contributor.authorZhao, Yifan
dc.date.accessioned2021-05-20T14:24:13Z
dc.date.available2021-05-20T14:24:13Z
dc.date.issued2021-05-17
dc.description.abstractThe existing deep learning-based Personal Protective Equipment (PPE) detectors can only detect limited types of PPE and their performance needs to be improved, particularly for their deployment on real construction sites. This paper introduces an approach to train and evaluate eight deep learning detectors, for real application purposes, based on You Only Look Once (YOLO) architectures for six classes, including helmets with four colours, person, and vest. Meanwhile, a dedicated high-quality dataset, CHV, consisting of 1330 images, is constructed by considering real construction site background, different gestures, varied angles and distances, and multi PPE classes. The comparison result among the eight models shows that YOLO v5x has the best mAP (86.55%), and YOLO v5s has the fastest speed (52 FPS) on GPU. The detection accuracy of helmet classes on blurred faces decreases by 7%, while there is no effect on other person and vest classes. And the proposed detectors trained on the CHV dataset have a superior performance compared to other deep learning approaches on the same datasets. The novel multiclass CHV dataset is open for public use.en_UK
dc.identifier.citationWang Z, Wu Y, Yang L, et al., (2021) Fast personal protective equipment detection for real construction sites using deep learning approaches. Sensors, Volume 21, Issue 10, May 2021, Article number 3478en_UK
dc.identifier.issn1424-8220
dc.identifier.urihttps://doi.org/10.3390/s21103478
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/16701
dc.language.isoenen_UK
dc.publisherMDPIen_UK
dc.rightsAttribution 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/*
dc.subjectreal-time detectionen_UK
dc.subjectimage dataseten_UK
dc.subjectYou Only Look Once (YOLO)en_UK
dc.subjectdeep learningen_UK
dc.subjectconstruction safetyen_UK
dc.subjectPPEen_UK
dc.titleFast personal protective equipment detection for real construction sites using deep learning approachesen_UK
dc.typeArticleen_UK

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Fast_personal_protective_equipment_detection_for_real_construction_sites-2021.pdf
Size:
35.39 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Staff publications (SATM)