</> Code with Papers by Syntology

Papers › Large, Complex, and Realistic Safety Clothing and Helmet Detection: Dataset and Method

Large, Complex, and Realistic Safety Clothing and Helmet Detection: Dataset and Method

3 Jun 2023arXiv:2306.02098archive 2025-07-28

Fusheng Yu, Jiang Li, XiaoPing Wang, Shaojin Wu, Junjie Zhang, Zhigang Zeng

Detecting safety clothing and helmets is paramount for ensuring the safety of construction workers. However, the development of deep learning models in this domain has been impeded by the scarcity of high-quality datasets. In this study, we construct a large, complex, and realistic safety clothing and helmet detection (SFCHD) dataset. SFCHD is derived from two authentic chemical plants, comprising 12,373 images, 7 categories, and 50,552 annotations. We partition the SFCHD dataset into training and testing sets with a ratio of 4:1 and validate its utility by applying several classic object detection algorithms. Furthermore, drawing inspiration from spatial and channel attention mechanisms, we design a spatial and channel attention-based low-light enhancement (SCALE) module. SCALE is a plug-and-play component with a high degree of flexibility. Extensive evaluations of the SCALE module on both the ExDark and SFCHD datasets have empirically demonstrated its efficacy in enhancing the performance of detectors under low-light conditions. The dataset and code are publicly available at https://github.com/lijfrank-open/SFCHD-SCALE.

PaperPDFCode

Code

lijfrank-open/SFCHD-SCALE officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

2D Object DetectionObject DetectionReal-Time Object DetectionSmall Object Detectionobject-detection

Datasets

Introduced by this paper, per the archive.

SFCHD

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection SFCHD YOLOv8+SCALE mAP@0.50 78.6 #1 of 12 Archive leaderboard report
Object Detection SFCHD YOLOv8+SCALE mAP@0.5:0.95 53.3 #1 of 12 Archive leaderboard report
Object Detection SFCHD TOOD+SCALE mAP@0.50 79.3 #2 of 12 Archive leaderboard report
Object Detection SFCHD TOOD+SCALE mAP@0.5:0.95 52.4 #2 of 12 Archive leaderboard report
Object Detection SFCHD TOOD mAP@0.50 78.9 #3 of 12 Archive leaderboard report
Object Detection SFCHD TOOD mAP@0.5:0.95 52.3 #3 of 12 Archive leaderboard report
Object Detection SFCHD YOLOv8 mAP@0.50 77.9 #4 of 12 Archive leaderboard report
Object Detection SFCHD YOLOv8 mAP@0.5:0.95 52.2 #4 of 12 Archive leaderboard report
Object Detection SFCHD VFNet+SCALE mAP@0.50 76.6 #5 of 12 Archive leaderboard report
Object Detection SFCHD VFNet+SCALE mAP@0.5:0.95 51.4 #5 of 12 Archive leaderboard report
Object Detection SFCHD VFNet mAP@0.50 76.4 #6 of 12 Archive leaderboard report
Object Detection SFCHD VFNet mAP@0.5:0.95 51.0 #6 of 12 Archive leaderboard report
Object Detection SFCHD Faster RCNN mAP@0.50 76.4 #7 of 12 Archive leaderboard report
Object Detection SFCHD Faster RCNN mAP@0.5:0.95 50.3 #7 of 12 Archive leaderboard report
Object Detection SFCHD FCOS mAP@0.50 76.4 #8 of 12 Archive leaderboard report
Object Detection SFCHD FCOS mAP@0.5:0.95 49.6 #8 of 12 Archive leaderboard report
Object Detection SFCHD YOLOv5 mAP@0.50 74.1 #9 of 12 Archive leaderboard report
Object Detection SFCHD YOLOv5 mAP@0.5:0.95 49.6 #9 of 12 Archive leaderboard report
Object Detection SFCHD FCOS+SCALE mAP@0.50 76.3 #10 of 12 Archive leaderboard report
Object Detection SFCHD FCOS+SCALE mAP@0.5:0.95 49.5 #10 of 12 Archive leaderboard report
Object Detection SFCHD RetinaNet mAP@0.50 75.9 #11 of 12 Archive leaderboard report
Object Detection SFCHD RetinaNet mAP@0.5:0.95 48.9 #11 of 12 Archive leaderboard report
Object Detection SFCHD SSD mAP@0.50 72.8 #12 of 12 Archive leaderboard report
Object Detection SFCHD SSD mAP@0.5:0.95 41.5 #12 of 12 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections