A unified object and keypoint detection framework for Personal Protective Equipment use
Accurately detecting whether workers wear Personal Protective Equipment (PPE) in real time plays an important role in safety management. Previous studies mainly used multiple models jointly or only object detection for wearing relationship judgments. This makes it difficult to provide real-time, acc...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | Developments in the Built Environment |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666165924002400 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850064063210455040 |
|---|---|
| author | Bin Yang Hongru Xiao Binghan Zhang |
| author_facet | Bin Yang Hongru Xiao Binghan Zhang |
| author_sort | Bin Yang |
| collection | DOAJ |
| description | Accurately detecting whether workers wear Personal Protective Equipment (PPE) in real time plays an important role in safety management. Previous studies mainly used multiple models jointly or only object detection for wearing relationship judgments. This makes it difficult to provide real-time, accurate detection of security relationships. Therefore, this paper proposes safe-wearing detection rules and a novel multi-targets and keypoints detection framework (MTKF), which is capable of accomplishing multiple classes of targets and keypoints detection simultaneously in one-stage, to get more accurate results. In order to improve the performance in the PPE and worker keypoints detection in challenging construction scenes, the detection head transformation strategy, mix group shuffle attention (MGSA) module, and the improved dual and cross-class suppression algorithm (DC-NMS) are proposed. The experimental results are implemented on one established dataset (Joint dataset) and two public datasets (SHWD and COCO), which conduct a comprehensive evaluation in multiple dimensions. Compared to the baseline model, our method improves the mAP by 2.6%–7.1%, reduces the number of parameters by at least 70%, and is able to achieve an inference speed of 155 fps. |
| format | Article |
| id | doaj-art-7f097f532bdd4e3d83567c6613cd38e9 |
| institution | DOAJ |
| issn | 2666-1659 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Developments in the Built Environment |
| spelling | doaj-art-7f097f532bdd4e3d83567c6613cd38e92025-08-20T02:49:25ZengElsevierDevelopments in the Built Environment2666-16592024-12-012010055910.1016/j.dibe.2024.100559A unified object and keypoint detection framework for Personal Protective Equipment useBin Yang0Hongru Xiao1Binghan Zhang2College of Civil Engineering, Tongji University, Shanghai, ChinaCorresponding author.; College of Civil Engineering, Tongji University, Shanghai, ChinaCollege of Civil Engineering, Tongji University, Shanghai, ChinaAccurately detecting whether workers wear Personal Protective Equipment (PPE) in real time plays an important role in safety management. Previous studies mainly used multiple models jointly or only object detection for wearing relationship judgments. This makes it difficult to provide real-time, accurate detection of security relationships. Therefore, this paper proposes safe-wearing detection rules and a novel multi-targets and keypoints detection framework (MTKF), which is capable of accomplishing multiple classes of targets and keypoints detection simultaneously in one-stage, to get more accurate results. In order to improve the performance in the PPE and worker keypoints detection in challenging construction scenes, the detection head transformation strategy, mix group shuffle attention (MGSA) module, and the improved dual and cross-class suppression algorithm (DC-NMS) are proposed. The experimental results are implemented on one established dataset (Joint dataset) and two public datasets (SHWD and COCO), which conduct a comprehensive evaluation in multiple dimensions. Compared to the baseline model, our method improves the mAP by 2.6%–7.1%, reduces the number of parameters by at least 70%, and is able to achieve an inference speed of 155 fps.http://www.sciencedirect.com/science/article/pii/S2666165924002400Construction safetyMulti-targets and keypoints detectionOne-stage frameworkConstruction site |
| spellingShingle | Bin Yang Hongru Xiao Binghan Zhang A unified object and keypoint detection framework for Personal Protective Equipment use Developments in the Built Environment Construction safety Multi-targets and keypoints detection One-stage framework Construction site |
| title | A unified object and keypoint detection framework for Personal Protective Equipment use |
| title_full | A unified object and keypoint detection framework for Personal Protective Equipment use |
| title_fullStr | A unified object and keypoint detection framework for Personal Protective Equipment use |
| title_full_unstemmed | A unified object and keypoint detection framework for Personal Protective Equipment use |
| title_short | A unified object and keypoint detection framework for Personal Protective Equipment use |
| title_sort | unified object and keypoint detection framework for personal protective equipment use |
| topic | Construction safety Multi-targets and keypoints detection One-stage framework Construction site |
| url | http://www.sciencedirect.com/science/article/pii/S2666165924002400 |
| work_keys_str_mv | AT binyang aunifiedobjectandkeypointdetectionframeworkforpersonalprotectiveequipmentuse AT hongruxiao aunifiedobjectandkeypointdetectionframeworkforpersonalprotectiveequipmentuse AT binghanzhang aunifiedobjectandkeypointdetectionframeworkforpersonalprotectiveequipmentuse AT binyang unifiedobjectandkeypointdetectionframeworkforpersonalprotectiveequipmentuse AT hongruxiao unifiedobjectandkeypointdetectionframeworkforpersonalprotectiveequipmentuse AT binghanzhang unifiedobjectandkeypointdetectionframeworkforpersonalprotectiveequipmentuse |