SHEL5K: An Extended Dataset and Benchmarking for Safety Helmet Detection
Wearing a safety helmet is important in construction and manufacturing industrial activities to avoid unpleasant situations. This safety compliance can be ensured by developing an automatic helmet detection system using various computer vision and deep learning approaches. Developing a deep-learning...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/6/2315 |
| _version_ | 1797442316130058240 |
|---|---|
| author | Munkh-Erdene Otgonbold Munkhjargal Gochoo Fady Alnajjar Luqman Ali Tan-Hsu Tan Jun-Wei Hsieh Ping-Yang Chen |
| author_facet | Munkh-Erdene Otgonbold Munkhjargal Gochoo Fady Alnajjar Luqman Ali Tan-Hsu Tan Jun-Wei Hsieh Ping-Yang Chen |
| author_sort | Munkh-Erdene Otgonbold |
| collection | DOAJ |
| description | Wearing a safety helmet is important in construction and manufacturing industrial activities to avoid unpleasant situations. This safety compliance can be ensured by developing an automatic helmet detection system using various computer vision and deep learning approaches. Developing a deep-learning-based helmet detection model usually requires an enormous amount of training data. However, there are very few public safety helmet datasets available in the literature, in which most of them are not entirely labeled, and the labeled one contains fewer classes. This paper presents the Safety HELmet dataset with 5K images (SHEL5K) dataset, an enhanced version of the SHD dataset. The proposed dataset consists of six completely labeled classes (<i>helmet</i>, <i>head</i>, <i>head with helmet</i>, <i>person with helmet</i>, <i>person without helmet</i>, and <i>face</i>). The proposed dataset was tested on multiple state-of-the-art object detection models, i.e., YOLOv3 (YOLOv3, YOLOv3-tiny, and YOLOv3-SPP), YOLOv4 (YOLOv4 and YOLOv4<sub>pacsp-x-mish</sub>), YOLOv5-P5 (YOLOv5s, YOLOv5m, and YOLOv5x), the Faster Region-based Convolutional Neural Network (Faster-RCNN) with the Inception V2 architecture, and YOLOR. The experimental results from the various models on the proposed dataset were compared and showed improvement in the mean Average Precision (mAP). The SHEL5K dataset had an advantage over other safety helmet datasets as it contains fewer images with better labels and more classes, making helmet detection more accurate. |
| first_indexed | 2024-03-09T12:40:04Z |
| format | Article |
| id | doaj.art-a2daf3239215465bb91f503ea297b401 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T12:40:04Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-a2daf3239215465bb91f503ea297b4012023-11-30T22:19:15ZengMDPI AGSensors1424-82202022-03-01226231510.3390/s22062315SHEL5K: An Extended Dataset and Benchmarking for Safety Helmet DetectionMunkh-Erdene Otgonbold0Munkhjargal Gochoo1Fady Alnajjar2Luqman Ali3Tan-Hsu Tan4Jun-Wei Hsieh5Ping-Yang Chen6Department of Computer Science and Software Engineering, College of Information Technology, United Arab Emirates University, Al Ain 15551, United Arab EmiratesDepartment of Computer Science and Software Engineering, College of Information Technology, United Arab Emirates University, Al Ain 15551, United Arab EmiratesDepartment of Computer Science and Software Engineering, College of Information Technology, United Arab Emirates University, Al Ain 15551, United Arab EmiratesDepartment of Computer Science and Software Engineering, College of Information Technology, United Arab Emirates University, Al Ain 15551, United Arab EmiratesDepartment of Electrical Engineering, National Taipei University of Technology, Taipei 10608, TaiwanCollege of Artificial Intelligence and Green Energy, National Yang Ming Chiao Tung University, Hsinchu 30010, TaiwanDepartment of Computer Science, National Yang Ming Chiao Tung University, Hsinchu 30010, TaiwanWearing a safety helmet is important in construction and manufacturing industrial activities to avoid unpleasant situations. This safety compliance can be ensured by developing an automatic helmet detection system using various computer vision and deep learning approaches. Developing a deep-learning-based helmet detection model usually requires an enormous amount of training data. However, there are very few public safety helmet datasets available in the literature, in which most of them are not entirely labeled, and the labeled one contains fewer classes. This paper presents the Safety HELmet dataset with 5K images (SHEL5K) dataset, an enhanced version of the SHD dataset. The proposed dataset consists of six completely labeled classes (<i>helmet</i>, <i>head</i>, <i>head with helmet</i>, <i>person with helmet</i>, <i>person without helmet</i>, and <i>face</i>). The proposed dataset was tested on multiple state-of-the-art object detection models, i.e., YOLOv3 (YOLOv3, YOLOv3-tiny, and YOLOv3-SPP), YOLOv4 (YOLOv4 and YOLOv4<sub>pacsp-x-mish</sub>), YOLOv5-P5 (YOLOv5s, YOLOv5m, and YOLOv5x), the Faster Region-based Convolutional Neural Network (Faster-RCNN) with the Inception V2 architecture, and YOLOR. The experimental results from the various models on the proposed dataset were compared and showed improvement in the mean Average Precision (mAP). The SHEL5K dataset had an advantage over other safety helmet datasets as it contains fewer images with better labels and more classes, making helmet detection more accurate.https://www.mdpi.com/1424-8220/22/6/2315YOLOv3YOLOv4 YOLOv5YOLORsafety helmetSHEL5Kobject detection |
| spellingShingle | Munkh-Erdene Otgonbold Munkhjargal Gochoo Fady Alnajjar Luqman Ali Tan-Hsu Tan Jun-Wei Hsieh Ping-Yang Chen SHEL5K: An Extended Dataset and Benchmarking for Safety Helmet Detection Sensors YOLOv3 YOLOv4 YOLOv5 YOLOR safety helmet SHEL5K object detection |
| title | SHEL5K: An Extended Dataset and Benchmarking for Safety Helmet Detection |
| title_full | SHEL5K: An Extended Dataset and Benchmarking for Safety Helmet Detection |
| title_fullStr | SHEL5K: An Extended Dataset and Benchmarking for Safety Helmet Detection |
| title_full_unstemmed | SHEL5K: An Extended Dataset and Benchmarking for Safety Helmet Detection |
| title_short | SHEL5K: An Extended Dataset and Benchmarking for Safety Helmet Detection |
| title_sort | shel5k an extended dataset and benchmarking for safety helmet detection |
| topic | YOLOv3 YOLOv4 YOLOv5 YOLOR safety helmet SHEL5K object detection |
| url | https://www.mdpi.com/1424-8220/22/6/2315 |
| work_keys_str_mv | AT munkherdeneotgonbold shel5kanextendeddatasetandbenchmarkingforsafetyhelmetdetection AT munkhjargalgochoo shel5kanextendeddatasetandbenchmarkingforsafetyhelmetdetection AT fadyalnajjar shel5kanextendeddatasetandbenchmarkingforsafetyhelmetdetection AT luqmanali shel5kanextendeddatasetandbenchmarkingforsafetyhelmetdetection AT tanhsutan shel5kanextendeddatasetandbenchmarkingforsafetyhelmetdetection AT junweihsieh shel5kanextendeddatasetandbenchmarkingforsafetyhelmetdetection AT pingyangchen shel5kanextendeddatasetandbenchmarkingforsafetyhelmetdetection |