YOLO-DFAN: Effective High-Altitude Safety Belt Detection Network
This paper proposes the You Only Look Once (YOLO) dependency fusing attention network (DFAN) detection algorithm, improved based on the lightweight network YOLOv4-tiny. It combines the advantages of fast speed of traditional lightweight networks and high precision of traditional heavyweight networks...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Future Internet |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-5903/14/12/349 |
| _version_ | 1797458231234134016 |
|---|---|
| author | Wendou Yan Xiuying Wang Shoubiao Tan |
| author_facet | Wendou Yan Xiuying Wang Shoubiao Tan |
| author_sort | Wendou Yan |
| collection | DOAJ |
| description | This paper proposes the You Only Look Once (YOLO) dependency fusing attention network (DFAN) detection algorithm, improved based on the lightweight network YOLOv4-tiny. It combines the advantages of fast speed of traditional lightweight networks and high precision of traditional heavyweight networks, so it is very suitable for the real-time detection of high-altitude safety belts in embedded equipment. In response to the difficulty of extracting the features of an object with a low effective pixel ratio—which is an object with a low ratio of actual area to detection anchor area in the YOLOv4-tiny network—we make three major improvements to the baseline network: The first improvement is introducing the atrous spatial pyramid pooling network after CSPDarkNet-tiny extracts features. The second is to propose the DFAN, while the third is to introduce the path aggregation network (PANet) to replace the feature pyramid network (FPN) of the original network and fuse it with the DFAN. According to the experimental results in the high-altitude safety belt dataset, YOLO-DFAN improves the accuracy by 5.13% compared with the original network, and its detection speed meets the real-time demand. The algorithm also exhibits a good improvement on the Pascal voc07+12 dataset. |
| first_indexed | 2024-03-09T16:34:07Z |
| format | Article |
| id | doaj.art-3ba8c39c7ad041628632d5adfdd513ed |
| institution | Directory Open Access Journal |
| issn | 1999-5903 |
| language | English |
| last_indexed | 2024-03-09T16:34:07Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Future Internet |
| spelling | doaj.art-3ba8c39c7ad041628632d5adfdd513ed2023-11-24T14:58:19ZengMDPI AGFuture Internet1999-59032022-11-01141234910.3390/fi14120349YOLO-DFAN: Effective High-Altitude Safety Belt Detection NetworkWendou Yan0Xiuying Wang1Shoubiao Tan2School of Integrated Circuits, Anhui University, He Fei 230039, ChinaSchool of Integrated Circuits, Anhui University, He Fei 230039, ChinaSchool of Integrated Circuits, Anhui University, He Fei 230039, ChinaThis paper proposes the You Only Look Once (YOLO) dependency fusing attention network (DFAN) detection algorithm, improved based on the lightweight network YOLOv4-tiny. It combines the advantages of fast speed of traditional lightweight networks and high precision of traditional heavyweight networks, so it is very suitable for the real-time detection of high-altitude safety belts in embedded equipment. In response to the difficulty of extracting the features of an object with a low effective pixel ratio—which is an object with a low ratio of actual area to detection anchor area in the YOLOv4-tiny network—we make three major improvements to the baseline network: The first improvement is introducing the atrous spatial pyramid pooling network after CSPDarkNet-tiny extracts features. The second is to propose the DFAN, while the third is to introduce the path aggregation network (PANet) to replace the feature pyramid network (FPN) of the original network and fuse it with the DFAN. According to the experimental results in the high-altitude safety belt dataset, YOLO-DFAN improves the accuracy by 5.13% compared with the original network, and its detection speed meets the real-time demand. The algorithm also exhibits a good improvement on the Pascal voc07+12 dataset.https://www.mdpi.com/1999-5903/14/12/349high-altitude safety belt detectionlow-effective-pixel-ratio objectimproved YOLOv4-tinyattention mechanism |
| spellingShingle | Wendou Yan Xiuying Wang Shoubiao Tan YOLO-DFAN: Effective High-Altitude Safety Belt Detection Network Future Internet high-altitude safety belt detection low-effective-pixel-ratio object improved YOLOv4-tiny attention mechanism |
| title | YOLO-DFAN: Effective High-Altitude Safety Belt Detection Network |
| title_full | YOLO-DFAN: Effective High-Altitude Safety Belt Detection Network |
| title_fullStr | YOLO-DFAN: Effective High-Altitude Safety Belt Detection Network |
| title_full_unstemmed | YOLO-DFAN: Effective High-Altitude Safety Belt Detection Network |
| title_short | YOLO-DFAN: Effective High-Altitude Safety Belt Detection Network |
| title_sort | yolo dfan effective high altitude safety belt detection network |
| topic | high-altitude safety belt detection low-effective-pixel-ratio object improved YOLOv4-tiny attention mechanism |
| url | https://www.mdpi.com/1999-5903/14/12/349 |
| work_keys_str_mv | AT wendouyan yolodfaneffectivehighaltitudesafetybeltdetectionnetwork AT xiuyingwang yolodfaneffectivehighaltitudesafetybeltdetectionnetwork AT shoubiaotan yolodfaneffectivehighaltitudesafetybeltdetectionnetwork |