Improved YOLOv5-based for small traffic sign detection under complex weather
Abstract Traffic sign detection is a challenging task for unmanned driving systems. In the traffic sign detection process, the object size and weather conditions vary widely, which will have a certain impact on the detection accuracy. In order to solve the problem of balanced detecting precision of...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-09-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-42753-3 |
| _version_ | 1797453196092768256 |
|---|---|
| author | Shenming Qu Xinyu Yang Huafei Zhou Yuan Xie |
| author_facet | Shenming Qu Xinyu Yang Huafei Zhou Yuan Xie |
| author_sort | Shenming Qu |
| collection | DOAJ |
| description | Abstract Traffic sign detection is a challenging task for unmanned driving systems. In the traffic sign detection process, the object size and weather conditions vary widely, which will have a certain impact on the detection accuracy. In order to solve the problem of balanced detecting precision of traffic sign recognition model in different weather conditions, and it is difficult to detect occluded objects and small objects, this paper proposes a small object detection algorithm based on improved YOLOv5s in complex weather. First, we add the coordinate attention(CA) mechanism in the backbone, a light-weight yet effective module, embedding the location information of traffic signs into the channel attention to improve the feature extraction ability of the network. Second, we exploit effectively fine-grained features about small traffic signs from the shallower layers by adding one prediction head to YOLOv5s. Finally, we use Alpha-IoU to improve the original positioning loss CIoU, improving the accuracy of bbox regression. Applying this model to the recently proposed CCTSDB 2021 dataset, for small objects, the precision is 88.1%, and the recall rate is 79.8%, compared with the original YOLOv5s model, it is improved by 12.5% and 23.9% respectively, and small traffic signs can be effectively detected under different weather conditions, with low miss rate and high detection accuracy. The source code will be made publicly available at https://github.com/yang-0706/ImprovedYOLOv5s . |
| first_indexed | 2024-03-09T15:19:21Z |
| format | Article |
| id | doaj.art-3d3e047b6e6e407aa19dec24485c0ee8 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-09T15:19:21Z |
| publishDate | 2023-09-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-3d3e047b6e6e407aa19dec24485c0ee82023-11-26T12:53:18ZengNature PortfolioScientific Reports2045-23222023-09-0113111210.1038/s41598-023-42753-3Improved YOLOv5-based for small traffic sign detection under complex weatherShenming Qu0Xinyu Yang1Huafei Zhou2Yuan Xie3School of Software, Henan UniversitySchool of Software, Henan UniversitySchool of Software, Henan UniversitySchool of Software, Henan UniversityAbstract Traffic sign detection is a challenging task for unmanned driving systems. In the traffic sign detection process, the object size and weather conditions vary widely, which will have a certain impact on the detection accuracy. In order to solve the problem of balanced detecting precision of traffic sign recognition model in different weather conditions, and it is difficult to detect occluded objects and small objects, this paper proposes a small object detection algorithm based on improved YOLOv5s in complex weather. First, we add the coordinate attention(CA) mechanism in the backbone, a light-weight yet effective module, embedding the location information of traffic signs into the channel attention to improve the feature extraction ability of the network. Second, we exploit effectively fine-grained features about small traffic signs from the shallower layers by adding one prediction head to YOLOv5s. Finally, we use Alpha-IoU to improve the original positioning loss CIoU, improving the accuracy of bbox regression. Applying this model to the recently proposed CCTSDB 2021 dataset, for small objects, the precision is 88.1%, and the recall rate is 79.8%, compared with the original YOLOv5s model, it is improved by 12.5% and 23.9% respectively, and small traffic signs can be effectively detected under different weather conditions, with low miss rate and high detection accuracy. The source code will be made publicly available at https://github.com/yang-0706/ImprovedYOLOv5s .https://doi.org/10.1038/s41598-023-42753-3 |
| spellingShingle | Shenming Qu Xinyu Yang Huafei Zhou Yuan Xie Improved YOLOv5-based for small traffic sign detection under complex weather Scientific Reports |
| title | Improved YOLOv5-based for small traffic sign detection under complex weather |
| title_full | Improved YOLOv5-based for small traffic sign detection under complex weather |
| title_fullStr | Improved YOLOv5-based for small traffic sign detection under complex weather |
| title_full_unstemmed | Improved YOLOv5-based for small traffic sign detection under complex weather |
| title_short | Improved YOLOv5-based for small traffic sign detection under complex weather |
| title_sort | improved yolov5 based for small traffic sign detection under complex weather |
| url | https://doi.org/10.1038/s41598-023-42753-3 |
| work_keys_str_mv | AT shenmingqu improvedyolov5basedforsmalltrafficsigndetectionundercomplexweather AT xinyuyang improvedyolov5basedforsmalltrafficsigndetectionundercomplexweather AT huafeizhou improvedyolov5basedforsmalltrafficsigndetectionundercomplexweather AT yuanxie improvedyolov5basedforsmalltrafficsigndetectionundercomplexweather |