Crack Detection on Road Surfaces Based on Improved YOLOv8
Road defect detection is vital for road maintenance but remains challenging due to the complexity of backgrounds, low resolution, and crack similarity. This paper introduces YOLOv8-VOS(VOS means ‘vanillaNet+ODConv+SEAttention’), an enhanced road crack detection algorithm that i...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10802889/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846113901385613312 |
|---|---|
| author | Haiyang Wu Lingyun Kong Denghui Liu |
| author_facet | Haiyang Wu Lingyun Kong Denghui Liu |
| author_sort | Haiyang Wu |
| collection | DOAJ |
| description | Road defect detection is vital for road maintenance but remains challenging due to the complexity of backgrounds, low resolution, and crack similarity. This paper introduces YOLOv8-VOS(VOS means ‘vanillaNet+ODConv+SEAttention’), an enhanced road crack detection algorithm that incorporates an improved Vanilla Net backbone with Squeeze-and-Excitation (SE) attention and ODConv modules. The loss function is replaced with WIoU to better balance bounding box regression. Experiments on the RDD2022 dataset demonstrate a 2% improvement in average accuracy over the original YOLOv8, achieving 53.7%. The proposed model effectively identifies road cracks in complex traffic backgrounds, contributing to safer and more efficient road maintenance. |
| format | Article |
| id | doaj-art-d8cc3177519e4d989d062d6c8f0c2f88 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-d8cc3177519e4d989d062d6c8f0c2f882024-12-21T00:00:43ZengIEEEIEEE Access2169-35362024-01-011219085019086410.1109/ACCESS.2024.351763210802889Crack Detection on Road Surfaces Based on Improved YOLOv8Haiyang Wu0https://orcid.org/0009-0009-2122-7435Lingyun Kong1https://orcid.org/0000-0001-7248-3900Denghui Liu2School of Electronic Information, Xijing University, Xi’an, Shaanxi, ChinaSchool of Electronic Information, Xijing University, Xi’an, Shaanxi, ChinaSchool of Electronic Information, Xijing University, Xi’an, Shaanxi, ChinaRoad defect detection is vital for road maintenance but remains challenging due to the complexity of backgrounds, low resolution, and crack similarity. This paper introduces YOLOv8-VOS(VOS means ‘vanillaNet+ODConv+SEAttention’), an enhanced road crack detection algorithm that incorporates an improved Vanilla Net backbone with Squeeze-and-Excitation (SE) attention and ODConv modules. The loss function is replaced with WIoU to better balance bounding box regression. Experiments on the RDD2022 dataset demonstrate a 2% improvement in average accuracy over the original YOLOv8, achieving 53.7%. The proposed model effectively identifies road cracks in complex traffic backgrounds, contributing to safer and more efficient road maintenance.https://ieeexplore.ieee.org/document/10802889/Vanilla NetYOLOv8RDD2022road crack detectionODConvroad maintenance |
| spellingShingle | Haiyang Wu Lingyun Kong Denghui Liu Crack Detection on Road Surfaces Based on Improved YOLOv8 IEEE Access Vanilla Net YOLOv8 RDD2022 road crack detection ODConv road maintenance |
| title | Crack Detection on Road Surfaces Based on Improved YOLOv8 |
| title_full | Crack Detection on Road Surfaces Based on Improved YOLOv8 |
| title_fullStr | Crack Detection on Road Surfaces Based on Improved YOLOv8 |
| title_full_unstemmed | Crack Detection on Road Surfaces Based on Improved YOLOv8 |
| title_short | Crack Detection on Road Surfaces Based on Improved YOLOv8 |
| title_sort | crack detection on road surfaces based on improved yolov8 |
| topic | Vanilla Net YOLOv8 RDD2022 road crack detection ODConv road maintenance |
| url | https://ieeexplore.ieee.org/document/10802889/ |
| work_keys_str_mv | AT haiyangwu crackdetectiononroadsurfacesbasedonimprovedyolov8 AT lingyunkong crackdetectiononroadsurfacesbasedonimprovedyolov8 AT denghuiliu crackdetectiononroadsurfacesbasedonimprovedyolov8 |