OBC-YOLOv8: an improved road damage detection model based on YOLOv8
Effective and efficient detection of pavement distress is very important for the normal use and maintenance of roads. To achieve this goal, a new road damage detection method based on YOLOv8 is proposed in this article. Firstly, omni-dimensional dynamic convolution (ODConv) block is employed to bett...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2025-01-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-2593.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841551890585747456 |
|---|---|
| author | Shizheng Zhang Zhihao Liu Kunpeng Wang Wanwei Huang Pu Li |
| author_facet | Shizheng Zhang Zhihao Liu Kunpeng Wang Wanwei Huang Pu Li |
| author_sort | Shizheng Zhang |
| collection | DOAJ |
| description | Effective and efficient detection of pavement distress is very important for the normal use and maintenance of roads. To achieve this goal, a new road damage detection method based on YOLOv8 is proposed in this article. Firstly, omni-dimensional dynamic convolution (ODConv) block is employed to better grasp the complex and diverse features of damage objects by making dynamic adjustment according to the features of input images. Secondly, to extract the global and local feature information simultaneously to better improve the feature extraction ability of the model, BoTNet is added to the end of the backbone, which can combine the advantages of convolutional neural network (CNN) and Transformer. Finally, the coordinate attention mechanism (CA) is incorporated into the Neck section to make more accurate speculations and enhance detection accuracy further which can effectively mitigate irrelevant feature interference. The new proposed model is named OBC-YOLOv8 and the experimental results on the RDD2022-China dataset demonstrate its superiority compared with baselines, with 1.8% and 1.6% increases in mean average precision 50 (mAP@0.5) and F1-score, respectively. |
| format | Article |
| id | doaj-art-f81935a6421a4c93a6cce5bc2937f362 |
| institution | Kabale University |
| issn | 2376-5992 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj-art-f81935a6421a4c93a6cce5bc2937f3622025-01-09T15:05:12ZengPeerJ Inc.PeerJ Computer Science2376-59922025-01-0111e259310.7717/peerj-cs.2593OBC-YOLOv8: an improved road damage detection model based on YOLOv8Shizheng ZhangZhihao LiuKunpeng WangWanwei HuangPu LiEffective and efficient detection of pavement distress is very important for the normal use and maintenance of roads. To achieve this goal, a new road damage detection method based on YOLOv8 is proposed in this article. Firstly, omni-dimensional dynamic convolution (ODConv) block is employed to better grasp the complex and diverse features of damage objects by making dynamic adjustment according to the features of input images. Secondly, to extract the global and local feature information simultaneously to better improve the feature extraction ability of the model, BoTNet is added to the end of the backbone, which can combine the advantages of convolutional neural network (CNN) and Transformer. Finally, the coordinate attention mechanism (CA) is incorporated into the Neck section to make more accurate speculations and enhance detection accuracy further which can effectively mitigate irrelevant feature interference. The new proposed model is named OBC-YOLOv8 and the experimental results on the RDD2022-China dataset demonstrate its superiority compared with baselines, with 1.8% and 1.6% increases in mean average precision 50 (mAP@0.5) and F1-score, respectively.https://peerj.com/articles/cs-2593.pdfRoad damage detectionDeep-learningYOLOv8Attention mechanismDynamic convolution |
| spellingShingle | Shizheng Zhang Zhihao Liu Kunpeng Wang Wanwei Huang Pu Li OBC-YOLOv8: an improved road damage detection model based on YOLOv8 PeerJ Computer Science Road damage detection Deep-learning YOLOv8 Attention mechanism Dynamic convolution |
| title | OBC-YOLOv8: an improved road damage detection model based on YOLOv8 |
| title_full | OBC-YOLOv8: an improved road damage detection model based on YOLOv8 |
| title_fullStr | OBC-YOLOv8: an improved road damage detection model based on YOLOv8 |
| title_full_unstemmed | OBC-YOLOv8: an improved road damage detection model based on YOLOv8 |
| title_short | OBC-YOLOv8: an improved road damage detection model based on YOLOv8 |
| title_sort | obc yolov8 an improved road damage detection model based on yolov8 |
| topic | Road damage detection Deep-learning YOLOv8 Attention mechanism Dynamic convolution |
| url | https://peerj.com/articles/cs-2593.pdf |
| work_keys_str_mv | AT shizhengzhang obcyolov8animprovedroaddamagedetectionmodelbasedonyolov8 AT zhihaoliu obcyolov8animprovedroaddamagedetectionmodelbasedonyolov8 AT kunpengwang obcyolov8animprovedroaddamagedetectionmodelbasedonyolov8 AT wanweihuang obcyolov8animprovedroaddamagedetectionmodelbasedonyolov8 AT puli obcyolov8animprovedroaddamagedetectionmodelbasedonyolov8 |