YOLOv8-PCD: a pavement crack detection method based on enhanced feature fusion

Ting Cao; Wenbin Li; Han Sun; Penghui Wang; Zhichao Gong

doi:10.1117/12.3054712

20 December 2024 YOLOv8-PCD: a pavement crack detection method based on enhanced feature fusion

Ting Cao, Wenbin Li, Han Sun, Penghui Wang, Zhichao Gong

Author Affiliations +

Proceedings Volume 13421, Eighth International Conference on Traffic Engineering and Transportation System (ICTETS 2024); 134210F (2024) https://doi.org/10.1117/12.3054712
Event: Eighth International Conference on Traffic Engineering and Transportation System (ICTETS 2024), 2024, Dalian, China

Abstract

With deep learning prevailing in intelligent transportation systems, pavement crack detection using object detection has aroused wide attentions in both academic research and engineering application. Unfortunately, it still a challenge to focus on pavement critical areas and perceive crack at different scales due to the complexity in traffic background. To improve feature extraction and fusion capabilities, a pavement crack detection method named YOLOv8-PCD is proposed in this paper based on enhanced feature fusion. Firstly, the Biformer attention mechanism is incorporated into the network to enhance its performance in handling pavement objects at varying scales. Secondly, the Neck network is upgraded to BiFPN to better integrate crack features from different levels, thereby improving the detection capabilities. Finally, the experiments verify the proposed method could accomplish satisfactory result in both robustness and accuracy.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Ting Cao, Wenbin Li, Han Sun, Penghui Wang, and Zhichao Gong "YOLOv8-PCD: a pavement crack detection method based on enhanced feature fusion", Proc. SPIE 13421, Eighth International Conference on Traffic Engineering and Transportation System (ICTETS 2024), 134210F (20 December 2024); https://doi.org/10.1117/12.3054712

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE