Multiple distresses detection for Asphalt Pavement using improved you Only Look Once Algorithm based on convolutional neural network

ABSTRACT

Leveraging the YOLOv7 object detection framework, this study introduces YOLOv7-CSP, a refined algorithm tailored for identifying asphalt pavement distress with enhanced precision. Utilizing advanced image processing for dataset preprocessing, including data augmentation and denoising, YOLOv7-CSP integrates the CSPNeXt structure and CA attention mechanism for improved detection accuracy and efficiency. The algorithm optimizes anchor box selection through Kmeans clustering and employs a secondary labeling method to enhance learning efficiency and dataset quality. Comparative tests reveal YOLOv7-CSP's superior performance, with significant improvements in mAP, F1 score, GFLOPS, and FPS metrics, demonstrating its effectiveness in detecting various pavement distresses. This innovative approach marks a significant advancement in automatic pavement distress recognition, offering a robust solution for highway maintenance decision-making.

KEYWORDS:

• Pavement distress detection; image recognition
• YOLOv7
• CSPNext
• secondary labelling

Acknowledgments

H. D. wants to thank the support from the Hunan Transportation Science and Technology Foundation (CN) (grant number 202104), and the National Natural Science Foundation of China (grant numbers 52278468 and U22A20235).

Disclosure statement

No potential conflict of interest was reported by the author(s).

Data availability statement

Some data, models, or code generated or used during the study are available by request.

Credit authorship contribution statement

Han-Cheng Dan: Conceptualization, Methodology, Writing-original draft, Data curation, Formal Analysis, Investigation, Funding acquisition. Peng Yan: Data curation, Software, Writing-original draft. Jiawei Tan: Conceptualization, Writing-review & editing. Yingchao Zhou: Writing-review & editing. Bingjie Lu: Writing-review & editing.

Additional information

Funding

This work was supported by National Natural Science Foundation of China [grant number: 52278468]; Hunan Transportation Science and Technology Foundation [grant number: 202104].