Real-time tunnel lining crack detection based on an improved You Only Look Once version X algorithm. Issue 1 (2nd January 2023)

• Record Type: Journal Article
• Authors: Zhou, Zhong; Yan, Longbin; Zhang, Junjie; Yang, Hao
• Is Part Of: Georisk. Volume 17:Issue 1(2023)
• Page Start: 181
• Page End: 195
• Publication Date: 2023-01-02
• Subjects: Tunnel -- deep learning -- crack detection -- channel attention mechanism; Environmental risk assessment -- Periodicals; Hazardous geographic environments -- Risk assessment -- Periodicals; Reliability (Engineering) -- Periodicals; Risk management -- Periodicals; 624.151
• DOI: 10.1080/17499518.2023.2172187
• Languages: English
• ISSNs: 1749-9518

Abstract

ABSTRACT: To solve slow speed and low accuracy of traditional detection methods of tunnel lining cracks, especially under the complicated situation of tunnel in operation, this work proposed an improved You Only Look Once version X (YOLOX) tunnel lining crack image detection algorithm. First, Mobilenetv3 was used to replace YOLOX's CSPDarknet network. The Efficient Channel Attention (ECA) module was then added to the enhanced feature extraction network, and the IOU loss function was replaced by the generalised IOU (GIOU) loss function. A tunnel crack image data set was constructed and used to compare the performance of the improved YOLOX algorithm with that of five other algorithms. The improved YOLOX algorithm solves the shortcomings of the other five algorithms. The results showed that the improved YOLOX algorithm had 82.48% F1 score and 87.28% AP value, which is higher than that of the other five algorithms at varying degrees. In addition, the data size of the improved YOLOX model was 51.2 M, which is 75.27% compressed compared to the YOLOX model. The time was 16.52 ms, and the FPS was 60.52 frames/s. Therefore, the proposed improved YOLOX algorithm can realise the high-speed, high-precision, real-time dynamic detection of tunnel lining cracks in complicated environments.