Auxcoformer: Auxiliary and Contrastive Transformer for Robust Crack Detection in Adverse Weather Conditions

• Published in: Mathematics (Basel) 2024-03, Vol.12 (5), p.690
• Main Authors: Yoon, Jae Hyun, Jung, Jong Won, Yoo, Seok Bong
• Format: Article
• Language: English
• Subjects: 3D discrete cosine transform; adverse weather conditions; Analysis; Automation; Autonomous navigation; auxiliary and contrastive transformer; Connectivity; contrastive patch loss; crack detection; Cracks; Deep learning; Electric transformers; Image degradation; Maintenance; Public safety; Rain; Robots; robust representation; Training; Unmanned aerial vehicles; Weather
• ISSN: 2227-7390; 2227-7390
• DOI: 10.3390/math12050690

Crack detection is integral in civil infrastructure maintenance, with automated robots for detailed inspections and repairs becoming increasingly common. Ensuring fast and accurate crack detection for autonomous vehicles is crucial for safe road navigation. In these fields, existing detection models demonstrate impressive performance. However, they are primarily optimized for clear weather and struggle with occlusions and brightness variations in adverse weather conditions. These problems affect automated robots and autonomous vehicle navigation that must operate reliably in diverse environmental conditions. To address this problem, we propose Auxcoformer, designed for robust crack detection in adverse weather conditions. Considering the image degradation caused by adverse weather conditions, Auxcoformer incorporates an auxiliary restoration network. This network efficiently restores damaged crack details, ensuring the primary detection network obtains better quality features. The proposed approach uses a non-local patch-based 3D transform technique, emphasizing the characteristics of cracks and making them more distinguishable. Considering the connectivity of cracks, we also introduce contrastive patch loss for precise localization. Then, we demonstrate the performance of Auxcoformer, comparing it with other detection models through experiments.