RTCNet: A novel real-time triple branch network for pavement crack semantic segmentation

• Published in: International journal of applied earth observation and geoinformation Vol. 136; p. 104347
• Main Authors: Liu, Bin, Kang, Jian, Guan, Haiyan, Zhi, Xiaodong, Yu, Yongtao, Ma, Lingfei, Peng, Daifeng, Xu, Linlin, Wang, Dongchuan
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.02.2025; Elsevier
• Subjects: cameras; data collection; decision making; Deep learning; Pavement crack detection; pavements; Real-time semantic segmentation; spatial data; Transformer; Triple-branch network; Deep learning; Triple-branch network; Transformer; Pavement crack detection; Real-time semantic segmentation

•A novel real-time triple-branch network was proposed for pavement crack detection under complex scenarios.•A transformer module for enlarging the global receptive field while preserving local details of cracks.•A boundary refinement module was designed to refine crack boundaries.•A manually annotat...