eprintid: 10192868 rev_number: 7 eprint_status: archive userid: 699 dir: disk0/10/19/28/68 datestamp: 2024-05-30 13:06:54 lastmod: 2024-05-30 13:06:54 status_changed: 2024-05-30 13:06:54 type: article metadata_visibility: show sword_depositor: 699 creators_name: Chu, H creators_name: Chen, W creators_name: Deng, L title: Cascade operation-enhanced high-resolution representation learning for meticulous segmentation of bridge cracks ispublished: pub divisions: UCL divisions: B04 divisions: C04 keywords: Deep learning, Crack segmentation, Cascade operation, Attention mechanism, High-resolution crack images, UAV crack inspection note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. abstract: High-resolution (HR) crack images have proven valuable for bridge inspection using unmanned aerial vehicles (UAVs), offering fine details crucial for accurate segmentation. Traditional deep learning (DL) struggles with HR images due to downsampling issues and limited computational resources. To address this, we propose Cascade-FcaHRNet, a HR representation learning-based multiscale architecture. It incorporates a frequency-channel attention mechanism to capture tiny crack features, a two-stage cascade operation for global and local refinement, and a region-sensitive loss to avoid ambiguous predictions. Ablation studies confirm the effectiveness of these modifications. Robustness experiments show improvements in performance metrics for crack segmentation. In a field test, the Cascade-FcaHRNet accurately segments bridge cracks wider than 0.5 mm from 4 K resolution images, enhancing safety and efficiency in UAV-based bridge inspection. The approach holds potential for developing scientifically sound maintenance and management strategies. date: 2024-08-01 date_type: published publisher: Elsevier BV official_url: http://dx.doi.org/10.1016/j.aei.2024.102508 full_text_type: other language: eng verified: verified_manual elements_id: 2266394 doi: 10.1016/j.aei.2024.102508 lyricists_name: Chen, Weiwei lyricists_id: WCHEF68 actors_name: Chen, Weiwei actors_id: WCHEF68 actors_role: owner full_text_status: restricted publication: Advanced Engineering Informatics volume: 61 article_number: 102508 issn: 1474-0346 citation: Chu, H; Chen, W; Deng, L; (2024) Cascade operation-enhanced high-resolution representation learning for meticulous segmentation of bridge cracks. Advanced Engineering Informatics , 61 , Article 102508. 10.1016/j.aei.2024.102508 <https://doi.org/10.1016/j.aei.2024.102508>. document_url: https://discovery.ucl.ac.uk/id/eprint/10192868/1/Cascade%20Operation-Enhanced%20High-Resolution%20Representation%20Learning%20for%20Meticulous%20Segmentation%20of%20Bridge%20Cracks-%20accepted%20version.pdf