{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:05:36Z","timestamp":1778083536905,"version":"3.51.4"},"reference-count":39,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T00:00:00Z","timestamp":1753315200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Guangzhou Railway Polytechnic","award":["GTXYR2431"],"award-info":[{"award-number":["GTXYR2431"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Achieving state-of-the-art performance (82.5% IoU, 85.6% F1), this paper proposes an enhanced DeepLabV3+ model for robust underwater crack detection through three integrated innovations: a physics-based light propagation correction model for illumination distortion, multi-scale feature extraction for variable crack dimensions, and curvature flow-guided loss for boundary precision. Our approach significantly outperforms DeepLabV3+, SCTNet, and LarvSeg by 10.6\u201313.4% IoU, demonstrating particular strength in detecting small cracks (78.1% IoU) under challenging low-light\/high-turbidity conditions. The solution provides a practical framework for automated underwater infrastructure inspection.<\/jats:p>","DOI":"10.3390\/a18080462","type":"journal-article","created":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T14:11:44Z","timestamp":1753366304000},"page":"462","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Light Propagation and Multi-Scale Enhanced DeepLabV3+ for Underwater Crack Detection"],"prefix":"10.3390","volume":"18","author":[{"given":"Wenji","family":"Ai","sequence":"first","affiliation":[{"name":"College of Transportation and Logistics, Guangzhou Railway Polytechnic, Guangzhou 511300, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaxuan","family":"Zou","sequence":"additional","affiliation":[{"name":"College of Transportation and Logistics, Guangzhou Railway Polytechnic, Guangzhou 511300, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7331-7987","authenticated-orcid":false,"given":"Zongchao","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Transportation and Logistics, Guangzhou Railway Polytechnic, Guangzhou 511300, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaodi","family":"Wang","sequence":"additional","affiliation":[{"name":"Earthquake Engineering Research & Test Center, Guangzhou University, Guangzhou 510006, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1703-3362","authenticated-orcid":false,"given":"Shuai","family":"Teng","sequence":"additional","affiliation":[{"name":"School of Intelligent Construction and Civil Engineering, Zhongyuan University of Technology, Zhengzhou 450007, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,7,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"3853","DOI":"10.1109\/TII.2021.3117034","article-title":"Visual and Intelligent Identification Methods for Defects in Underwater Structure Using Alternating Current Field Measurement Technique","volume":"18","author":"Yuan","year":"2022","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1415","DOI":"10.1080\/01691864.2016.1218794","article-title":"Development of a stable localized visual inspection system for underwater structures","volume":"30","author":"Yang","year":"2016","journal-title":"Adv. Robot."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1378","DOI":"10.1007\/s11709-022-0855-8","article-title":"Detecting large-scale underwater cracks based on remote operated vehicle and graph convolutional neural network","volume":"16","author":"Cao","year":"2022","journal-title":"Front. Struct. Civ. Eng."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1016\/j.aej.2023.07.011","article-title":"Method for detecting surface defects of underwater buildings: Binocular vision based on sinusoidal grating fringe assistance","volume":"78","author":"Bi","year":"2023","journal-title":"Alex. Eng. J."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"8760324","DOI":"10.1155\/2020\/8760324","article-title":"Improved Dark Channel Defogging Algorithm for Defect Detection in Underwater Structures","volume":"2020","author":"Bao","year":"2020","journal-title":"Adv. Mater. Sci. Eng."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1520\/JTE100662","article-title":"Thickness Gaging of Thin Plates by Multi-Peak Frequency Decomposition of Lamb Wave Signals","volume":"36","author":"Edalati","year":"2008","journal-title":"J. Test. Eval."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1504\/IJMPT.2006.011268","article-title":"Defect detection in thin plates by ultrasonic lamb wave techniques","volume":"27","author":"Edalati","year":"2006","journal-title":"Int. J. Mater. Prod. Technol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"114969","DOI":"10.1016\/j.measurement.2024.114969","article-title":"Method of interval fusion with preference aggregation in brightness thresholds selection for automatic weld surface defects recognition","volume":"236","author":"Muravyov","year":"2024","journal-title":"Measurement"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1280","DOI":"10.1134\/S1061830923600855","article-title":"Automatic Segmentation by the Method of Interval Fusion with Preference Aggregation When Recognizing Weld Defects","volume":"59","author":"Muravyov","year":"2023","journal-title":"Russ. J. Nondestruct. Test."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1016\/j.neucom.2023.01.056","article-title":"A systematic review and analysis of deep learning-based underwater object detection","volume":"527","author":"Xu","year":"2023","journal-title":"Neurocomputing"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"551","DOI":"10.1177\/1475921716651039","article-title":"A detection and classification approach for underwater dam cracks","volume":"15","author":"Shi","year":"2016","journal-title":"Struct. Health Monit."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"20899","DOI":"10.1007\/s11042-022-14168-1","article-title":"ROV-based binocular vision system for underwater structure crack detection and width measurement","volume":"82","author":"Ma","year":"2023","journal-title":"Multimed. Tools Appl."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"101662","DOI":"10.1016\/j.uclim.2023.101662","article-title":"Damage identification of railway bridge underwater foundations based on optical images","volume":"51","author":"Jinchao","year":"2023","journal-title":"Urban Clim."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"23103","DOI":"10.1007\/s00521-023-08957-4","article-title":"Deep learning: Systematic review, models, challenges, and research directions","volume":"35","author":"Kaabouch","year":"2023","journal-title":"Neural Comput. Appl."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zhu, S.S., Li, X.Y., Wan, G., Wang, H.R., Shao, S., and Shi, P.F. (2024). Underwater Dam Crack Image Classification Algorithm Based on Improved VanillaNet. Symmetry, 16.","DOI":"10.3390\/sym16070845"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"3893","DOI":"10.1049\/ipr2.12602","article-title":"A method of underwater bridge structure damage detection method based on a lightweight deep convolutional network","volume":"16","author":"Li","year":"2022","journal-title":"IET Image Process."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Talib, L.F., Amin, J., Sharif, M., and Raza, M. (2024). Transformer-based semantic segmentation and CNN network for detection of histopathological lung cancer. Biomed. Signal Process. Control, 92.","DOI":"10.1016\/j.bspc.2024.106106"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Dong, Q., Chen, X., Jiang, L., Wang, L., Chen, J., and Zhao, Y. (2024). Semantic Segmentation of Remote Sensing Images Depicting Environmental Hazards in High-Speed Rail Network Based on Large-Model Pre-Classification. Sensors, 24.","DOI":"10.3390\/s24061876"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"04024101","DOI":"10.1061\/JBENF2.BEENG-7032","article-title":"Underwater Surface Defect Recognition of Bridges Based on Fusion of Semantic Segmentation and Three-Dimensional Point Cloud","volume":"30","author":"Hou","year":"2025","journal-title":"J. Bridge Eng."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2650","DOI":"10.1111\/mice.13401","article-title":"Two-step rapid inspection of underwater concrete bridge structures combining sonar, camera, and deep learning","volume":"40","author":"Sun","year":"2024","journal-title":"Comput.-Aided Civ. Infrastruct. Eng."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"112151","DOI":"10.1016\/j.ymssp.2024.112151","article-title":"Transfer learning in bridge monitoring: Laboratory study on domain adaptation for population-based SHM of multispan continuous girder bridges","volume":"224","author":"Giglioni","year":"2025","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.undsp.2023.09.012","article-title":"Transfer learning-based encoder-decoder model with visual explanations for infrastructure crack segmentation: New open database and comprehensive evaluation","volume":"17","author":"Liu","year":"2024","journal-title":"Undergr. Space"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"104600","DOI":"10.1016\/j.autcon.2022.104600","article-title":"Underwater crack pixel-wise identification and quantification for dams via lightweight semantic segmentation and transfer learning","volume":"144","author":"Li","year":"2022","journal-title":"Autom. Constr."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"105906","DOI":"10.1016\/j.autcon.2024.105906","article-title":"Plug-and-play method for segmenting concrete bridge cracks using the segment anything model with a fractal dimension matrix prompt","volume":"170","author":"Teng","year":"2025","journal-title":"Autom. Constr."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Xu, Z., Wu, D., Yu, C., Chu, X., Sang, N., and Gao, C. (2024, January 20\u201327). SCTNet: Single-Branch CNN with Transformer Semantic Information for Real-Time Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, Vancouver, BC, Canada.","DOI":"10.1609\/aaai.v38i6.28457"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Yu, H., Dai, D., Zhao, Z., He, D., Hu, H., and Wang, L. (2024, January 18\u201320). LarvSeg: Exploring Image Classification Data for Large Vocabulary Semantic Segmentation via Category-Wise Attentive Classifier. Proceedings of the Chinese Conference on Pattern Recognition and Computer Vision (PRCV), Singapore.","DOI":"10.1007\/978-981-97-8487-5_4"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Bai, Y., Li, J., Shi, L., Jiang, Q., Yan, B., and Wang, Z. (2023). DME-DeepLabV3+: A lightweight model for diabetic macular edema extraction based on DeepLabV3+ architecture. Front. Med., 10.","DOI":"10.3389\/fmed.2023.1150295"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"6228532","DOI":"10.1155\/2022\/6228532","article-title":"Semantic Segmentation of PHT Based on Improved DeeplabV3+","volume":"2022","author":"Fang","year":"2022","journal-title":"Math. Probl. Eng."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., and Adam, H. (2018, January 8\u201314). Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.C. (2018, January 18\u201323). MobileNetV2: Inverted Residuals and Linear Bottlenecks. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1016\/j.oceaneng.2014.11.036","article-title":"Deriving inherent optical properties from background color and underwater image enhancement","volume":"94","author":"Zhao","year":"2015","journal-title":"Ocean Eng."},{"key":"ref_32","unstructured":"Gonzalez, R., and Woods, R. (2018). Digital Image Processing, Pearson Education."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"878","DOI":"10.1016\/j.ijleo.2017.05.022","article-title":"Modeling and simulating the bidirectional reflectance distribution function (BRDF) of seawater polluted by oil emulsion","volume":"140","author":"Chen","year":"2017","journal-title":"Optik"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Zhao, C., Lv, W., Zhang, X., Yu, Z., and Wang, S. (2023). MMS-Net: Multi-level multi-scale feature extraction network for medical image segmentation. Biomed. Signal Process. Control, 86.","DOI":"10.1016\/j.bspc.2023.105330"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1023\/A:1021893111352","article-title":"Digital Curvature Flow and Its Application for Skeletonization","volume":"18","author":"Imiya","year":"2003","journal-title":"J. Math. Imaging Vis."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1007\/s10711-017-0271-8","article-title":"Gauss maps of the Ricci-mean curvature flow","volume":"194","author":"Koike","year":"2018","journal-title":"Geom. Dedicata"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"100191","DOI":"10.1016\/j.dibe.2023.100191","article-title":"A transfer learning-based YOLO network for sewer defect detection in comparison to classic object detection methods","volume":"15","author":"Situ","year":"2023","journal-title":"Dev. Built Environ."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1016\/j.istruc.2023.05.062","article-title":"Surface concrete cracks detection and segmentation using transfer learning and multi-resolution image processing","volume":"54","author":"Iraniparast","year":"2023","journal-title":"Structures"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"104950","DOI":"10.1016\/j.autcon.2023.104950","article-title":"Automatic concrete infrastructure crack semantic segmentation using deep learning","volume":"152","author":"Chen","year":"2023","journal-title":"Autom. Constr."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/8\/462\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:15:33Z","timestamp":1760033733000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/8\/462"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,24]]},"references-count":39,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["a18080462"],"URL":"https:\/\/doi.org\/10.3390\/a18080462","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,24]]}}}