{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T18:38:37Z","timestamp":1778179117090,"version":"3.51.4"},"reference-count":31,"publisher":"MDPI AG","issue":"21","license":[{"start":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T00:00:00Z","timestamp":1761350400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The automated inspection of civil infrastructure with Unmanned Aerial Vehicles (UAVs) is hampered by the challenge of accurately segmenting multi-damage in high-resolution imagery. While foundational models like the Segment Anything Model (SAM) offer data-efficient segmentation, their effectiveness is constrained by prompting strategies, especially for geometrically complex defects. This paper presents a comprehensive comparative analysis of deep learning strategies to identify an optimal deep learning pipeline for segmenting cracks, efflorescences, and exposed rebars. It systematically evaluates three distinct end-to-end segmentation frameworks: the native output of a YOLO11 model; the Segment Anything Model (SAM), prompted by bounding boxes; and SAM, guided by a point-prompting mechanism derived from the detector\u2019s probability map. Based on these findings, a final, optimized hybrid pipeline is proposed: for linear cracks, the native segmentation output of the SAHI-trained YOLO model is used, while for efflorescence and exposed rebar, the model\u2019s bounding boxes are used to prompt SAM for a refined segmentation. This class-specific strategy yielded a final mean Average Precision (mAP50) of 0.593, with class-specific Intersection over Union (IoU) scores of 0.495 (cracks), 0.331 (efflorescence), and 0.205 (exposed rebar). The results establish that the future of automated inspection lies in intelligent frameworks that leverage the respective strengths of specialized detectors and powerful foundation models in a context-aware manner.<\/jats:p>","DOI":"10.3390\/s25216568","type":"journal-article","created":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T05:48:46Z","timestamp":1761716926000},"page":"6568","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A Hybrid YOLO and Segment Anything Model Pipeline for Multi-Damage Segmentation in UAV Inspection Imagery"],"prefix":"10.3390","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9214-4823","authenticated-orcid":false,"given":"Rafael","family":"Cabral","sequence":"first","affiliation":[{"name":"CONSTRUCT\u2014iRail, Faculty of Engineering, University of Porto, 4200-465 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2929-8950","authenticated-orcid":false,"given":"Ricardo","family":"Santos","sequence":"additional","affiliation":[{"name":"CONSTRUCT\u2014iRail, Faculty of Engineering, University of Porto, 4200-465 Porto, Portugal"},{"name":"iBuilt, School of Engineering, Polytechnic of Porto, 4249-015 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4148-9426","authenticated-orcid":false,"given":"Jos\u00e9 A. F. O.","family":"Correia","sequence":"additional","affiliation":[{"name":"CONSTRUCT\u2014iRail, Faculty of Engineering, University of Porto, 4200-465 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8624-9904","authenticated-orcid":false,"given":"Diogo","family":"Ribeiro","sequence":"additional","affiliation":[{"name":"CONSTRUCT\u2014iRail, Faculty of Engineering, University of Porto, 4200-465 Porto, Portugal"},{"name":"iBuilt, School of Engineering, Polytechnic of Porto, 4249-015 Porto, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2025,10,25]]},"reference":[{"key":"ref_1","unstructured":"ASCE (2021). Report Card for America\u2009s Infrastructure: Bridges, American Society of Civil Engineers."},{"key":"ref_2","unstructured":"Moore, M., Phares, B.M., Graybeal, B., Rolander, D., Washer, G., and Wiss, J. (2008). Reliability of Visual Inspection for Highway Bridges, No. FHWA-RD-01-105."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"5530300","DOI":"10.1155\/2024\/5530300","article-title":"Partial-model-based damage identification of long-span steel truss bridge based on stiffness separation method","volume":"2024","author":"Xiao","year":"2024","journal-title":"Struct. Control. Health Monit."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Kim, I.H., Jeon, H., Baek, S.C., Hong, W.H., and Jung, H.J. (2018). Application of Crack Identification Techniques for an Aging Concrete Bridge Inspection Using an Unmanned Aerial Vehicle. Sensors, 18.","DOI":"10.3390\/s18061881"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1080\/10168664.2024.2368220","article-title":"Technologies and Platforms for Remote and Autonomous Bridge Inspection\u2014Review","volume":"35","author":"Rakoczy","year":"2025","journal-title":"Struct. Eng. Int."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Lemos, R., Cabral, R., Ribeiro, D., Santos, R., Alves, V., and Dias, A. (2023). Automatic Detection of Corrosion in Large-Scale Industrial Buildings Based on Artificial Intelligence and Unmanned Aerial Vehicles. Appl. Sci., 13.","DOI":"10.3390\/app13031386"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Olaszek, P., Maciejewski, E., Rakoczy, A., Cabral, R., Santos, R., and Ribeiro, D. (2024). Remote Inspection of Bridges with the Integration of Scanning Total Station and Unmanned Aerial Vehicle Data. Remote Sens., 16.","DOI":"10.3390\/rs16224176"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1031","DOI":"10.1016\/j.conbuildmat.2018.08.011","article-title":"Comparison of deep convolutional neural networks and edge detectors for image-based crack detection in concrete","volume":"186","author":"Dorafshan","year":"2018","journal-title":"Constr. Build. Mater."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27\u201330). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","volume":"39","author":"Ren","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Sun, S., Liu, W., and Cui, R. (2022, January 1\u20133). YOLO Based Bridge Surface Defect Detection Using Decoupled Prediction. Proceedings of the 7th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS), Tianjin, China.","DOI":"10.1109\/ACIRS55390.2022.9845546"},{"key":"ref_12","first-page":"e03722","article-title":"Recognition of steel bridge corrosion considering the effect of training dataset quality","volume":"21","author":"Wang","year":"2024","journal-title":"Case Stud. Constr. Mater."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"109742","DOI":"10.1016\/j.measurement.2021.109742","article-title":"An optimized railway fastener detection method based on modified Faster R-CNN","volume":"182","author":"Bai","year":"2021","journal-title":"Measurement"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Cabral, R., Ribeiro, D., and Rakoczy, A. (2024). Engineering the Future: A Deep Dive into Remote Inspection and Reality Capture for Railway Infrastructure Digitalization. Digital Railway Infrastructure, Springer.","DOI":"10.1007\/978-3-031-49589-2_12"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., and Darrell, T. (2015, January 7\u201312). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5\u20139). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_17","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_18","doi-asserted-by":"crossref","unstructured":"He, K.M., Gkioxari, G., Doll\u00e1r, P., and Girshick, R. (2017, January 22\u201329). Mask R-CNN. Proceedings of the International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Santos J\u00fanior, E.S.D., Paix\u00e3o, T., and Alvarez, A.B. (2025). Comparative performance of YOLOv8, YOLOv9, YOLOv10, and YOLOv11 for layout analysis of historical documents images. Appl. Sci., 15.","DOI":"10.3390\/app15063164"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Shao, Y., Li, L., Li, J., Yao, X., Li, Q., and Hao, H. (2025). Advancing crack detection with generative AI for structural health monitoring. Struct. Health Monit., 14759217251369000.","DOI":"10.1177\/14759217251369000"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1170","DOI":"10.1177\/14759217231182303","article-title":"A novel transformer-based semantic segmentation framework for structural condition assessment","volume":"23","author":"Wang","year":"2024","journal-title":"Struct. Health Monit."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"e2117","DOI":"10.1002\/tal.2117","article-title":"Intelligent crack identification method for high-rise buildings aided by synthetic environments","volume":"33","author":"Yao","year":"2024","journal-title":"Struct. Des. Tall Spec. Build."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Rodriguez-Vazquez, J., Fernandez-Cortizas, M., Perez-Saura, D., Molina, M., and Campoy, P. (2023). Overcoming Domain Shift in Neural Networks for Accurate Plant Counting in Aerial Images. Remote Sens., 15.","DOI":"10.20944\/preprints202302.0070.v1"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., and Lo, W.-Y. (2023, January 1\u20136). Segment Anything. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Paris, France.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1186\/s43065-024-00103-1","article-title":"Crack SAM: Enhancing crack detection utilizing foundation models and Detectron2 architecture","volume":"5","author":"Rakshitha","year":"2024","journal-title":"J. Infrastruct. Preserv. Resil."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"106037","DOI":"10.1016\/j.autcon.2025.106037","article-title":"Multi-class segmentation of structural damage and pathological manifestations using YOLOv8 and Segment Anything Model","volume":"172","author":"Santos","year":"2025","journal-title":"Autom. Constr."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Flotzinger, J., R\u00f6sch, P.J., and Braml, T. (2024, January 3\u20138). dacl10k: Benchmark for semantic bridge damage segmentation. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA.","DOI":"10.1109\/WACV57701.2024.00843"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Benjdira, B., Bazi, Y., Koubaa, A., and Ouni, K. (2019). Unsupervised Domain Adaptation Using Generative Adversarial Networks for Semantic Segmentation of Aerial Images. Remote Sens., 11.","DOI":"10.3390\/rs11111369"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"11434","DOI":"10.1109\/JSTARS.2024.3407808","article-title":"Cross-Domain Land Cover Classification of Remote Sensing Images Based on Full-Level Domain Adaptation","volume":"17","author":"Meng","year":"2024","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"073001","DOI":"10.1088\/1361-665X\/ade7db","article-title":"Systematic critical review of structural health monitoring under environmental and operational variability: Approaches for baseline compensation, adaptation, and reference-free techniques","volume":"34","author":"Rezazadeh","year":"2025","journal-title":"Smart Mater. Struct."},{"key":"ref_31","unstructured":"(2025, January 16). Ultralytics. YOLO11. Available online: https:\/\/github.com\/ultralytics\/ultralytics."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/21\/6568\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T05:51:46Z","timestamp":1761717106000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/21\/6568"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,25]]},"references-count":31,"journal-issue":{"issue":"21","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["s25216568"],"URL":"https:\/\/doi.org\/10.3390\/s25216568","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,25]]}}}