{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T01:09:52Z","timestamp":1790298592607,"version":"4.1.0"},"reference-count":40,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T00:00:00Z","timestamp":1771027200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"CSLLPP"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The assessment of structural degradation in reinforced concrete bridges is a crucial task for infrastructure maintenance and safety. Traditional inspection methods are often time-consuming, dependent on expert interpretation and weather conditions. This study explores the potential of artificial intelligence to support inspectors in the detection of typical deterioration patterns in reinforced (RC) and prestressed concrete (PRC) bridges, developing the VIADUCT (Visual Inspection and Automated Damage Understanding by Computer vision Techniques) software tool. Unlike previous studies, focusing only on a limited variety of possible defects (e.g., cracks, water stains), this study aims to train a deep learning model to be able to recognise a larger range of defects, such as those foreseen by the current Italian code for the assessment of existing bridges. The methodology relies on the YOLOv8n object detection model, which was trained, validated, and tested using a dataset including 1045 either wide-angle or detailed photographs taken during routine inspections. With these kinds of images being challenging for object detection algorithms (they include large parts of the background), multimodal attention mechanisms were implemented in the Graphical User Interface (GUI) through the semantic segmentation of the bridge surface using both the SAM and the U-Net model, as well as a tile reduction approach. These attention mechanisms allow the object detection model to focus on the relevant portions of the image (i.e., the bridge), while suppressing background information. Despite the limitation of the small size dataset used for training, results showed promising detection capabilities and precision. Furthermore, VIADUCT is ready to accept and use newer and more efficient versions of the object detection model, as soon as they become available.<\/jats:p>","DOI":"10.3390\/s26041242","type":"journal-article","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T08:38:39Z","timestamp":1771231119000},"page":"1242","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A Code-Conforming Computer Vision Framework for Visual Inspection of Reinforced and Prestressed Concrete Bridges"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1182-9298","authenticated-orcid":false,"given":"Giuseppe","family":"Santarsiero","sequence":"first","affiliation":[{"name":"Department of Engineering, University of Basilicata, 85100 Potenza, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9497-9250","authenticated-orcid":false,"given":"Valentina","family":"Picciano","sequence":"additional","affiliation":[{"name":"Department of Engineering, University of Basilicata, 85100 Potenza, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicola","family":"Ventricelli","sequence":"additional","affiliation":[{"name":"Department of Engineering, University of Basilicata, 85100 Potenza, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4588-2812","authenticated-orcid":false,"given":"Angelo","family":"Masi","sequence":"additional","affiliation":[{"name":"Department of Engineering, University of Basilicata, 85100 Potenza, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"110659","DOI":"10.1016\/j.engstruct.2020.110659","article-title":"Collapse analysis of the Polcevera viaduct by the applied element method","volume":"214","author":"Domaneschi","year":"2020","journal-title":"Eng. Struct."},{"key":"ref_2","unstructured":"Ministero delle Infrastrutture e dei Trasporti (2020). Linee Guida per la Classificazione e Gestione del Rischio, la Valutazione Della Sicurezza ed il Monitoraggio dei Ponti Esistenti, italian technical code."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Santarsiero, G., Masi, A., Picciano, V., and Digrisolo, A. (2021). The Italian guidelines on risk classification and management of bridges: Applications and remarks on large-scale risk assessments. Infrastructures, 6.","DOI":"10.3390\/infrastructures6080111"},{"key":"ref_4","first-page":"100190","article-title":"Structural health monitoring of exterior beam\u2013column subassemblies through detailed numerical modelling and using various machine learning techniques","volume":"6","author":"Santarsiero","year":"2021","journal-title":"Mach. Learn. Appl."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref_6","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_7","doi-asserted-by":"crossref","first-page":"105210","DOI":"10.1016\/j.rineng.2025.105210","article-title":"Automated assessment of bridge guardrails for regional prioritization based on open-source data and deep learning algorithms","volume":"26","author":"Santarsiero","year":"2025","journal-title":"Results Eng."},{"key":"ref_8","first-page":"277","article-title":"Generative AI and ChatGPT: Applications, challenges, and AI-human collaboration","volume":"25","author":"Zheng","year":"2023","journal-title":"J. Inf. Technol. Case Appl. Res."},{"key":"ref_9","unstructured":"Autodesk, and Deloitte (2024). State of Digital Adoption in the Construction Industry, Autodesk. Report."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Ni, Y., Mao, J., Fu, Y., Wang, H., Zong, H., and Luo, K. (2023). Damage Detection and Localization of Bridge Deck Pavement Based on Deep Learning. Sensors, 23.","DOI":"10.3390\/s23115138"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1007\/s43503-024-00034-6","article-title":"Evaluating fine tuned deep learning models for real-time earthquake damage assessment with drone-based images","volume":"3","author":"Kizilay","year":"2024","journal-title":"AI Civ. Eng."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1188","DOI":"10.1111\/mice.12815","article-title":"Multicategory damage detection and safety assessment of post-earthquake reinforced concrete structures using deep learning","volume":"37","author":"Zou","year":"2022","journal-title":"Comput. Aided Civ. Inf."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"115629","DOI":"10.1016\/j.engstruct.2023.115629","article-title":"Detection of damages caused by earthquake and reinforcement corrosion in RC buildings with Deep Transfer Learning","volume":"279","author":"Dogan","year":"2023","journal-title":"Eng. Struct."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"229591","DOI":"10.1016\/j.tecto.2022.229591","article-title":"The 2020 Samos Mw7 earthquake: Source model depicting complexity and rupture directivity","volume":"843","author":"Plicka","year":"2022","journal-title":"Tectonophysics"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"327","DOI":"10.5194\/isprs-archives-XLVIII-2-W8-2024-327-2024","article-title":"Deep Learning-Based AI-Assisted Visual Inspection Systems for Historic Buildings and their Comparative Performance with ChatGPT-4O","volume":"48","author":"Mishra","year":"2024","journal-title":"Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"107105","DOI":"10.1016\/j.jobe.2023.107105","article-title":"Deep learning for crack detection on masonry fa\u00e7ades using limited data and transfer learning","volume":"76","author":"Katsigiannis","year":"2023","journal-title":"J. Build. Eng."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"103514","DOI":"10.1016\/j.dsp.2022.103514","article-title":"A survey of modern deep learning based object detection models","volume":"126","author":"Zaidi","year":"2022","journal-title":"Digit. Signal Process."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016). Rethinking the inception architecture for computer vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE. Available online: http:\/\/ieeexplore.ieee.org\/document\/7780677\/.","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"e21450","DOI":"10.1016\/j.heliyon.2023.e21450","article-title":"PV resource evaluation based on Xception and VGG19 two-layer network algorithm","volume":"9","author":"Li","year":"2023","journal-title":"Heliyon"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1080\/15583058.2024.2376177","article-title":"Automated Surface Crack Detection in Historical Constructions with Various Materials Using Deep Learning-Based YOLO Network","volume":"19","author":"Karimi","year":"2024","journal-title":"Int. J. Archit. Herit."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"115635","DOI":"10.1016\/j.measurement.2024.115635","article-title":"Recognition and quantification of apparent damage to concrete structure based on computer vision","volume":"240","author":"Liu","year":"2025","journal-title":"Measurement"},{"key":"ref_22","first-page":"04023048","article-title":"Deep learning-based detection and condition classification of bridge steel bearings","volume":"28","author":"Wang","year":"2023","journal-title":"Autom. Constr."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"105601","DOI":"10.1016\/j.autcon.2024.105601","article-title":"Deep learning for automated multiclass surface damage detection in bridge inspections","volume":"166","author":"Huang","year":"2024","journal-title":"Autom. Constr."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"12052","DOI":"10.1038\/s41598-024-62933-z","article-title":"YOLOv8-PD: An Improved Road damage detection algorithm based on YOLOv8n model","volume":"14","author":"Zeng","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Fukuoka, T., and Fujiu, M. (2023). Detection of Bridge Damages by Image Processing Using the Deep Learning Transformer Model. Buildings, 13.","DOI":"10.3390\/buildings13030788"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Yamane, T., Chun, P.J., Dang, J., and Okatani, T. (2024). Deep learning-based bridge damage cause estimation from multiple images using visual question answering. Struct. Infrastruct. Eng., 1\u201314.","DOI":"10.1080\/15732479.2024.2355929"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"8627","DOI":"10.1038\/s41598-024-58707-2","article-title":"Enhanced YOLO v3 for precise detection of apparent damage on bridges amidst complex backgrounds","volume":"14","author":"Su","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"103514","DOI":"10.1016\/j.autcon.2020.103514","article-title":"A real-time detection approach for bridge cracks based on YOLOv4-FPM","volume":"122","author":"Yu","year":"2021","journal-title":"Autom. Constr."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"104555","DOI":"10.1016\/j.autcon.2022.104555","article-title":"Concrete dam damage detection and localisation based on YOLOv5s-HSC and photogrammetric 3D reconstruction","volume":"143","author":"Zhao","year":"2022","journal-title":"Autom. Constr."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Dong, X., Liu, Y., and Dai, J. (2024). Concrete Surface Crack Detection Algorithm Based on Improved YOLOv8. Sensors, 24.","DOI":"10.3390\/s24165252"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"18994","DOI":"10.1109\/ACCESS.2025.3532832","article-title":"Using Attention for Improving Defect Detection in Existing RC Bridges","volume":"13","author":"Ruggieri","year":"2025","journal-title":"IEEE Access"},{"key":"ref_32","first-page":"47","article-title":"Eigen-CAM: Visual explanations for deep convolutional neural networks","volume":"2","author":"Muhammad","year":"2021","journal-title":"Soc. Social. Netw. Comput. Sci."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1186\/s43251-022-00073-y","article-title":"Advanced bridge visual inspection using real-time machine learning in edge devices","volume":"3","author":"Zakaria","year":"2022","journal-title":"Adv. Bridge Eng."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"115536","DOI":"10.1016\/j.measurement.2024.115536","article-title":"A portable real-time concrete bridge damage detection system","volume":"240","author":"Chen","year":"2025","journal-title":"Measurement"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"100648","DOI":"10.1016\/j.atech.2024.100648","article-title":"Comparative performance of YOLOv8, YOLOv9, YOLOv10, YOLOv11 and Faster R-CNN models for detection of multiple weed species","volume":"9","author":"Sharma","year":"2024","journal-title":"Smart Agric. Technol."},{"key":"ref_36","unstructured":"Dwyer, B., Nelson, J., Hansen, T., and Solawetz, J. (2025, April 14). Roboflow (Version 1.0) [Software]. Available online: https:\/\/roboflow.com."},{"key":"ref_37","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). Segment Anything. Proceedings of the IEEE\/CVF International Conference on Computer Vision, IEEE.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. arXiv.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"\u00dcnel, F.\u00d6., \u00d6zkalayci, B.O., and \u00c7i\u011fla, C. (2019, January 16\u201317). The Power of Tiling for Small Object Detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Long Beach, CA, USA.","DOI":"10.1109\/CVPRW.2019.00084"},{"key":"ref_40","unstructured":"(2026, February 07). Demonstration Video of VIADUCT Visual Inspection Pipeline Set up by HAIRI (Human-Driven AI for Resilient Infrastructure) Laboratory at University of Basilicata, Italy. Available online: https:\/\/youtu.be\/bWD7NJa5gec."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/4\/1242\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T08:39:07Z","timestamp":1771231147000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/4\/1242"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,14]]},"references-count":40,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["s26041242"],"URL":"https:\/\/doi.org\/10.3390\/s26041242","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,14]]}}}