{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T20:19:59Z","timestamp":1778962799124,"version":"3.51.4"},"reference-count":39,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2023,1,20]],"date-time":"2023-01-20T00:00:00Z","timestamp":1674172800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"national funds","award":["UIDB\/04708\/2020"],"award-info":[{"award-number":["UIDB\/04708\/2020"]}]},{"name":"national funds","award":["UI\/BD\/150970\/2021"],"award-info":[{"award-number":["UI\/BD\/150970\/2021"]}]},{"name":"Multiprojectus\/Garcia Garcia","award":["UIDB\/04708\/2020"],"award-info":[{"award-number":["UIDB\/04708\/2020"]}]},{"name":"Multiprojectus\/Garcia Garcia","award":["UI\/BD\/150970\/2021"],"award-info":[{"award-number":["UI\/BD\/150970\/2021"]}]},{"name":"Portuguese Science Foundation","award":["UIDB\/04708\/2020"],"award-info":[{"award-number":["UIDB\/04708\/2020"]}]},{"name":"Portuguese Science Foundation","award":["UI\/BD\/150970\/2021"],"award-info":[{"award-number":["UI\/BD\/150970\/2021"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Applied Sciences"],"abstract":"<jats:p>In recent years, Artificial Intelligence (AI) provided essential tools to enhance the productivity of activities related to civil engineering, particularly in design, construction, and maintenance. In this framework, the present work proposes a novel AI computer vision methodology for automatically identifying the corrosion phenomenon on roofing systems of large-scale industrial buildings. The proposed method can be incorporated into computational packages for easier integration by the industry to enhance the inspection activities\u2019 performance. For this purpose, a dedicated image database with more than 8k high-resolution aerial images was developed for supervised training. An Unmanned Aerial Vehicle (UAV) was used to acquire remote georeferenced images safely and efficiently. The corrosion anomalies were manually annotated using a segmentation strategy summing up 18,381 instances. These anomalies were identified through instance segmentation using the Mask based Region-Convolution Neural Network (Mask R-CNN) framework adjusted to the created dataset. Some adjustments were performed to enhance the performance of the classification model, particularly defining an adequate input image size, data augmentation strategy, Intersection over a Union (IoU) threshold during training, and type of backbone network. The inferences show promising results, with correct detections even under complex backgrounds, poor illumination conditions, and instances of significantly reduced dimensions. Furthermore, in scenarios without a roofing system, the model proved reliable, not producing any false positive occurrences. The best model achieved metrics\u2019 values equal to 65.1% for the bounding box detection Average Precision (AP) and 59.2% for the mask AP, considering an IoU of 50%. Regarding classification metrics, the precision and recall were equal to 85.8% and 84.0%, respectively. The developed methodology proved to be extremely valuable for guiding infrastructure managers in taking physically informed decisions based on the real assets condition.<\/jats:p>","DOI":"10.3390\/app13031386","type":"journal-article","created":{"date-parts":[[2023,1,20]],"date-time":"2023-01-20T06:52:41Z","timestamp":1674197561000},"page":"1386","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":48,"title":["Automatic Detection of Corrosion in Large-Scale Industrial Buildings Based on Artificial Intelligence and Unmanned Aerial Vehicles"],"prefix":"10.3390","volume":"13","author":[{"given":"Rafael","family":"Lemos","sequence":"first","affiliation":[{"name":"Department of Civil Engineering, School of Mines, Federal University of Ouro Preto, Ouro Preto 35400-000, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9214-4823","authenticated-orcid":false,"given":"Rafael","family":"Cabral","sequence":"additional","affiliation":[{"name":"CONSTRUCT-LESE, 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-LESE, School of Engineering, Polytechnic of Porto, 4249-015 Porto, Portugal"}]},{"given":"Ricardo","family":"Santos","sequence":"additional","affiliation":[{"name":"CONSTRUCT-LESE, School of Engineering, Polytechnic of Porto, 4249-015 Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8572-0722","authenticated-orcid":false,"given":"Vinicius","family":"Alves","sequence":"additional","affiliation":[{"name":"Department of Civil Engineering, School of Mines, Federal University of Ouro Preto, Ouro Preto 35400-000, Brazil"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5734-075X","authenticated-orcid":false,"given":"Andr\u00e9","family":"Dias","sequence":"additional","affiliation":[{"name":"INESC TEC, School of Engineering, Polytechnic of Porto, 4249-015 Porto, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2023,1,20]]},"reference":[{"key":"ref_1","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_2","doi-asserted-by":"crossref","unstructured":"Ya\u011f, \u0130., and Altan, A. (2022). Artificial Intelligence-Based Robust Hybrid Algorithm Design and Implementation for Real-Time Detection of Plant Diseases in Agricultural Environments. Biology, 11.","DOI":"10.3390\/biology11121732"},{"key":"ref_3","unstructured":"(2023, January 11). Work-Related Fatal Injuries in Great Britain, Available online: https:\/\/www.hse.gov.uk\/statistics\/pdf\/fatalinjuries.pdf."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Rey-Merch\u00e1n, M.D.C., G\u00f3mez-de-Gabriel, J.M., L\u00f3pez-Arquillos, A., and Choi, S.D. (2021). Analysis of Falls from Height Variables in Occupational Accidents. Int. J. Environ. Res. Public. Health, 18.","DOI":"10.3390\/ijerph182413417"},{"key":"ref_5","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_6","first-page":"248","article-title":"ImageNet: A Large-Scale Hierarchical Image Database","volume":"8","author":"Deng","year":"2009","journal-title":"CVPR"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1109\/TPAMI.2015.2437384","article-title":"Region-Based Convolutional Networks for Accurate Object Detection and Segmentation","volume":"38","author":"Girshick","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_8","unstructured":"Ren, S., He, K., Girshick, R., and Sun, J. (2016). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. arXiv, Available online: https:\/\/arxiv.org\/abs\/1506.01497."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Dollar, P., and Girshick, R. (2017, January 22\u201329). Mask R-CNN. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"103517","DOI":"10.1016\/j.autcon.2020.103517","article-title":"Roles of artificial intelligence in construction engineering and management: A critical review and future trends","volume":"122","author":"Pan","year":"2021","journal-title":"Autom. Constr."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1111\/mice.12579","article-title":"Detecting safety helmet wearing on construction sites with bounding-box regression and deep transfer learning","volume":"36","author":"Shen","year":"2021","journal-title":"Comput.-Aided Civ. Infrastruct. Eng."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"103602","DOI":"10.1016\/j.autcon.2021.103602","article-title":"A deep learning approach for real-time rebar counting on the construction site based on YOLOv3 detector","volume":"124","author":"Li","year":"2021","journal-title":"Autom. Constr."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"101672","DOI":"10.1016\/j.jobe.2020.101672","article-title":"Scene understanding in construction and buildings using image processing methods: A comprehensive review and a case study","volume":"33","author":"Arashpour","year":"2021","journal-title":"J. Build. Eng."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"103850","DOI":"10.1016\/j.autcon.2021.103850","article-title":"Artificial intelligence quality inspection of steel bars installation by integrating mask R-CNN and stereo vision","volume":"130","author":"Kardovskyi","year":"2021","journal-title":"Autom. Constr."},{"key":"ref_15","unstructured":"Redmon, J., and Farhadi, A. (2018). YOLOv3: An Incremental Improvement. arXiv, Available online: http:\/\/arxiv.org\/abs\/1804.02767."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"104327","DOI":"10.1016\/j.autcon.2022.104327","article-title":"Integrated vision-based automated progress monitoring of indoor construction using mask region-based convolutional neural networks and BIM","volume":"140","author":"Wei","year":"2022","journal-title":"Autom. Constr."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"106022","DOI":"10.1016\/j.resconrec.2021.106022","article-title":"Using computer vision to recognize composition of construction waste mixtures: A semantic segmentation approach","volume":"178","author":"Lu","year":"2022","journal-title":"Resour. Conserv. Recycl."},{"key":"ref_18","unstructured":"Chen, L.-C., Papandreou, G., Schroff, F., and Adam, H. (2017). Rethinking Atrous Convolution for Semantic Image Segmentation. arXiv, Available online: http:\/\/arxiv.org\/abs\/1706.05587."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"891","DOI":"10.1109\/LGRS.2020.2988326","article-title":"Building Area Estimation in Drone Aerial Images Based on Mask R-CNN","volume":"18","author":"Chen","year":"2021","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"103634","DOI":"10.1016\/j.autcon.2021.103634","article-title":"Attention-guided analysis of infrastructure damage with semi-supervised deep learning","volume":"125","author":"Karaaslan","year":"2021","journal-title":"Autom. Constr."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"104324","DOI":"10.1016\/j.autcon.2022.104324","article-title":"Detection of exposed steel rebars based on deep-learning techniques and unmanned aerial vehicles","volume":"139","author":"Santos","year":"2022","journal-title":"Autom. Constr."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Zhan, Y., Liu, W., and Maruyama, Y. (2022). Damaged Building Extraction Using Modified Mask R-CNN Model Using Post-Event Aerial Images of the 2016 Kumamoto Earthquake. Remote Sens., 14.","DOI":"10.3390\/rs14041002"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"103414","DOI":"10.1016\/j.autcon.2020.103414","article-title":"Improved Mask R-CNN with distance guided intersection over union for GPR signature detection and segmentation","volume":"121","author":"Hou","year":"2021","journal-title":"Autom. Constr."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"3424","DOI":"10.1177\/1475921721989407","article-title":"Steel bridge corrosion inspection with combined vision and thermographic images","volume":"20","author":"Hwang","year":"2021","journal-title":"Struct. Health Monit."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Munawar, H.S., Ullah, F., Shahzad, D., Heravi, A., Qayyum, S., and Akram, J. (2022). Civil Infrastructure Damage and Corrosion Detection: An Application of Machine Learning. Buildings, 12.","DOI":"10.3390\/buildings12020156"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1375","DOI":"10.1007\/s13349-021-00515-7","article-title":"Recognition and location of steel structure surface corrosion based on unmanned aerial vehicle images","volume":"11","author":"Han","year":"2021","journal-title":"J. Civ. Struct. Health Monit."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1108\/SSMT-04-2021-0013","article-title":"Detection of solder paste defects with an optimization-based deep learning model using image processing techniques","volume":"33","author":"Sezer","year":"2021","journal-title":"Solder. Surf. Mt. Technol."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Forkan, A.R.M., Kang, Y.-B., Jayaraman, P.P., Liao, K., Kaul, R., Morgan, G., Ranjan, R., and Sinha, S. (2021). CorrDetector: A Framework for Structural Corrosion Detection from Drone Images using Ensemble Deep Learning. arXiv, Available online: http:\/\/arxiv.org\/abs\/2102.04686.","DOI":"10.1016\/j.eswa.2021.116461"},{"key":"ref_29","unstructured":"Albanie, S., Varol, G., Momeni, L., Afouras, T., Brown, A., Zhang, C., Coto, E., Camgoz, N.C., Saunders, B., and Dutta, A. (2023, January 11). Signer Diarisation in the Wild. Available online: https:\/\/www.robots.ox.ac.uk\/~vgg\/research\/signer_diarisation\/."},{"key":"ref_30","unstructured":"Hiroto, H. (2022, November 04). Digging into Detectron 2\u2014Part 1. Available online: https:\/\/medium.com\/@hirotoschwert\/digging-into-detectron-2-47b2e794fabd."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2015). Deep Residual Learning for Image Recognition. arXiv, Available online: http:\/\/arxiv.org\/abs\/1512.03385.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015). Fast R-CNN. arXiv, Available online: http:\/\/arxiv.org\/abs\/1504.08083.","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017, January 21\u201326). Feature Pyramid Networks for Object Detection. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1186\/s40537-019-0197-0","article-title":"A survey on Image Data Augmentation for Deep Learning","volume":"6","author":"Shorten","year":"2019","journal-title":"J. Big Data"},{"key":"ref_35","unstructured":"Poole, B., Sohl-Dickstein, J., and Ganguli, S. (2014). Analyzing noise in autoencoders and deep networks. arXiv, Available online: http:\/\/arxiv.org\/abs\/1406.1831."},{"key":"ref_36","unstructured":"Clark, A. (2023, January 11). Pillow (PIL Fork) Documentation. Available online: https:\/\/buildmedia.readthedocs.org\/media\/pdf\/pillow\/latest\/pillow.pdf."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A Survey on Transfer Learning","volume":"22","author":"Pan","year":"2010","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_38","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Bourdev, L., Girshick, R., Hays, J., Perona, P., Ramanan, D., Zitnick, C.L., and Doll\u00e1r, P. (2015). Microsoft COCO: Common Objects in Context. arXiv, Available online: http:\/\/arxiv.org\/abs\/1405.0312."},{"key":"ref_39","unstructured":"Kingma, D.P., and Ba, J. (2017). Adam: A Method for Stochastic Optimization. arXiv, Available online: http:\/\/arxiv.org\/abs\/1412.6980."}],"container-title":["Applied Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2076-3417\/13\/3\/1386\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:11:55Z","timestamp":1760119915000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2076-3417\/13\/3\/1386"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,20]]},"references-count":39,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2023,2]]}},"alternative-id":["app13031386"],"URL":"https:\/\/doi.org\/10.3390\/app13031386","relation":{},"ISSN":["2076-3417"],"issn-type":[{"value":"2076-3417","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,20]]}}}