{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T15:51:37Z","timestamp":1778255497283,"version":"3.51.4"},"reference-count":33,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2022,6,21]],"date-time":"2022-06-21T00:00:00Z","timestamp":1655769600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"British Engineering and Physics Sciences Research Council"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Aircraft maintenance plays a key role in the safety of air transport. One of its most significant procedures is the visual inspection of the aircraft skin for defects. This is mainly carried out manually and involves a high skilled human walking around the aircraft. It is very time consuming, costly, stressful and the outcome heavily depends on the skills of the inspector. In this paper, we propose a two-step process for automating the defect recognition and classification from visual images. The visual inspection can be carried out with the use of an unmanned aerial vehicle (UAV) carrying an image sensor to fully automate the procedure and eliminate any human error. With our proposed method in the first step, we perform the crucial part of recognizing the defect. If a defect is found, the image is fed to an ensemble of classifiers for identifying the type. The classifiers are a combination of different pretrained convolution neural network (CNN) models, which we retrained to fit our problem. For achieving our goal, we created our own dataset with defect images captured from aircrafts during inspection in TUI\u2019s maintenance hangar. The images were preprocessed and used to train different pretrained CNNs with the use of transfer learning. We performed an initial training of 40 different CNN architectures to choose the ones that best fitted our dataset. Then, we chose the best four for fine tuning and further testing. For the first step of defect recognition, the DenseNet201 CNN architecture performed better, with an overall accuracy of 81.82%. For the second step for the defect classification, an ensemble of different CNN models was used. The results show that even with a very small dataset, we can reach an accuracy of around 82% in the defect recognition and even 100% for the classification of the categories of missing or damaged exterior paint and primer and dents.<\/jats:p>","DOI":"10.3390\/s22134682","type":"journal-article","created":{"date-parts":[[2022,6,22]],"date-time":"2022-06-22T04:12:01Z","timestamp":1655871121000},"page":"4682","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":32,"title":["Defects Recognition Algorithm Development from Visual UAV Inspections"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1314-0603","authenticated-orcid":false,"given":"Nicolas P.","family":"Avdelidis","sequence":"first","affiliation":[{"name":"School of Aerospace, Transport & Manufacturing, Cranfield University, Cranfield MK43 0AL, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3966-7633","authenticated-orcid":false,"given":"Antonios","family":"Tsourdos","sequence":"additional","affiliation":[{"name":"School of Aerospace, Transport & Manufacturing, Cranfield University, Cranfield MK43 0AL, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3396-5744","authenticated-orcid":false,"given":"Pasquale","family":"Lafiosca","sequence":"additional","affiliation":[{"name":"School of Aerospace, Transport & Manufacturing, Cranfield University, Cranfield MK43 0AL, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Richard","family":"Plaster","sequence":"additional","affiliation":[{"name":"ADDIT, 17 Railton Road, Wolseley Business Park, Kempston, Bedford MK42 7PN, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anna","family":"Plaster","sequence":"additional","affiliation":[{"name":"ADDIT, 17 Railton Road, Wolseley Business Park, Kempston, Bedford MK42 7PN, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark","family":"Droznika","sequence":"additional","affiliation":[{"name":"TUI Airline, Area 8, Hangar 61, Percival Way, London Luton Airport, Luton LU2 9PA, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,6,21]]},"reference":[{"key":"ref_1","unstructured":"(2022, April 11). The EU in the World, Eurostat 2020 Edition. Available online: https:\/\/ec.europa.eu\/eurostat\/web\/products-statistical-books\/-\/ks-ex-20-001."},{"key":"ref_2","unstructured":"(2022, April 11). The EU in the World, Eurostat 2021 Edition. Available online: https:\/\/ec.europa.eu\/eurostat\/web\/products-statistical-books\/-\/ks-ei-21-001."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Sprong, J., Jiang, X., and Polinder, H. (2019, January 21\u201326). Deployment of Prognostics to Optimize Aircraft Maintenance\u2014A Literature Review: A Literature Review. Proceedings of the Annual Conference of the PHM Society, Scottsdale, AZ, USA.","DOI":"10.36001\/phmconf.2019.v11i1.776"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Gunatilake, P., Siegel, M., Jordan, A.G., and Podnar, G.W. (1996). Image enhancement and understanding for remote visual inspection of aircraft surface. Nondestructive Evaluation of Aging Aircraft, Airports, and Aerospace Hardware, SPIE.","DOI":"10.1117\/12.259117"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"61110","DOI":"10.1117\/1.JEI.24.6.061110","article-title":"Automated exterior inspection of an aircraft with a pan-tilt-zoom camera mounted on a mobile robot","volume":"24","author":"Larnier","year":"2015","journal-title":"J. Electron. Imaging"},{"key":"ref_6","first-page":"2","article-title":"Image understanding algorithms for remote visual inspection of aircraft surfaces","volume":"Volume 3029","author":"Gunatilake","year":"1997","journal-title":"Machine Vision Applications in Industrial Inspection V"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"633","DOI":"10.1007\/s12541-010-0075-3","article-title":"A survey of climbing robots: Locomotion and adhesion","volume":"11","author":"Chu","year":"2010","journal-title":"Int. J. Precis. Eng. Manuf."},{"key":"ref_8","unstructured":"Zhiwei, X., Muhua, C., and Qingji, G. (2009). The structure and defects recognition algorithm of an aircraft surface defects inspection robot. 2009 International Conference on Information and Automation, Zhuhai, China, 22\u201325 June 2009, IEEE."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1109\/MRA.2002.1160067","article-title":"Climbing the walls [robots]","volume":"9","author":"Mukherjee","year":"2002","journal-title":"IEEE Robot. Autom. Mag."},{"key":"ref_10","unstructured":"A. F. R. Laboratory (2022, April 11). Robotic arm tool poised to save costly inspection time. Int. J. Precis. Eng. Manuf., Available online: https:\/\/www.afspc.af.mil\/News\/Article-Display\/Article\/1088209\/robotic-arm-tool-poised-to-save-costly-inspection-time\/."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Nansai, S., and Mohan, R.E. (2016). A survey of wall climbing robots: Recent advances and challenges. Robotics, 5.","DOI":"10.3390\/robotics5030014"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Addabbo, P., Angrisano, A., Bernardi, M.L., Gagliarde, G., Mennella, A., Nisi, M., and Ullo, S. (2017, January 21\u201323). A UAV infrared measurement approach for defect detection in photovoltaic plants. Proceedings of the 2017 IEEE International Workshop on Metrology for AeroSpace (MetroAeroSpace), Padua, Italy.","DOI":"10.1109\/MetroAeroSpace.2017.7999594"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"320","DOI":"10.1016\/j.ifacol.2016.09.055","article-title":"Design and Development of a Novel Spherical UAV","volume":"49","author":"Malandrakis","year":"2016","journal-title":"IFAC-PapersOnLine"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1260\/1369-4332.17.3.289","article-title":"Quality Assessment of Unmanned Aerial Vehicle (UAV) Based Visual Inspection of Structures","volume":"17","author":"Morgenthal","year":"2014","journal-title":"Adv. Struct. Eng."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Malandrakis, K., Savvaris, A., Domingo, J.A.G., Avdelidis, N., Tsilivis, P., Plumacker, F., Zanotti Fragonara, L., and Tsourdos, A. (2018, January 20\u201322). Inspection of Aircraft Wing Panels Using Unmanned Aerial Vehicles. Proceedings of the 2018 5th IEEE International Workshop on Metrology for AeroSpace (MetroAeroSpace), Rome, Italy.","DOI":"10.1109\/MetroAeroSpace.2018.8453598"},{"key":"ref_16","first-page":"38","article-title":"Computer aided visual inspection of aircraft surfaces","volume":"6","author":"Mumtaz","year":"2012","journal-title":"Int. J. Image Processing"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Ortiz, A., Bonnin-Pascual, F., Garcia-Fidalgo, E., and Company-Corcoles, J. (2016). Vision-based corrosion detection assisted by a micro-aerial vehicle in a vessel inspection application. Sensors, 16.","DOI":"10.3390\/s16122118"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Tzitzilonis, V., Malandrakis, K., Zanotti Fragonara, L., Gonzalez Domingo, J.A., Avdelidis, N.P., Tsourdos, A., and Forster, K. (2019). Inspection of Aircraft Wing Panels Using Unmanned Aerial Vehicles. Sensors, 19.","DOI":"10.3390\/s19081824"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Li, Y., Huang, H., Xie, Q., Yao, L., and Chen, Q. (2018). Research on a surface defect detection algorithm based on MobileNet-SSD. Appl. Sci., 8.","DOI":"10.3390\/app8091678"},{"key":"ref_20","unstructured":"Malekzadeh, T., Abdollahzadeh, M., Nejati, H., and Cheung, N.-M. (2017). Aircraft fuselage defect detection using deep neural networks. arXiv."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Tao, X., Zhang, D., Ma, W., Liu, X., and Xu, D. (2018). Automatic metallic surface defect detection and recognition with convolutional neural networks. Appl. Sci., 8.","DOI":"10.3390\/app8091575"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"731","DOI":"10.1111\/mice.12334","article-title":"Autonomous structural visual inspection using region-based deep learning for detecting multiple damage types","volume":"33","author":"Cha","year":"2018","journal-title":"Comput. Aided Civ. Infrastruct. Eng."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Kim, B., and Cho, S. (2018). Automated Vision-Based Detection of Cracks on Concrete Surfaces Using a Deep Learning Technique. Sensors, 18.","DOI":"10.3390\/s18103452"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"6357185","DOI":"10.1155\/2018\/6357185","article-title":"Astronaut visual tracking of flying assistant robot in space station based on deep learning and probabilistic model","volume":"2018","author":"Zhang","year":"2018","journal-title":"Int. J. Aerosp. Eng."},{"key":"ref_25","first-page":"71","article-title":"Vision-based concrete crack detection using a convolutional neural network","volume":"Volume 2","author":"Caicedo","year":"2017","journal-title":"Dynamics of Civil Structures"},{"key":"ref_26","unstructured":"Kang, D., and Cha, Y.-J. (2018). Damage detection with an autonomous UAV using deep learning. Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2018, SPIE."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"885","DOI":"10.1111\/mice.12375","article-title":"Autonomous UAVs for structural health monitoring using deep learning and an ultrasonic beacon system with geo-tagging","volume":"33","author":"Kang","year":"2018","journal-title":"Comput. Aided Civ. Infrastruct. Eng."},{"key":"ref_28","unstructured":"(2022, April 11). TUI\u00a9. Available online: https:\/\/www.tuigroup.com\/en-en."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009, January 20\u201325). ImageNet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Tan, C., Sun, F., Kong, T., Zhang, W., Yang, C., and Liu, C. (2018). A Survey on Deep Transfer Learning. The 27th International Conference on Artificial Neural Networks (ICANN 2018), Rhodes, Greece, 4\u20137 October 2018, Springer.","DOI":"10.1007\/978-3-030-01424-7_27"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1016\/j.patcog.2016.07.001","article-title":"Towards better exploiting convolutional neural networks for remote sensing scene classification","volume":"61","author":"Keiller","year":"2017","journal-title":"Pattern Recognit."},{"key":"ref_32","unstructured":"Abadi, M. (2022, April 14). TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. Available online: https:\/\/www.tensorflow.org."},{"key":"ref_33","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/13\/4682\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:36:49Z","timestamp":1760139409000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/13\/4682"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,21]]},"references-count":33,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2022,7]]}},"alternative-id":["s22134682"],"URL":"https:\/\/doi.org\/10.3390\/s22134682","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6,21]]}}}