{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T23:04:40Z","timestamp":1781737480747,"version":"3.54.5"},"reference-count":48,"publisher":"MDPI AG","issue":"21","license":[{"start":{"date-parts":[[2020,10,31]],"date-time":"2020-10-31T00:00:00Z","timestamp":1604102400000},"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 installation of solar plants everywhere in the world increases year by year. Automated diagnostic methods are needed to inspect the solar plants and to identify anomalies within these photovoltaic panels. The inspection is usually carried out by unmanned aerial vehicles (UAVs) using thermal imaging sensors. The first step in the whole process is to detect the solar panels in those images. However, standard image processing techniques fail in case of low-contrast images or images with complex backgrounds. Moreover, the shades of power lines or structures similar to solar panels impede the automated detection process. In this research, two self-developed methods are compared for the detection of panels in this context, one based on classical techniques and another one based on deep learning, both with a common post-processing step. The first method is based on edge detection and classification, in contrast to the second method is based on training a region based convolutional neural networks to identify a panel. The first method corrects for the low contrast of the thermal image using several preprocessing techniques. Subsequently, edge detection, segmentation and segment classification are applied. The latter is done using a support vector machine trained with an optimized texture descriptor vector. The second method is based on deep learning trained with images that have been subjected to three different pre-processing operations. The postprocessing use the detected panels to infer the location of panels that were not detected. This step selects contours from detected panels based on the panel area and the angle of rotation. Then new panels are determined by the extrapolation of these contours. The panels in 100 random images taken from eleven UAV flights over three solar plants are labeled and used to evaluate the detection methods. The metrics for the new method based on classical techniques reaches a precision of 0.997, a recall of 0.970 and a F1 score of 0.983. The metrics for the method of deep learning reaches a precision of 0.996, a recall of 0.981 and a F1 score of 0.989. The two panel detection methods are highly effective in the presence of complex backgrounds.<\/jats:p>","DOI":"10.3390\/s20216219","type":"journal-article","created":{"date-parts":[[2020,10,31]],"date-time":"2020-10-31T21:39:56Z","timestamp":1604180396000},"page":"6219","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":64,"title":["Solar Panel Detection within Complex Backgrounds Using Thermal Images Acquired by UAVs"],"prefix":"10.3390","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2165-8536","authenticated-orcid":false,"given":"Jhon Jairo","family":"Vega D\u00edaz","sequence":"first","affiliation":[{"name":"Centro de Investigaci\u00f3n en Ciencias B\u00e1sicas y Aplicadas, Doctorado en Ciencia Aplicada, Universidad Antonio Nari\u00f1o (UAN), 110231 Bogot\u00e1, Colombia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3986-823X","authenticated-orcid":false,"given":"Michiel","family":"Vlaminck","sequence":"additional","affiliation":[{"name":"Telecommunications and Information Processing (TELIN), Ghent University, Imec, B-9000 Ghent, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dionysios","family":"Lefkaditis","sequence":"additional","affiliation":[{"name":"Sitemark, Gaston Geenslaan 11, 3001 Leuven , Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sergio Alejandro","family":"Orjuela Vargas","sequence":"additional","affiliation":[{"name":"Facultad de Ingenier\u00eda Mec\u00e1nica Electr\u00f3nica y Biomedica, Universidad Antonio Nari\u00f1o (UAN), 730001 Ibagu\u00e9, Tolima, Colombia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiep","family":"Luong","sequence":"additional","affiliation":[{"name":"Telecommunications and Information Processing (TELIN), Ghent University, Imec, B-9000 Ghent, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2020,10,31]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Busu, M. (2020). Analyzing the impact of the renewable energy sources on economic growth at the EU level using an ARDL model. Mathematics, 8.","DOI":"10.3390\/math8081367"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Zheng, Y., and Weng, Q. (2020). Modeling the effect of green roof systems and photovoltaic panels for building energy savings to mitigate climate change. Remote Sens., 12.","DOI":"10.3390\/rs12152402"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Javadi, M.S., Gough, M., Lotfi, M., Esmaeel Nezhad, A., Santos, S.F., and Catal\u00e3o, J.P.S. (2020). Optimal self-scheduling of home energy management system in the presence of photovoltaic power generation and batteries. Energy, 210.","DOI":"10.1016\/j.energy.2020.118568"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1007\/978-981-15-6259-4_87","article-title":"Management strategy of power exchange in a building between grid, photovoltaic and batteries","volume":"681","author":"Dhriyyef","year":"2020","journal-title":"Lect. Notes Electr. Eng."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.renene.2020.06.141","article-title":"Constructing statutory energy goal compliant wind and solar PV infrastructure pathways","volume":"161","author":"Thomas","year":"2020","journal-title":"Renew. Energy"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"132466","DOI":"10.1109\/ACCESS.2020.3010212","article-title":"A Review for Solar Panel Fire Accident Prevention in Large-Scale PV Applications","volume":"8","author":"Wu","year":"2020","journal-title":"IEEE Access"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1016\/j.enconman.2016.11.031","article-title":"A practical technique for on-line monitoring of a photovoltaic plant connected to a single-phase grid","volume":"132","author":"Yahyaoui","year":"2017","journal-title":"Energy Convers. Manag."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Ber\u00e1nek, V., Ol\u0161an, T., Libra, M., Poulek, V., Sedl\u00e1\u010dek, J., Dang, M.Q., and Tyukhov, I.I. (2018). New monitoring system for photovoltaic power plants\u2019 management. Energies, 11.","DOI":"10.3390\/en11102495"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"938","DOI":"10.4028\/www.scientific.net\/AMM.635-637.938","article-title":"Research on solar panels online defect detecting method","volume":"635-637","author":"Wang","year":"2014","journal-title":"Appl. Mech. Mater."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Haider, M., Doegar, A., and Verma, R.K. (2018, January 28\u201329). Fault identification in electrical equipment using thermal image processing. Proceedings of the 2018 International Conference on Computing, Power and Communication Technologies (GUCON), Greater Noida, India.","DOI":"10.1109\/GUCON.2018.8675108"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Phoolwani, U.K., Sharma, T., Singh, A., and Gawre, S.K. (2020, January 22\u201323). IoT Based Solar Panel Analysis using Thermal Imaging. Proceedings of the 2020 IEEE International Students\u2019 Conference on Electrical, Electronics and Computer Science (SCEECS), Bhopal, India.","DOI":"10.1109\/SCEECS48394.2020.114"},{"key":"ref_12","unstructured":"Chen, J., Lin, C., and Liu, C. (1978). The efficiency and performance detection algorithm and system development for photovoltaic system through use of thermal image processing technology. AIP Conf. Proc., 470088."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1007\/s13319-018-0186-7","article-title":"A Mamdani Fuzzy Logic System to Enhance Solar Cell Micro-Cracks Image Processing","volume":"9","author":"Chawla","year":"2018","journal-title":"3D Research"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Sulas-Kern, D.B., Johnston, S., and Meydbray, J. (2019, January 16\u201321). Fill Factor Loss in Fielded Photovoltaic Modules Due to Metallization Failures, Characterized by Luminescence and Thermal Imaging. Proceedings of the 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC), Chicago, IL, USA.","DOI":"10.1109\/PVSC40753.2019.8980840"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Alsafasfeh, M., Abdel-Qader, I., and Bazuin, B. (2017, January 17\u201318). Fault detection in photovoltaic system using SLIC and thermal images. Proceedings of the 22017 8th International Conference on Information Technology (ICIT), Amman, Jordan.","DOI":"10.1109\/ICITECH.2017.8079925"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Men\u00e9ndez, O., Guam\u00e1n, R., P\u00e9rez, M., and Cheein, F.A. (2018). Photovoltaic modules diagnosis using artificial vision techniques for artifact minimization. Energies, 11.","DOI":"10.3390\/en11071688"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1016\/j.infrared.2017.04.015","article-title":"Scheme for predictive fault diagnosis in photo-voltaic modules using thermal imaging","volume":"83","author":"Jaffery","year":"2017","journal-title":"Infrared Phys. Technol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"94760O","DOI":"10.1117\/12.2179792","article-title":"Automatic solar panel recognition and defect detection using infrared imaging","volume":"Volume 9476","author":"Gao","year":"2015","journal-title":"Automatic Target Recognition XXV"},{"key":"ref_19","first-page":"38","article-title":"Detecting Hot Spots in Photovoltaic Panels Using Low-Cost Thermal Cameras","volume":"1152","year":"2020","journal-title":"Commun. Comput. Inf. Sci."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Henry, C., Poudel, S., Lee, S.W., and Jeong, H. (2020). Automatic detection system of deteriorated PV modules using drone with thermal camera. Appl. Sci., 10.","DOI":"10.3390\/app10113802"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Lee, D., and Park, J. (2019). Development of Solar-Panel Monitoring Method Using Unmanned Aerial Vehicle and Thermal Infrared Sensor. IOP Conference Series: Materials Science and Engineering, IOP Publishing.","DOI":"10.1088\/1757-899X\/611\/1\/012085"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Lee, D.H., and Park, J.H. (2019). Developing inspection methodology of solar energy plants by thermal infrared sensor on board unmanned aerial vehicles. Energies, 12.","DOI":"10.3390\/en12152928"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Park, J., and Lee, D. (2019). Precise Inspection Method of Solar Photovoltaic Panel Using Optical and Thermal Infrared Sensor Image Taken by Drones. IOP Conference Series: Materials Science and Engineering, IOP Publishing.","DOI":"10.1088\/1757-899X\/611\/1\/012089"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Lee, S., An, K.E., Jeon, B.D., Cho, K.Y., Lee, S.J., and Seo, D. (2018, January 12\u201314). Detecting faulty solar panels based on thermal image processing. Proceedings of the 2018 IEEE International Conference on Consumer Electronics (ICCE), Las Vegas, NV, USA.","DOI":"10.1109\/ICCE.2018.8326228"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"L\u00f3pez-Fern\u00e1ndez, L., Lag\u00fcela, S., Fern\u00e1ndez, J., and Gonz\u00e1lez-Aguilera, D. (2017). Automatic evaluation of photovoltaic power stations from high-density RGB-T 3D point clouds. Remote Sens., 9.","DOI":"10.3390\/rs9060631"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Alsafasfeh, M., Abdel-Qader, I., Bazuin, B., Alsafasfeh, Q., and Su, W. (2018). Unsupervised fault detection and analysis for large photovoltaic systems using drones and machine vision. Energies, 11.","DOI":"10.3390\/en11092252"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Ismail, H., Chikte, R., Bandyopadhyay, A., and Al Jasmi, N. (2019, January 11\u201314). Autonomous detection of PV panels using a drone. Proceedings of the ASME International Mechanical Engineering Congress and Exposition, Salt Lake City, UT, USA.","DOI":"10.1115\/IMECE2019-12080"},{"key":"ref_28","first-page":"1","article-title":"Segmentation of Thermography Image of Solar Cells and Panels","volume":"1152","year":"2020","journal-title":"Commun. Comput. Inf. Sci."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Greco, A., Pironti, C., Saggese, A., Vento, M., and Vigilante, V. (2020, January 7\u20139). A deep learning based approach for detecting panels in photovoltaic plants. Proceedings of the ACM International Conference Proceeding Series, Las Palmas de Gran Canaria, Spain.","DOI":"10.1145\/3378184.3378185"},{"key":"ref_30","first-page":"107","article-title":"Deep learning algorithm for the segmentation of the interested region of an infrared thermal image","volume":"46","author":"Zhu","year":"2019","journal-title":"J. Xidian Univ."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Liao, K.C., and Lu, J.H. (2020). Using Matlab real-time image analysis for solar panel fault detection with UAV. Journal of Physics: Conference Series, IOP Publishing Ltd.","DOI":"10.1088\/1742-6596\/1509\/1\/012010"},{"key":"ref_32","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 4th IEEE International Workshop on Metrology for AeroSpace (MetroAeroSpace), Padua, Italy.","DOI":"10.1109\/MetroAeroSpace.2017.7999594"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Uma, J., Muniraj, C., and Sathya, N. (2019). Diagnosis of photovoltaic (PV) panel defects based on testing and evaluation of thermal image. J. Test. Eval., 47.","DOI":"10.1520\/JTE20170653"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Dhimish, M., and Alrashidi, A. (2020). Photovoltaic degradation rate affected by different weather conditions: A case study based on pv systems in the uk and australia. Electronics, 9.","DOI":"10.3390\/electronics9040650"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Libra, M., Dane\u010dek, M., Le\u0161etick\u00fd, J., Poulek, V., Sedl\u00e1\u010dek, J., and Ber\u00e1nek, V. (2019). Monitoring of defects of a photovoltaic power plant using a drone. Energies, 12.","DOI":"10.3390\/en12050795"},{"key":"ref_36","unstructured":"Dji (2020, September 20). Zenmuse XT Specs. Available online: https:\/\/www.dji.com\/zenmuse-xt\/specs."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","article-title":"Array programming with NumPy","volume":"585","author":"Harris","year":"2020","journal-title":"Nature"},{"key":"ref_38","unstructured":"Garrido, G., and Joshi, P. (2018). OpenCV 3.x with Python By Example\u2014Second Edition: Make the Most of OpenCV and Python to Build Applications for Object Recognition and Augmented Reality, Packt Publishing. [2nd ed.]."},{"key":"ref_39","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"e104","DOI":"10.1158\/0008-5472.CAN-17-0339","article-title":"Computational radiomics system to decode the radiographic phenotype","volume":"77","author":"Fedorov","year":"2017","journal-title":"Cancer Res."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1007\/978-3-030-40124-5_5","article-title":"Curadiomics: A GPU-based radiomics feature extraction toolkit","volume":"11991","author":"Jiao","year":"2020","journal-title":"Lect. Notes Comput. Sci."},{"key":"ref_42","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., and Girshick, R. (2020, September 20). Detectron2. Available online: https:\/\/github.com\/facebookresearch\/detectron2."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"44","DOI":"10.3389\/fninf.2014.00044","article-title":"The Insight ToolKit image registration framework","volume":"8","author":"Avants","year":"2014","journal-title":"Front. Neuroinform."},{"key":"ref_44","unstructured":"Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., and Dubourg, V. (2020, September 20). Sckit Learn. 1.5. Stochastic Gradient Descent., Available online: https:\/\/scikit-learn.org\/stable\/modules\/sgd.html."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"657","DOI":"10.1007\/978-981-13-9042-5_56","article-title":"Deep Learning Techniques\u2014R-CNN to Mask R-CNN: A Survey","volume":"999","author":"Bharati","year":"2020","journal-title":"Computational Intelligence in Pattern Recognition"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"e1318","DOI":"10.1002\/widm.1318","article-title":"Benchmarking in classification and regression","volume":"9","author":"Hoffmann","year":"2019","journal-title":"Wiley Interdiscip. Rev. Data Min. Knowl. Discov."},{"key":"ref_47","unstructured":"Tharwat, A. (2018). Classification assessment methods. Appl. Comput. Inform."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Chicco, D., and Jurman, G. (2020). The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genom., 21.","DOI":"10.1186\/s12864-019-6413-7"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/21\/6219\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:27:26Z","timestamp":1760178446000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/21\/6219"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,31]]},"references-count":48,"journal-issue":{"issue":"21","published-online":{"date-parts":[[2020,11]]}},"alternative-id":["s20216219"],"URL":"https:\/\/doi.org\/10.3390\/s20216219","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10,31]]}}}