{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T08:18:27Z","timestamp":1769156307936,"version":"3.49.0"},"reference-count":24,"publisher":"MDPI AG","issue":"23","license":[{"start":{"date-parts":[[2021,11,26]],"date-time":"2021-11-26T00:00:00Z","timestamp":1637884800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Deep learning (DL)\u2014in particular convolutional neural networks (CNN)\u2014methods are widely spread in object detection and recognition of remote sensing images. In the domain of DL, there is a need for large numbers of training samples. These samples are mostly generated based on manual identification. Identifying and labelling these objects is very time-consuming. The developed approach proposes a partially automated procedure for the sample creation and avoids manual labelling of rooftop photovoltaic (PV) systems. By combining address data of existing rooftop PV systems from the German Plant Register, the Georeferenced Address Data and the Official House Surroundings Germany, a partially automated generation of training samples is achieved. Using a selection of 100,000 automatically generated samples, a network using a RetinaNet-based architecture combining ResNet101, a feature pyramid network, a classification and a regression network is trained, applied on a large area and post-filtered by intersection with additional automatically identified locations of existing rooftop PV systems. Based on a proof-of-concept application, a second network is trained with the filtered selection of approximately 51,000 training samples. In two independent test applications using high-resolution aerial images of Saarland in Germany, buildings with PV systems are detected with a precision of at least 92.77 and a recall of 84.47.<\/jats:p>","DOI":"10.3390\/rs13234793","type":"journal-article","created":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T01:45:02Z","timestamp":1638323102000},"page":"4793","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Semi-Automatic Generation of Training Samples for Detecting Renewable Energy Plants in High-Resolution Aerial Images"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5947-3473","authenticated-orcid":false,"given":"Maximilian","family":"Kleebauer","sequence":"first","affiliation":[{"name":"Energy Meteorology and Geo Information System, Fraunhofer Institute for Energy Economics and Energy System Technology, 34119 Kassel, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4181-759X","authenticated-orcid":false,"given":"Daniel","family":"Horst","sequence":"additional","affiliation":[{"name":"Energy Meteorology and Geo Information System, Fraunhofer Institute for Energy Economics and Energy System Technology, 34119 Kassel, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7476-3663","authenticated-orcid":false,"given":"Christoph","family":"Reudenbach","sequence":"additional","affiliation":[{"name":"Environmental Informatics, Faculty of Geography, Philipps-University Marburg, 35037 Marburg, Germany"}]}],"member":"1968","published-online":{"date-parts":[[2021,11,26]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Malof, J.M., Hou, R., Collins, L.M., Bradbury, K., and Newell, R. (2015, January 22\u201325). Automatic solar photovoltaic panel detection in satellite imagery. Proceedings of the 2015 International Conference on Renewable Energy Research and Applications (ICRERA), Palermo, Italy.","DOI":"10.1109\/ICRERA.2015.7418643"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Malof, J.M., Collins, L.M., Bradbury, K., and Newell, R.G. (2016, January 20\u201323). A deep convolutional neural network and a random forest classifier for solar photovoltaic array detection in aerial imagery. Proceedings of the 2016 IEEE International Conference on Renewable Energy Research and Applications (ICRERA), Birmingham, UK.","DOI":"10.1109\/ICRERA.2016.7884415"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Malof, J.M., Collins, L.M., and Bradbury, K. (2017, January 23\u201328). A deep convolutional neural network, with pre-training, for solar photovoltaic array detection in aerial imagery. Proceedings of the 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Fort Worth, TX, USA.","DOI":"10.1109\/IGARSS.2017.8127092"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Yuan, J., Yang, H.L., Omitaomu, O.A., and Bhaduri, B.L. (2016, January 5\u20138). Large-scale solar panel mapping from aerial images using deep convolutional networks. Proceedings of the 2016 IEEE International Conference on Big Data (Big Data), Washington, DC, USA.","DOI":"10.1109\/BigData.2016.7840915"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2605","DOI":"10.1016\/j.joule.2018.11.021","article-title":"DeepSolar: A Machine Learning Framework to Efficiently Construct a Solar Deployment Database in the United States","volume":"2","author":"Yu","year":"2018","journal-title":"Joule"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Mayer, K., Wang, Z., Arlt, M.-L., Neumann, D., and Rajagopal, R. (2020, January 7\u20139). DeepSolar for Germany: A deep learning framework for PV system mapping from aerial imagery. Proceedings of the 2020 International Conference on Smart Energy Systems and Technologies (SEST), Istanbul, Turkey.","DOI":"10.1109\/SEST48500.2020.9203258"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Zech, M., and Ranalli, J. (August, January 15). Predicting PV Areas in Aerial Images with Deep Learning. Proceedings of the 2020 47th IEEE Photovoltaic Specialists Conference (PVSC), Calgary, AB, Canada.","DOI":"10.1109\/PVSC45281.2020.9300636"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1109\/JSTSP.2011.2139193","article-title":"A Survey of Active Learning Algorithms for Supervised Remote Sensing Image Classification","volume":"5","author":"Tuia","year":"2011","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1007\/s11263-019-01247-4","article-title":"Deep Learning for Generic Object Detection: A Survey","volume":"128","author":"Liu","year":"2020","journal-title":"Int. J. Comput. Vis."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"16024","DOI":"10.3390\/rs71215819","article-title":"Automatic Labelling and Selection of Training Samples for High-Resolution Remote Sensing Image Classification over Urban Areas","volume":"7","author":"Huang","year":"2015","journal-title":"Remote Sens."},{"key":"ref_11","unstructured":"(2021, November 24). GeoBasis-DE\/BKG, Deutsche Post Direkt GmbH, Statistisches Bundesamt, Wiesbaden. Georeferenzierte Adressdaten\u2014GA. Available online: https:\/\/gdz.bkg.bund.de\/index.php\/default\/georeferenzierte-adressdaten-ga.html."},{"key":"ref_12","unstructured":"(2021, November 24). GeoBasis-DE \/ BKG. Hausumringe Deutschland: HU-DE. Available online: https:\/\/gdz.bkg.bund.de\/index.php\/default\/amtliche-hausumringe-deutschland-hu-de.html."},{"key":"ref_13","unstructured":"(2021, November 24). GeoBasis-DE \/ BKG. Digitale Orthophotos Bodenaufl\u00f6sung 20 cm (DOP20). Available online: https:\/\/gdz.bkg.bund.de\/index.php\/default\/digitale-orthophotos-bodenauflosung-20-cm-dop20.html."},{"key":"ref_14","first-page":"707","article-title":"Binary Codes Capable of Correcting Deletions, Insertions and Reversals","volume":"10","author":"Levenshtein","year":"1966","journal-title":"Sov. Phys. Dokl."},{"key":"ref_15","first-page":"218","article-title":"String matching algorithms and their applicability in various applications","volume":"1","author":"Singla","year":"2012","journal-title":"Int. J. Soft Comput. Eng."},{"key":"ref_16","first-page":"127","article-title":"Adaptating the levenshtein distance to contextual spelling correction","volume":"12","author":"Lhoussain","year":"2015","journal-title":"Int. J. Comput. Sci. Appl."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., and Dollar, P. (2017, January 22\u201329). Focal Loss for Dense Object Detection. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_19","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_20","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015, January 7\u201313). Fast R-CNN. Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile.","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref_21","unstructured":"Gaiser, H., de Vries, M., Lacatusu, V., Williamson, A., Liscio, E., Henon, Y., Gratie, C., Morariu, M., Ye, C., and Zlocha, M. (2019). Fizyr\/Keras-Retinanet 0.5.1."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Wolf, S., Sommer, L., and Schumann, A. (2021). FastAER Det: Fast Aerial Embedded Real-Time Detection. Remote Sens., 13.","DOI":"10.3390\/rs13163088"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Xiao, Z., Wang, K., Wan, Q., Tan, X., Xu, C., and Xia, F. (2021). A2S-Det: Efficiency Anchor Matching in Aerial Image Oriented Object Detection. Remote Sens., 13.","DOI":"10.3390\/rs13010073"},{"key":"ref_24","unstructured":"(2021, November 24). ZFTurbo. GitHub\u2014ZFTurbo\/Keras-RetinaNet-for-Open-Images-Challenge-2018: Code for 15th place in Kaggle Google AI Open Images\u2014Object Detection Track. Available online: https:\/\/github.com\/ZFTurbo\/Keras-RetinaNet-for-Open-Images-Challenge-2018."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/23\/4793\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:36:08Z","timestamp":1760168168000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/23\/4793"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,26]]},"references-count":24,"journal-issue":{"issue":"23","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["rs13234793"],"URL":"https:\/\/doi.org\/10.3390\/rs13234793","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,26]]}}}