{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T05:13:01Z","timestamp":1781932381961,"version":"3.54.5"},"reference-count":47,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2018,11,15]],"date-time":"2018-11-15T00:00:00Z","timestamp":1542240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100012627","name":"NASA Astrobiology Institute","doi-asserted-by":"publisher","award":["NNX11AO78A a"],"award-info":[{"award-number":["NNX11AO78A a"]}],"id":[{"id":"10.13039\/100012627","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["NS 1329702."],"award-info":[{"award-number":["NS 1329702."]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Geographic information systems (GIS) provide accurate maps of terrain, roads, waterways, and building footprints and heights. Aircraft, particularly small unmanned aircraft systems (UAS), can exploit this and additional information such as building roof structure to improve navigation accuracy and safely perform contingency landings particularly in urban regions. However, building roof structure is not fully provided in maps. This paper proposes a method to automatically label building roof shape from publicly available GIS data. Satellite imagery and airborne LiDAR data are processed and manually labeled to create a diverse annotated roof image dataset for small to large urban cities. Multiple convolutional neural network (CNN) architectures are trained and tested, with the best performing networks providing a condensed feature set for support vector machine and decision tree classifiers. Satellite image and LiDAR data fusion is shown to provide greater classification accuracy than using either data type alone. Model confidence thresholds are adjusted leading to significant increases in models precision. Networks trained from roof data in Witten, Germany and Manhattan (New York City) are evaluated on independent data from these cities and Ann Arbor, Michigan.<\/jats:p>","DOI":"10.3390\/s18113960","type":"journal-article","created":{"date-parts":[[2018,11,15]],"date-time":"2018-11-15T11:32:47Z","timestamp":1542281567000},"page":"3960","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":56,"title":["Roof Shape Classification from LiDAR and Satellite Image Data Fusion Using Supervised Learning"],"prefix":"10.3390","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5458-9787","authenticated-orcid":false,"given":"Jeremy","family":"Castagno","sequence":"first","affiliation":[{"name":"Robotics Program, University of Michigan, Ann Arbor, MI 48109, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2132-6256","authenticated-orcid":false,"given":"Ella","family":"Atkins","sequence":"additional","affiliation":[{"name":"Robotics Program, University of Michigan, Ann Arbor, MI 48109, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2018,11,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Ochoa, C.A., and Atkins, E.M. (2017, January 9\u201313). Fail-Safe Navigation for Autonomous Urban Multicopter Flight. Proceedings of the AIAA Information Systems-AIAA Infotech @ Aerospace, Grapevine, TX, USA.","DOI":"10.2514\/6.2017-0222"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Castagno, J., Ochoa, C., and Atkins, E. (2018, January 12\u201315). Comprehensive Risk-based Planning for Small Unmanned Aircraft System Rooftop Landing. Proceedings of the 2018 International Conference on Unmanned Aircraft Systems (ICUAS), Dallas, TX, USA.","DOI":"10.1109\/ICUAS.2018.8453483"},{"key":"ref_3","unstructured":"OpenStreetMap Contributors (2018, July 01). Planet Dump. Available online: https:\/\/www.openstreetmap.org."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Castagno, J., and Atkins, E.M. (2018, January 25\u201329). Automatic Classification of Roof Shapes for Multicopter Emergency Landing Site Selection. Proceedings of the 2018 Aviation Technology, Integration, and Operations Conference, Atlanta, GA, USA.","DOI":"10.2514\/6.2018-3977"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"7393","DOI":"10.1109\/TGRS.2014.2311991","article-title":"Seamless fusion of LiDAR and aerial imagery for building extraction","volume":"52","author":"Zhou","year":"2014","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"570","DOI":"10.1016\/j.isprsjprs.2010.09.006","article-title":"An update on automatic 3D building reconstruction","volume":"65","author":"Haala","year":"2010","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"5241","DOI":"10.3390\/s90705241","article-title":"Automatic Roof Plane Detection and Analysis in Airborne Lidar Point Clouds for Solar Potential Assessment","volume":"9","author":"Jochem","year":"2009","journal-title":"Sensors"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Yan, Y., Su, N., Zhao, C., and Wang, L. (2017). A Dynamic Multi-Projection-Contour Approximating Framework for the 3D Reconstruction of Buildings by Super-Generalized Optical Stereo-Pairs. Sensors, 17.","DOI":"10.3390\/s17092153"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Malihi, S., Valadan Zoej, M.J., Hahn, M., Mokhtarzade, M., and Arefi, H. (2016). 3D Building Reconstruction Using Dense Photogrammetric Point Cloud. ISPRS Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci., 71\u201374.","DOI":"10.5194\/isprsarchives-XLI-B3-71-2016"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"25","DOI":"10.5194\/isprs-annals-IV-2-W3-25-2017","article-title":"Photogrammetric 3D Building Reconstruction from Thermal Images","volume":"IV-2\/W3","author":"Maset","year":"2017","journal-title":"ISPRS Ann. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Yan, Y., Gao, F., Deng, S., and Su, N. (2017). A Hierarchical Building Segmentation in Digital Surface Models for 3D Reconstruction. Sensors, 17.","DOI":"10.3390\/s17020222"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.renene.2017.12.096","article-title":"A city-scale roof shape classification using machine learning for solar energy applications","volume":"121","author":"Mohajeri","year":"2018","journal-title":"Renew. Energy"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Assouline, D., Mohajeri, N., and Scartezzini, J.L. (2017). Building rooftop classification using random forests for large-scale PV deployment. Proc. SPIE, 10428.","DOI":"10.1117\/12.2277692"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","article-title":"Deep learning in neural networks: An overview","volume":"61","author":"Schmidhuber","year":"2015","journal-title":"Neural Netw."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"833","DOI":"10.5194\/isprs-archives-XLI-B3-833-2016","article-title":"Knowledge based 3D building model recognition using convolutional neural networks from lidar and aerial imageries","volume":"XLI-B3","author":"Alidoost","year":"2016","journal-title":"Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"653","DOI":"10.5194\/isprs-archives-XLII-1-W1-653-2017","article-title":"Roof Type Selection based on patch-based classsification using deep learning for high Resolution Satellite Imagery","volume":"42","author":"Partovi","year":"2017","journal-title":"Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci.-ISPRS Arch."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet Large Scale Visual Recognition Challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1186\/s40537-016-0043-6","article-title":"A survey of transfer learning","volume":"3","author":"Weiss","year":"2016","journal-title":"J. Big Data"},{"key":"ref_19","unstructured":"Tang, Y. (2013). Deep Learning using Support Vector Machines. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"202","DOI":"10.1016\/j.isprsjprs.2003.09.006","article-title":"Reconstruction of 3D building models from aerial images and maps","volume":"58","author":"Suveg","year":"2004","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_21","first-page":"W24","article-title":"Automatic building reconstruction from cadastral maps and aerial images","volume":"36","author":"Taillandier","year":"2005","journal-title":"Int. Arch. Photogramm. Remote Sens."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1016\/j.isprsjprs.2011.10.003","article-title":"3D building reconstruction based on given ground plan information and surface models extracted from spaceborne imagery","volume":"67","author":"Tack","year":"2012","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_23","unstructured":"PROJ Contributors (2018). PROJ Coordinate Transformation Software Library, Open Source Geospatial Foundation."},{"key":"ref_24","unstructured":"(2018, September 05). Laser (LAS) File Format Exchagne Activities. Available online: https:\/\/www.asprs.org\/divisions-committees\/lidar-division\/laser-las-file-format-exchange-activities."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1016\/j.cageo.2016.07.003","article-title":"Whitebox GAT: A case study in geomorphometric analysis","volume":"95","author":"Lindsay","year":"2016","journal-title":"Comput. Geosci."},{"key":"ref_26","unstructured":"Samosky, J.T. (1993). SectionView\u2014A System for Interactively Specifying and Visualizing Sections through Three-Dimensional Medical Image Data. [Ph.D. Thesis, Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science]."},{"key":"ref_27","unstructured":"Iglewicz, B., and Hoaglin, D. (1993). How to Detect and Handle Outliers, ASQC Quality Press. ASQC Basic References In Quality Control."},{"key":"ref_28","first-page":"320","article-title":"Algorithm AS 217: Computation of the dip statistic to test for unimodality","volume":"34","author":"Hartigan","year":"1985","journal-title":"J. R. Stat. Soc. Ser. C (Appl. Stat.)"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"83","DOI":"10.3758\/s13428-012-0225-x","article-title":"Assessing bimodality to detect the presence of a dual cognitive process","volume":"45","author":"Freeman","year":"2013","journal-title":"Behav. Res. Methods"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2015). Deep Residual Learning for Image Recognition. arXiv.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2015). Rethinking the Inception Architecture for Computer Vision. arXiv.","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., and Vanhoucke, V. (2016). Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning. arXiv.","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref_33","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A Method for Stochastic Optimization. arXiv."},{"key":"ref_34","unstructured":"Chollet, F. (2018, September 05). Keras. Available online: https:\/\/github.com\/fchollet\/keras."},{"key":"ref_35","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_36","unstructured":"Land NRW (2018, July 01). Witten County Portal. Data Was Retrieved through ArcGIS World Imagery. Available online: https:\/\/www.land.nrw\/de\/tags\/open-data."},{"key":"ref_37","unstructured":"Open NRW (2018, September 05). Open Geo Data. Available online: https:\/\/www.opengeodata.nrw.de\/produkte\/geobasis\/dom\/dom1l\/."},{"key":"ref_38","unstructured":"New York State (2018, July 01). 2016 Annual Lot New York County. Data Was retrieved through ArcGIS World Imagery, Available online: http:\/\/gis.ny.gov\/gateway\/orthoprogram\/lot16\/new-york.htm."},{"key":"ref_39","unstructured":"USGS (2018, September 05). LIDAR Point Cloud NY CMPG 2013, Available online: ftp:\/\/rockyftp.cr.usgs.gov\/vdelivery\/Datasets\/Staged\/Elevation\/LPC\/Projects\/USGS_Lidar_Point_Cloud_NY_CMPG_2013_LAS_2015\/metadata."},{"key":"ref_40","unstructured":"NYC Open Data (2018, September 08). Building Footprints. Available online: https:\/\/data.cityofnewyork.us\/Housing-Development\/Building-Footprints\/nqwf-w8eh."},{"key":"ref_41","unstructured":"Microsoft (2018, September 05). Bing Maps. Available online: https:\/\/www.bing.com\/maps."},{"key":"ref_42","unstructured":"USGS (2018, September 05). Lidar Point Cloud, Available online: ftp:\/\/rockyftp.cr.usgs.gov\/vdelivery\/Datasets\/Staged\/Elevation\/LPC\/Projects\/MI_WashtenawCo_2009\/laz."},{"key":"ref_43","unstructured":"Canziani, A., Paszke, A., and Culurciello, E. (2016). An Analysis of Deep Neural Network Models for Practical Applications. arXiv."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1016\/j.isprsjprs.2013.10.004","article-title":"Results of the ISPRS benchmark on urban object detection and 3D building reconstruction","volume":"93","author":"Rottensteiner","year":"2014","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_45","unstructured":"Qi, C.R., Su, H., Mo, K., and Guibas, L.J. (2016). PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. arXiv."},{"key":"ref_46","unstructured":"Qi, C.R., Yi, L., Su, H., and Guibas, L.J. (2017). PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space. arXiv."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Xu, Y., Fan, T., Xu, M., Zeng, L., and Qiao, Y. (2018). SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters. arXiv.","DOI":"10.1007\/978-3-030-01237-3_6"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/11\/3960\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T15:29:51Z","timestamp":1760196591000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/11\/3960"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11,15]]},"references-count":47,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2018,11]]}},"alternative-id":["s18113960"],"URL":"https:\/\/doi.org\/10.3390\/s18113960","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,11,15]]}}}