{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T08:07:01Z","timestamp":1767773221010,"version":"build-2065373602"},"reference-count":63,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2019,4,29]],"date-time":"2019-04-29T00:00:00Z","timestamp":1556496000000},"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>Road network extraction from remote sensing images has played an important role in various areas. However, due to complex imaging conditions and terrain factors, such as occlusion and shades, it is very challenging to extract road networks with complete topology structures. In this paper, we propose a learning-based road network extraction framework via a Multi-supervised Generative Adversarial Network (MsGAN), which is jointly trained by the spectral and topology features of the road network. Such a design makes the network capable of learning how to \u201cguess\u201d the aberrant road cases, which is caused by occlusion and shadow, based on the relationship between the road region and centerline; thus, it is able to provide a road network with integrated topology. Additionally, we also present a sample quality measurement to efficiently generate a large number of training samples with a little human interaction. Through the experiments on images from various satellites and the comprehensive comparisons to state-of-the-art approaches on the public datasets, it is demonstrated that the proposed method is able to provide high-quality results, especially for the completeness of the road network.<\/jats:p>","DOI":"10.3390\/rs11091017","type":"journal-article","created":{"date-parts":[[2019,4,29]],"date-time":"2019-04-29T07:01:22Z","timestamp":1556521282000},"page":"1017","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":43,"title":["Topology-Aware Road Network Extraction via Multi-Supervised Generative Adversarial Networks"],"prefix":"10.3390","volume":"11","author":[{"given":"Yang","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, Xiamen University, Xiamen 361005, China"},{"name":"College of Electronic Science, National University of Defense Technology, Changsha 410073, China"}]},{"given":"Zhangyue","family":"Xiong","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Xiamen University, Xiamen 361005, China"}]},{"given":"Yu","family":"Zang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Xiamen University, Xiamen 361005, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6075-796X","authenticated-orcid":false,"given":"Cheng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Xiamen University, Xiamen 361005, China"}]},{"given":"Jonathan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Xiamen University, Xiamen 361005, China"},{"name":"Department of Geography and Environmental Management, University of Waterloo, Waterloo, ON N2L 3G1, Canada"}]},{"given":"Xiang","family":"Li","sequence":"additional","affiliation":[{"name":"College of Electronic Science, National University of Defense Technology, Changsha 410073, China"}]}],"member":"1968","published-online":{"date-parts":[[2019,4,29]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Mnih, V., and Hinton, G.E. (2010). Learning to Detect Roads in High-Resolution Aerial Images. European Conference on Computer Vision, Springer.","key":"ref_1","DOI":"10.1007\/978-3-642-15567-3_16"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"530","DOI":"10.1109\/TPAMI.2004.1273918","article-title":"Learning to detect natural image boundaries using local brightness, color, and texture cues","volume":"26","author":"Martin","year":"2004","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2016.2514602","article-title":"Road Network Extraction via Aperiodic Directional Structure Measurement","volume":"54","author":"Zang","year":"2016","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"doi-asserted-by":"crossref","unstructured":"Baumgartner, A., Steger, C., Mayer, H., and Eckstein, W. (1997). Multi-Resolution, Semantic Objects, and Context for Road Extraction. Semantic Modeling for the Acquisition of Topographic Information from Images and Maps, Birkh\u00e4user.","key":"ref_4","DOI":"10.1007\/978-3-0348-8906-3_29"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"4441","DOI":"10.1109\/TGRS.2012.2190078","article-title":"Road network detection using probabilistic and graph theoretical methods","volume":"50","author":"Sirmacek","year":"2012","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"unstructured":"Ziems, M., Breitkopf, U., Heipke, C., and Rottensteiner, F. (September, January 25). Multiple-model based verification of road data. Proceedings of the XXII ISPRS Congress, Melbourne, Australia.","key":"ref_6"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"3359","DOI":"10.1109\/TGRS.2013.2272593","article-title":"An Integrated Method for Urban Main-Road Centerline Extraction From Optical Remotely Sensed Imagery","volume":"52","author":"Shi","year":"2014","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_8","first-page":"1","article-title":"Joint Enhancing Filtering for Road Network Extraction","volume":"99","author":"Zang","year":"2016","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_9","first-page":"32","article-title":"Road detection from high-resolution satellite images using artificial neural networks","volume":"9","author":"Mokhtarzade","year":"2007","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1977","DOI":"10.1080\/01431160802546837","article-title":"Road centreline extraction from high resolution imagery based on multiscale structural features and support vector machines","volume":"30","author":"Huang","year":"2009","journal-title":"Int. J. Remote Sens."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the Dimensionality of Data with Neural Networks","volume":"313","author":"Hinton","year":"2006","journal-title":"Science"},{"doi-asserted-by":"crossref","unstructured":"Wegner, J.D., Montoya-Zegarra, J.A., and Schindler, K. (2013, January 23\u201328). A Higher-Order CRF Model for Road Network Extraction. Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA.","key":"ref_12","DOI":"10.1109\/CVPR.2013.222"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"3322","DOI":"10.1109\/TGRS.2017.2669341","article-title":"Automatic Road Detection and Centerline Extraction via Cascaded End-to-End Convolutional Neural Network","volume":"55","author":"Cheng","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1192","DOI":"10.1109\/TIP.2005.864232","article-title":"Road extraction from aerial images using a region competition algorithm","volume":"15","author":"Amo","year":"2006","journal-title":"IEEE Trans. Image Process."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2211","DOI":"10.1109\/TIP.2010.2045715","article-title":"General road detection from a single image","volume":"19","author":"Kong","year":"2010","journal-title":"IEEE Trans. Image Process."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"3037","DOI":"10.1016\/S0167-8655(03)00164-8","article-title":"State of the art on automatic road extraction for GIS update: a novel classification","volume":"24","author":"Mena","year":"2003","journal-title":"Pattern Recognit. Lett."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1016\/j.cviu.2004.10.006","article-title":"A system to detect houses and residential street networks in multispectral satellite images","volume":"98","author":"Unsalan","year":"2005","journal-title":"Comput. Vision Image Underst."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"3906","DOI":"10.1109\/TGRS.2011.2136381","article-title":"Use of Salient Features for the Design of a Multistage Framework to Extract Roads From High-Resolution Multispectral Satellite Images","volume":"49","author":"Das","year":"2011","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2073","DOI":"10.1109\/36.951102","article-title":"A model-based approach to the automatic extraction of linear features from airborne images","volume":"39","author":"Katartzis","year":"2001","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1023\/B:VISI.0000013086.45688.5d","article-title":"A Gibbs Point Process for Road Extraction from Remotely Sensed Images","volume":"57","author":"Stoica","year":"2004","journal-title":"Int. J. Comput. Vis."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1109\/LGRS.2006.873875","article-title":"Improving urban road extraction in high-resolution images exploiting directional filtering, perceptual grouping, and simple topological concepts","volume":"3","author":"Gamba","year":"2006","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2807","DOI":"10.1109\/TGRS.2010.2041783","article-title":"Road Extraction From Satellite Images Using Particle Filtering and Extended Kalman Filtering","volume":"48","author":"Movaghati","year":"2010","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"511","DOI":"10.1109\/36.992826","article-title":"The line segment match method for extracting road network from high-resolution satellite images","volume":"40","author":"Shi","year":"2002","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"4653","DOI":"10.1080\/01431160701250382","article-title":"Classified road detection from satellite images based on perceptual organization","volume":"28","author":"Yang","year":"2007","journal-title":"Int. J. Remote Sens."},{"key":"ref_25","first-page":"95","article-title":"Automatic extraction and evaluation of road networks from satellite imagery","volume":"32","author":"Wiedemann","year":"1999","journal-title":"Int. Arch. Photogramm. Remote Sens."},{"key":"ref_26","first-page":"976","article-title":"Automatic completion and evaluation of road networks","volume":"33","author":"Wiedeman","year":"2000","journal-title":"Int. Arch. Photogramm. Remote Sens."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1457","DOI":"10.14358\/PERS.70.12.1457","article-title":"Increasing efficiency of road extraction by self-diagnosis","volume":"70","author":"Hinz","year":"2004","journal-title":"Photogramm. Eng. Remote Sens."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1016\/j.isprsjprs.2009.10.004","article-title":"Delineation and geometric modeling of road networks","volume":"65","author":"Poullis","year":"2010","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1111\/j.1477-9730.2011.00670.x","article-title":"Road network extraction in suburban areas","volume":"27","author":"Grote","year":"2012","journal-title":"Photogramm. Rec."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"4144","DOI":"10.1109\/TGRS.2007.906107","article-title":"Road Network Extraction and Intersection Detection From Aerial Images by Tracking Road Footprints","volume":"45","author":"Hu","year":"2007","journal-title":"Int. J. Remote Sens."},{"key":"ref_31","first-page":"8331","article-title":"Semi-automatic road tracking by template matching and distance transformation in urban areas","volume":"32","author":"Zhang","year":"2011","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1109\/34.659930","article-title":"An Unbiased Detector of Curvilinear Structures","volume":"20","author":"Steger","year":"1998","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"doi-asserted-by":"crossref","unstructured":"Steger, C., Mayer, H., and Radig, B. (1997). The role of grouping for road extraction. Automatic Extraction of Man-Made Objects from Aerial and Space Images (II), Springer.","key":"ref_33","DOI":"10.1007\/978-3-0348-8906-3_24"},{"unstructured":"Peteri, R., and Ranchin, T. (2006, January 6\u201310). Automated road network extraction using collaborative linear and surface models. Proceedings of the MAPPS\/ASPRS 2006 Fall Conference \u201cMeasuring the Earth II: Latest Develoopments with Digital Surface Modelling and Automated Feature Extration\u201d, San Antonio, TX, USA.","key":"ref_34"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1007\/s10851-006-7451-8","article-title":"General Adaptive Neighborhood Image Processing: Part I: Introduction and Theoretical Aspects","volume":"25","author":"Debayle","year":"2006","journal-title":"J. Math. Imaging Vis."},{"doi-asserted-by":"crossref","unstructured":"Qin, Y., Chi, M., Liu, X., Zhang, Y., Zeng, Y., and Zhao, Z. (2018, January 22\u201327). Classification of High Resolution Urban Remote Sensing Images Using Deep Networks by Integration of Social Media Photos. Proceedings of the IGARSS 2018\u20142018 IEEE International Geoscience and Remote Sensing Symposium, Valencia, Spain.","key":"ref_36","DOI":"10.1109\/IGARSS.2018.8518538"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1926","DOI":"10.1109\/JPROC.2017.2730585","article-title":"A novel methodology to label urban remote sensing images based on location-based social media photos","volume":"105","author":"Chi","year":"2017","journal-title":"Proc. IEEE"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"9086","DOI":"10.3390\/rs6099086","article-title":"Multi-level spatial analysis for change detection of urban vegetation at individual tree scale","volume":"6","author":"Zhou","year":"2014","journal-title":"Remote Sens."},{"doi-asserted-by":"crossref","unstructured":"He, F., Zhou, T., Xiong, W., Hasheminnasab, S., and Habib, A. (2018). Automated aerial triangulation for UAV-based mapping. Remote Sens., 10.","key":"ref_39","DOI":"10.3390\/rs10121952"},{"doi-asserted-by":"crossref","unstructured":"Zhao, X., Yu, B., Liu, Y., Chen, Z., Li, Q., Wang, C., and Wu, J. (2019). Estimation of Poverty Using Random Forest Regression with Multi-Source Data: A Case Study in Bangladesh. Remote Sens., 11.","key":"ref_40","DOI":"10.3390\/rs11040375"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"569","DOI":"10.1109\/TPAMI.2014.2345401","article-title":"Global Contrast based Salient Region Detection","volume":"37","author":"Cheng","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"doi-asserted-by":"crossref","unstructured":"Cheng, M.M., Warrell, J., Lin, W.Y., Zheng, S., Vineet, V., and Crook, N. (2013, January 1\u20138). Efficient salient region detection with soft image abstraction. Proceedings of the IEEE International Conference on Computer Vision, Sydney, NSW, Australia.","key":"ref_42","DOI":"10.1109\/ICCV.2013.193"},{"unstructured":"Borji, A., Cheng, M.M., Hou, Q., Jiang, H., and Li, J. (2014). Salient object detection: A survey. arXiv.","key":"ref_43"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"5706","DOI":"10.1109\/TIP.2015.2487833","article-title":"Salient Object Detection: A Benchmark","volume":"24","author":"Borji","year":"2015","journal-title":"IEEE Trans. Image Process."},{"doi-asserted-by":"crossref","unstructured":"Cheng, M.M., Liu, Y., Hou, Q., Bian, J., Torr, P., Hu, S.M., and Tu, Z. (2016). HFS: Hierarchical feature selection for efficient image segmentation. European Conference on Computer Vision, Springer.","key":"ref_45","DOI":"10.1007\/978-3-319-46487-9_53"},{"doi-asserted-by":"crossref","unstructured":"Liu, Y., Cheng, M.M., Hu, X., Wang, K., and Bai, X. (2017, January 21\u201326). Richer Convolutional Features for Edge Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","key":"ref_46","DOI":"10.1109\/CVPR.2017.622"},{"doi-asserted-by":"crossref","unstructured":"Chen, M., Habib, A., He, H., Zhu, Q., and Zhang, W. (2017). Robust feature matching method for SAR and optical images by using Gaussian-gamma-shaped bi-windows-based descriptor and geometric constraint. Remote Sens., 9.","key":"ref_47","DOI":"10.3390\/rs9090882"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"4528","DOI":"10.1109\/TGRS.2011.2146785","article-title":"LEGION-Based Automatic Road Extraction From Satellite Imagery","volume":"49","author":"Yuan","year":"2011","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_49","first-page":"2672","article-title":"Generative Adversarial Networks","volume":"3","author":"Goodfellow","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"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 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","key":"ref_50","DOI":"10.1109\/CVPR.2016.90"},{"unstructured":"Ulyanov, D., Vedaldi, A., and Lempitsky, V. (2016). Instance Normalization: The Missing Ingredient for Fast Stylization. arXiv.","key":"ref_51"},{"doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation, Springer International Publishing.","key":"ref_52","DOI":"10.1007\/978-3-319-24574-4_28"},{"doi-asserted-by":"crossref","unstructured":"Johnson, J., Alahi, A., and Li, F.F. (2016, January 8\u201316). Perceptual Losses for Real-Time Style Transfer and Super-Resolution. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.","key":"ref_53","DOI":"10.1007\/978-3-319-46475-6_43"},{"unstructured":"Simonyan, K., and Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv.","key":"ref_54"},{"unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A Method for Stochastic Optimization. arXiv.","key":"ref_55"},{"unstructured":"Mnih, V. (2013). Machine Learning for Aerial Image Labeling. [Ph.D. Thesis, University of Toronto].","key":"ref_56"},{"doi-asserted-by":"crossref","unstructured":"Wang, T.C., Liu, M.Y., Zhu, J.Y., Tao, A., Kautz, J., and Catanzaro, B. (2018, January 18\u201323). High-resolution image synthesis and semantic manipulation with conditional gans. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","key":"ref_57","DOI":"10.1109\/CVPR.2018.00917"},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1109\/LGRS.2012.2214761","article-title":"Road centerline extraction from high-resolution imagery based on shape features and multivariate adaptive regression splines","volume":"10","author":"Miao","year":"2013","journal-title":"IEEE IEEE Geosci. Remote Sens. Lett."},{"key":"ref_59","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1016\/j.neucom.2016.04.026","article-title":"Accurate urban road centerline extraction from VHR imagery via multiscale segmentation and tensor voting","volume":"205","author":"Cheng","year":"2016","journal-title":"Neurocomputing"},{"key":"ref_60","first-page":"276","article-title":"Analysis of automatic road extraction results from airborne SAR imagery","volume":"71","author":"Wessel","year":"2003","journal-title":"Appl. Therm. Eng."},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"709","DOI":"10.1109\/LGRS.2017.2672734","article-title":"Road Structure Refined CNN for Road Extraction in Aerial Image","volume":"14","author":"Wei","year":"2017","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_62","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1016\/j.isprsjprs.2015.07.002","article-title":"Road networks as collections of minimum cost paths","volume":"108","author":"Wegner","year":"2015","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"doi-asserted-by":"crossref","unstructured":"Zhong, Z., Li, J., Cui, W., and Jiang, H. (2016, January 10\u201315). Fully convolutional networks for building and road extraction: Preliminary results. Proceedings of the 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Beijing, China.","key":"ref_63","DOI":"10.1109\/IGARSS.2016.7729406"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/11\/9\/1017\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T12:47:59Z","timestamp":1760186879000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/11\/9\/1017"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4,29]]},"references-count":63,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2019,5]]}},"alternative-id":["rs11091017"],"URL":"https:\/\/doi.org\/10.3390\/rs11091017","relation":{},"ISSN":["2072-4292"],"issn-type":[{"type":"electronic","value":"2072-4292"}],"subject":[],"published":{"date-parts":[[2019,4,29]]}}}