{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T02:59:10Z","timestamp":1774493950150,"version":"3.50.1"},"reference-count":65,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2021,3,7]],"date-time":"2021-03-07T00:00:00Z","timestamp":1615075200000},"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 segmentation for synthetic aperture radar (SAR) images is of great practical significance. With the rapid development and wide application of SAR imaging technology, this problem has attracted much attention. At present, there are numerous road segmentation methods. This paper analyzes and summarizes the road segmentation methods for SAR images over the years. Firstly, the traditional road segmentation algorithms are classified according to the degree of automation and the principle. Advantages and disadvantages are introduced successively for each traditional method. Then, the popular segmentation methods based on deep learning in recent years are systematically introduced. Finally, novel deep segmentation neural networks based on the capsule paradigm and the self-attention mechanism are forecasted as future research for SAR images.<\/jats:p>","DOI":"10.3390\/rs13051011","type":"journal-article","created":{"date-parts":[[2021,3,7]],"date-time":"2021-03-07T21:52:15Z","timestamp":1615153935000},"page":"1011","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Review of Road Segmentation for SAR Images"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0114-8173","authenticated-orcid":false,"given":"Zengguo","family":"Sun","sequence":"first","affiliation":[{"name":"Key Laboratory of Modern Teaching Technology, Ministry of Education, Xi\u2019an 710062, China"},{"name":"School of Computer Science, Shaanxi Normal University, Xi\u2019an 710119, China"}]},{"given":"Hui","family":"Geng","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shaanxi Normal University, Xi\u2019an 710119, China"}]},{"given":"Zheng","family":"Lu","sequence":"additional","affiliation":[{"name":"Institute of Remote Sensing Satellite, Beijing 100094, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9592-262X","authenticated-orcid":false,"given":"Rafa\u0142","family":"Scherer","sequence":"additional","affiliation":[{"name":"Department of Intelligent Computer Systems, Czestochowa University of Technology, Armii Krajowej 36, 42-200 Cz\u0119stochowa, Poland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9073-5347","authenticated-orcid":false,"given":"Marcin","family":"Wo\u017aniak","sequence":"additional","affiliation":[{"name":"Faculty of Applied Mathematics, Silesian University of Technology, Kaszubska 23, 44-100 Gliwice, Poland"}]}],"member":"1968","published-online":{"date-parts":[[2021,3,7]]},"reference":[{"key":"ref_1","unstructured":"Zhang, Y.N., and Li, Y. (2004). The Key Technology of SAR Image Processing, Electronic Industry Press."},{"key":"ref_2","unstructured":"Oliver, C., and Quegan, S. (2004). Understanding Synthetic Aperture Radar Images, Artech House."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"488","DOI":"10.1080\/2150704X.2018.1562256","article-title":"A SAR change detection method based on the consistency of single-pixel difference and neighborhood difference","volume":"10","author":"Cui","year":"2019","journal-title":"Remote Sens. Lett."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"933","DOI":"10.1016\/j.dt.2019.11.014","article-title":"Arbitrary-oriented target detection in large scene sar images","volume":"16","author":"Han","year":"2020","journal-title":"Def. Technol."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Yang, F., Wang, H., and Jin, Z. (2020). A fusion network for road detection via spatial propagation and spatial transformation. Pattern Recognit., 100.","DOI":"10.1016\/j.patcog.2019.107141"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Yu, Z., Wang, W., Li, C., Liu, W., and Yang, J. (2018). Speckle Noise Suppression in SAR Images Using a Three-Step Algorithm. Sensors, 18.","DOI":"10.3390\/s18113643"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1109\/TGRS.1990.572977","article-title":"Finding Curvilinear Features in Speckled Images","volume":"28","author":"Samadani","year":"1990","journal-title":"IEEE Trans. Geosci. Remote. Sens."},{"key":"ref_8","first-page":"11","article-title":"Review of road network extraction from SAR images","volume":"18","author":"Cheng","year":"2013","journal-title":"J. Image Graph."},{"key":"ref_9","unstructured":"Cheng, J.H. (2013). Road Extraction in High-Resolution SAR Images, National University of Defense Technology."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1785","DOI":"10.1109\/TGRS.2003.813850","article-title":"Road vectors update using SAR imagery: A snake-based method","volume":"41","author":"Bentabet","year":"2003","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_11","first-page":"1403","article-title":"SAR image road extraction combining tensor voting and Snakes model","volume":"20","author":"Fu","year":"2015","journal-title":"J. Image Graph."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"207","DOI":"10.14358\/PERS.83.3.207","article-title":"Road Network Extraction from High-Resolution SAR Imagery Based on the Network Snake Model","volume":"83","author":"Saati","year":"2017","journal-title":"Photogramm. Eng. Remote. Sens."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1080\/01621459.1949.10483310","article-title":"The Monte Carlo Method","volume":"44","author":"Nicholas","year":"1949","journal-title":"J. Am. Stat. Assoc."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"8199","DOI":"10.1080\/01431161.2013.835082","article-title":"Road extraction from SAR imagery based on an improved particle filtering and snake model","volume":"34","author":"Liu","year":"2013","journal-title":"Int. J. Remote. Sens."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"4979","DOI":"10.1080\/01431161.2016.1225179","article-title":"Parallel particle filter for tracking road centerlines from high-resolution SAR images using detected road junctions as initial seed points","volume":"37","author":"Cheng","year":"2016","journal-title":"Int. J. Remote Sens."},{"key":"ref_16","unstructured":"Mu, L. (2010). Study on Road Extraction of High Resolution Polarimetric SAR Interferometry Data, Liaoning University of Engineering and Technology."},{"key":"ref_17","unstructured":"Cheng, J.H., Guan, Y.F., and Ku, X.S. (2011, January 15\u201317). Semi-automatic road centerline extraction in high-resolution SAR images based on circular template matching. Proceedings of the International Conference on Electric Information and Control Engineering, Wuhan, China."},{"key":"ref_18","first-page":"8","article-title":"High-resolution SAR image highway extraction algorithm","volume":"27","author":"Su","year":"2012","journal-title":"Remote Sens. Inf."},{"key":"ref_19","first-page":"866","article-title":"PolSAR image runways detection based on multi-stage classification","volume":"36","author":"Han","year":"2014","journal-title":"J. Syst. Eng. Electron."},{"key":"ref_20","first-page":"1308","article-title":"High-resolution SAR image road network extraction combining statistics and shape features","volume":"38","author":"Yu","year":"2013","journal-title":"J. Wuhan Univ."},{"key":"ref_21","first-page":"198","article-title":"New road extraction algorithm of high-resolution SAR image","volume":"52","author":"Xiao","year":"2016","journal-title":"Comput. Eng. Appl."},{"key":"ref_22","first-page":"1186","article-title":"Fast detection of airport runways in PolSAR images based on adaptive unsupervised classification","volume":"23","author":"Lu","year":"2019","journal-title":"J. Remote Sens."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"3721","DOI":"10.1080\/01431161.2018.1552814","article-title":"Multi-chromatic analysis polarimetric interferometric synthetic aperture radar (MCA-PollnSAR) for urban classification","volume":"40","author":"Biondi","year":"2019","journal-title":"Int. J. Remote Sens."},{"key":"ref_24","first-page":"227","article-title":"Semi-automatic road extraction from SAR images using EKF and PF, ISPRS-International Archives of the Photogrammetry","volume":"7","author":"Zhao","year":"2015","journal-title":"Remote Sens. Spat. Inf. Sci."},{"key":"ref_25","first-page":"1144","article-title":"Semi-automatic road extraction from SAR images using an improved profile matching and EKF","volume":"42","author":"Zhao","year":"2017","journal-title":"Geomat. Inf. Science Wuhan Univ."},{"key":"ref_26","first-page":"1218","article-title":"Automatic extraction of roads from low resolution SAR images","volume":"10","author":"Jia","year":"2005","journal-title":"J. Image Graph."},{"key":"ref_27","first-page":"36","article-title":"Research on roads automatic extraction from low resolution remote sensing image","volume":"12","author":"Hong","year":"2008","journal-title":"J. Remote Sens."},{"key":"ref_28","first-page":"820","article-title":"PolInSAR Image Classification Based on Compressed Sensing and Multi-scale Pyramid","volume":"37","author":"He","year":"2011","journal-title":"Acta Autom. Sin."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"434","DOI":"10.1109\/36.662728","article-title":"Detection of linear features in SAR images: Application to road network extraction","volume":"36","author":"Tupin","year":"1998","journal-title":"IEEE Trans. Geosci. Remote. Sens."},{"key":"ref_30","first-page":"17","article-title":"A road extraction algorithm combining MRF segmentation and mathematical morphology","volume":"35","author":"Chen","year":"2015","journal-title":"China Space Sci. Technol."},{"key":"ref_31","unstructured":"Cheng, J.H., Ding, W.X., and Zhu, X.W. (2016, January 23\u201326). GPU-accelerated main road extraction in Polarimetric SAR images based on MRF. Proceedings of the 42nd Annual Conference of the IEEE Industrial Electronics Society, Florence, Italy."},{"key":"ref_32","first-page":"156","article-title":"SAR image road detection based on Hough transform and genetic algorithm","volume":"3","author":"Jiang","year":"2005","journal-title":"Radar Sci. Technol."},{"key":"ref_33","first-page":"1134","article-title":"Automatic road extraction from SAR imagery based on genetic algorithm","volume":"13","author":"Jia","year":"2008","journal-title":"J. Image Graph."},{"key":"ref_34","first-page":"93","article-title":"Road network extraction in classified SAR images using genetic algorithm","volume":"93","author":"Xiao","year":"2004","journal-title":"J. Image Graph."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"246","DOI":"10.1006\/gmip.1996.0021","article-title":"Fuzzy Connectedness and Object Definition: Theory, Algorithms, and Applications in Image Segmentation","volume":"58","author":"Udupa","year":"1996","journal-title":"Graph. Model. Image Process."},{"key":"ref_36","first-page":"523","article-title":"Automatic road extraction from high resolution SAR images based on fuzzy connectedness","volume":"35","author":"Fu","year":"2015","journal-title":"J. Comput. Appl."},{"key":"ref_37","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_38","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"Lecun","year":"2015","journal-title":"Nature"},{"key":"ref_39","first-page":"1229","article-title":"Review of research on convolutional neural networks","volume":"40","author":"Zhou","year":"2017","journal-title":"Chin. J. Comput."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., and Darrell, T. (2014, January 24\u201327). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","article-title":"Selective search for object recognition","volume":"104","author":"Uijlings","year":"2013","journal-title":"Int. J. Comput. Vis."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","volume":"37","author":"He","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_43","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_44","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_45","first-page":"852","article-title":"AIR-SARShip-1.0: High-resolution SAR ship detection dataset","volume":"8","author":"Sun","year":"2019","journal-title":"J. Radars"},{"key":"ref_46","unstructured":"Dai, J.F., Li, Y., He, K.M., and Sun, J. (2016). R-FCN: Object detection via region-based fully convolutional networks. Neural Inf. Process. Syst., 179\u2013387."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Dai, J.F., He, K.M., and Sun, J. (2016, January 27\u201330). Instance-aware Semantic Segmentation via Multi-task Network Cascades. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.343"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Li, Y., Qi, H.Z., and Dai, J.F. (2017, January 22\u201325). Fully Convolutional Instance-aware Semantic Segmentation. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.472"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"He, K.M., Gkioxari, G., and Doll, R.P. (2017, January 22\u201329). Mask R-CNN. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"1867","DOI":"10.1109\/LGRS.2018.2864342","article-title":"Road segmentation in SAR satellite images with deep fully convolutional neural networks","volume":"15","author":"Corentin","year":"2018","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_51","first-page":"1778","article-title":"New method of SAR image road recognition based on deep learning","volume":"50","author":"Chen","year":"2020","journal-title":"J. Jilin Univ."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"John, V., Guo, C.Z., and Mita, S. (2016, January 4\u20138). Fast road scene segmentation using deep learning and scene-based models. Proceedings of the International Conference on Pattern Recognition, Cancun, Mexico.","DOI":"10.1109\/ICPR.2016.7900220"},{"key":"ref_53","unstructured":"Li, H.Y., Chen, Y.P., and Yang, Y. (August, January 28). Deep learning road extraction model based on similarity mapping relationship. Proceedings of the IEEE International Geoscience and Remote Sensing Symposium, Yokohama, Japan."},{"key":"ref_54","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_55","unstructured":"Sabour, S., Frosst, N., and Hinton, G.E. (2017, January 4\u20139). Dynamic routing between capsules. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Islam, K.A., P\u00e9rez, D., and Hill, V. (2018, January 23\u201326). Seagrass detection in coastal water through deep capsule networks. Proceedings of the Chinese Conference on Pattern Recognition and Computer Vision (PRCV), Guangzhou, China.","DOI":"10.1007\/978-3-030-03335-4_28"},{"key":"ref_57","unstructured":"Singh, M., Singh, R., and Vatsa, M. (November, January 27). Dual directed capsule network for very low-resolution image recognition. Proceedings of the International Conference on Computer Vision, Seoul, Korea."},{"key":"ref_58","doi-asserted-by":"crossref","unstructured":"Schwegmann, C.P., Kleynhans, W., and Salmon, B.P. (2018, January 22\u201327). Synthetic aperture radar ship detection using capsule networks. Proceedings of the IEEE International Geoscience and Remote Sensing Symposium, Valencia, Spain.","DOI":"10.1109\/IGARSS.2018.8517804"},{"key":"ref_59","doi-asserted-by":"crossref","unstructured":"Wang, Y.Q., Sun, A.X., and Han, J.L. (2018, January 23\u201327). Sentiment analysis by capsules. Proceedings of the Web Conference, Lyons, France.","DOI":"10.1145\/3178876.3186015"},{"key":"ref_60","doi-asserted-by":"crossref","unstructured":"Iqbal, T., Xu, Y., and Kong, Q.Q. (2018, January 3\u20137). Capsule routing for sound event detection. Proceedings of the European Signal Processing Conference, Rome, Italy.","DOI":"10.23919\/EUSIPCO.2018.8553198"},{"key":"ref_61","unstructured":"Hao, R., and Hong, L. (2018). Compositional coding capsule network with k-means routing for text classification. arXiv."},{"key":"ref_62","unstructured":"Vaswani, A., Shazeer, N., and Parmar, N. (2017, January 4\u20139). Attention is all you need. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_63","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1016\/j.neucom.2020.01.006","article-title":"Bidirectional LSTM with self-attention mechanism and multi-channel features for sentiment classification","volume":"387","author":"Li","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_64","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1016\/j.asoc.2020.106186","article-title":"BG-SAC: Entity relationship classification model based on self-attention supported Capsule networks","volume":"91","author":"Peng","year":"2020","journal-title":"Appl. Soft Comput. J."},{"key":"ref_65","doi-asserted-by":"crossref","unstructured":"Zhao, W., Chen, X., Chen, J., and Qu, Y. (2020). Sample Generation with Self-Attention Generative Adversarial Adaptation Network (SaGAAN) for Hyperspectral Image Classification. Remote. Sens., 12.","DOI":"10.3390\/rs12050843"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/5\/1011\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:34:35Z","timestamp":1760160875000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/5\/1011"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,7]]},"references-count":65,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2021,3]]}},"alternative-id":["rs13051011"],"URL":"https:\/\/doi.org\/10.3390\/rs13051011","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,7]]}}}