{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T15:33:13Z","timestamp":1760369593431,"version":"build-2065373602"},"reference-count":28,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2020,2,17]],"date-time":"2020-02-17T00:00:00Z","timestamp":1581897600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the National Key Research and Development Program of China","award":["No. 2016YFC0803000"],"award-info":[{"award-number":["No. 2016YFC0803000"]}]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No. 41371342, No. 61331016"],"award-info":[{"award-number":["No. 41371342, No. 61331016"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Synthetic Aperture Rradar (SAR) provides rich ground information for remote sensing survey and can be used all time and in all weather conditions. Polarimetric SAR (PolSAR) can further reveal surface scattering difference and improve radar\u2019s application ability. Most existing classification methods for PolSAR imagery are based on manual features, such methods with fixed pattern has poor data adaptability and low feature utilization, if directly input to the classifier. Therefore, combining PolSAR data characteristics and deep network with auto-feature learning ability forms a new breakthrough direction. In fact, feature learning of deep network is to realize function approximation from data to label, through multi-layer accumulation, but finite layers limit the network\u2019s mapping ability. According to manifold hypothesis, high-dimensional data exists in potential low-dimensional manifold and different types of data locates in different manifolds. Manifold learning can model core variables of the target, and separate different data\u2019s manifold as much as possible, so as to complete data classification better. Therefore, taking manifold hypothesis as a starting point, nonlinear manifold learning integrated with fully convolutional networks for PolSAR image classification method is proposed in this paper. Firstly, high-dimensional polarized features are extracted based on scattering matrix and coherence matrix of original PolSAR data, whose compact representation is mined by manifold learning. Meanwhile, drawing on transfer learning, pre-trained Fully Convolutional Networks (FCN) model is utilized to learn deep spatial features of PolSAR imagery. Considering complementary advantages, weighted strategy is adopted to embed manifold representation into deep spatial features, which are input into support vector machine (SVM) classifier for final classification. A series of experiments on three PolSAR datasets have verified effectiveness and superiority of the proposed classification algorithm.<\/jats:p>","DOI":"10.3390\/rs12040655","type":"journal-article","created":{"date-parts":[[2020,2,20]],"date-time":"2020-02-20T03:20:03Z","timestamp":1582168803000},"page":"655","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Nonlinear Manifold Learning Integrated with Fully Convolutional Networks for PolSAR Image Classification"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3662-5769","authenticated-orcid":false,"given":"Chu","family":"He","sequence":"first","affiliation":[{"name":"Electronic and Information School, Wuhan University, Wuhan 430072, China"},{"name":"State Key Laboratory for Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China"}]},{"given":"Mingxia","family":"Tu","sequence":"additional","affiliation":[{"name":"Electronic and Information School, Wuhan University, Wuhan 430072, China"}]},{"given":"Dehui","family":"Xiong","sequence":"additional","affiliation":[{"name":"Electronic and Information School, Wuhan University, Wuhan 430072, China"}]},{"given":"Mingsheng","family":"Liao","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China"},{"name":"Collaborative Innovation Center for Geospatial Technology, 129 Luoyu Road, Wuhan 430079, China"}]}],"member":"1968","published-online":{"date-parts":[[2020,2,17]]},"reference":[{"key":"ref_1","unstructured":"Lee, J.S., and Pottier, E. (2009). Polarimetric Radar Imaging: From Basics to Applications, CRC Press."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"722","DOI":"10.1109\/TGRS.2003.819883","article-title":"Unsupervised terrain classification preserving polarimetric scattering characteristics","volume":"42","author":"Lee","year":"2004","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_3","first-page":"171","article-title":"Identification of terrain cover using the optimum polarimetric classifier","volume":"2","author":"Kong","year":"1988","journal-title":"J. Electromagn. Waves Appl."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1109\/7.53442","article-title":"Optimal speckle reduction in polarimetric SAR imagery","volume":"26","author":"Novak","year":"1990","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"ref_5","first-page":"26","article-title":"Group Theory and Polarisation Algebra","volume":"75","author":"Cloude","year":"1986","journal-title":"Optik"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"963","DOI":"10.1109\/36.673687","article-title":"A Three-Component Scattering Model for Polarimetric SAR Data","volume":"36","author":"Freeman","year":"2002","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1109\/MGRS.2016.2540798","article-title":"Deep learning for remote sensing data: A technical tutorial on the state of the art","volume":"4","author":"Zhang","year":"2016","journal-title":"IEEE Geosci. Remote Sens. Mag."},{"key":"ref_8","unstructured":"Hansch, R., and Hellwich, O. (2019, December 28). Classifcation of Polarimetric Sar Data by Complex Valued Neural Networks. Available online: https:\/\/www.isprs.org\/proceedings\/xxxviii\/1_4_7-W5\/paper\/Haensch-147.pdf."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"He, C., Liu, X., Feng, D., Shi, B., Luo, B., and Liao, M. (2017). Hierarchical terrain classifcation based on multilayer bayesian network and conditional random feld. Remote Sens., 9.","DOI":"10.3390\/rs9010096"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"246","DOI":"10.1016\/j.eswa.2019.04.006","article-title":"Hyperspectral imagery classification based on semi-supervised 3-D deep neural network and adaptive band selection","volume":"129","author":"Sellami","year":"2019","journal-title":"Expert Syst. Appl."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhang, H., and Shen, Q. (2017). Spectral-spatial classification of hyperspectral imagery with 3D convolutional neural network. Remote Sens., 9.","DOI":"10.3390\/rs9010067"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Goodman, J. (1975). Statistical Properties of Laser Speckle Patterns. Laser Speckle and Related Phenomena, Springer.","DOI":"10.1007\/BFb0111436"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Lee, J.S. (1985, January 20\u201323). Speckle suppression and analysis for synthetic aperture radar images. Proceedings of the International Conference on Speckle, San Diego, CA, USA.","DOI":"10.1117\/12.949537"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1487","DOI":"10.1109\/LGRS.2016.2593098","article-title":"Unsupervised Classification of PolSAR Imagery via Kernel Sparse Subspace Clustering","volume":"13","author":"Song","year":"2016","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1109\/TGRS.2011.2168532","article-title":"Laplacian Eigenmaps-Based Polarimetric Dimensionality Reduction for SAR Image Classification","volume":"50","author":"Tu","year":"2012","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2323","DOI":"10.1126\/science.290.5500.2323","article-title":"Nonlinear dimensionality reduction by locally linear embedding","volume":"290","author":"Roweis","year":"2000","journal-title":"Science"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1126\/science.295.5552.7a","article-title":"The Isomap Algorithm and Topological Stability","volume":"295","author":"Balasubramanian","year":"2002","journal-title":"Science"},{"key":"ref_18","unstructured":"Ainsworth, T.L., and Lee, J.S. (2001, January 9\u201313). Optimal Polarimetric Decomposition Variables-non-linear Dimensionality Reduction. Proceedings of the IGARSS 2001\u2014IEEE 2001 International Geoscience and Remote Sensing Symposium (Cat. No.01CH37217), Sydney, Australia."},{"key":"ref_19","unstructured":"Ainsworth, T.L., and Lee, J.S. (2004, January 20\u201324). Polarimetric SAR Image Classification Exploiting Optimal Variables Derived from Multiple Image Data Sets. Proceedings of the IGARSS 2004, 2004 IEEE International Geoscience and Remote Sensing Symposium, Anchorage, AK, USA."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1373","DOI":"10.1162\/089976603321780317","article-title":"Laplacian Eigenmaps for Dimensionality Reduction and Data Representation","volume":"15","author":"Belkin","year":"2003","journal-title":"Neural Comput."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1109\/LGRS.2012.2198612","article-title":"Supervised Graph Embedding for Polarimetric SAR Image Classification","volume":"10","author":"Shi","year":"2013","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1007\/BF02070821","article-title":"Approximation properties of a multilayered feedforward artifcial neural network","volume":"1","author":"Mhaskar","year":"1993","journal-title":"Adv. Comput. Math."},{"key":"ref_23","unstructured":"Olah, C. (2020, January 10). Neural Networks, Manifolds, and Topology. Available online: https:\/\/colah.github.io\/posts\/2014-03-NN-Manifolds-Topology\/."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Wang, Y., He, C., Liu, X., and Liao, M. (2018). A hierarchical fully convolutional network integrated with sparse and low-rank subspace representations for polsar imagery classifcation. Remote Sens., 10.","DOI":"10.3390\/rs10020342"},{"key":"ref_25","unstructured":"Jonathan, L., Evan, S., and Trevor, D. (2015, January 7\u201312). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1699","DOI":"10.1109\/TGRS.2005.852084","article-title":"Four-component scattering model for polarimetric SAR image decomposition","volume":"43","author":"Yamaguchi","year":"2005","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_27","first-page":"2579","article-title":"Visualizing high-dimensional data using t-sne","volume":"9","author":"Hinton","year":"2008","journal-title":"Vigiliae Christ."},{"key":"ref_28","first-page":"17","article-title":"Deep Learning of Representations for Unsupervised and Transfer Learning","volume":"27","author":"Bengio","year":"2012","journal-title":"JMLR: Workshop Conf. Proc."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/12\/4\/655\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T08:58:23Z","timestamp":1760173103000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/12\/4\/655"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2,17]]},"references-count":28,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2020,2]]}},"alternative-id":["rs12040655"],"URL":"https:\/\/doi.org\/10.3390\/rs12040655","relation":{},"ISSN":["2072-4292"],"issn-type":[{"type":"electronic","value":"2072-4292"}],"subject":[],"published":{"date-parts":[[2020,2,17]]}}}