{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T06:33:51Z","timestamp":1770273231607,"version":"3.49.0"},"reference-count":50,"publisher":"MDPI AG","issue":"23","license":[{"start":{"date-parts":[[2023,11,22]],"date-time":"2023-11-22T00:00:00Z","timestamp":1700611200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62006186"],"award-info":[{"award-number":["62006186"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272383"],"award-info":[{"award-number":["62272383"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["GX2105"],"award-info":[{"award-number":["GX2105"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["SKLGIE2019-M-3-2"],"award-info":[{"award-number":["SKLGIE2019-M-3-2"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Program of Beilin District in Xi\u2019an","award":["62006186"],"award-info":[{"award-number":["62006186"]}]},{"name":"Science and Technology Program of Beilin District in Xi\u2019an","award":["62272383"],"award-info":[{"award-number":["62272383"]}]},{"name":"Science and Technology Program of Beilin District in Xi\u2019an","award":["GX2105"],"award-info":[{"award-number":["GX2105"]}]},{"name":"Science and Technology Program of Beilin District in Xi\u2019an","award":["SKLGIE2019-M-3-2"],"award-info":[{"award-number":["SKLGIE2019-M-3-2"]}]},{"name":"National Key Laboratory of Geographic Information Engineering","award":["62006186"],"award-info":[{"award-number":["62006186"]}]},{"name":"National Key Laboratory of Geographic Information Engineering","award":["62272383"],"award-info":[{"award-number":["62272383"]}]},{"name":"National Key Laboratory of Geographic Information Engineering","award":["GX2105"],"award-info":[{"award-number":["GX2105"]}]},{"name":"National Key Laboratory of Geographic Information Engineering","award":["SKLGIE2019-M-3-2"],"award-info":[{"award-number":["SKLGIE2019-M-3-2"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Deep learning methods have gained significant popularity in the field of polarimetric synthetic aperture radar (PolSAR) image classification. These methods aim to extract high-level semantic features from the original PolSAR data to learn the polarimetric information. However, using only original data, these methods cannot learn multiple scattering features and complex structures for extremely heterogeneous terrain objects. In addition, deep learning methods always cause edge confusion due to the high-level features. To overcome these limitations, we propose a novel approach that combines a new double-channel convolutional neural network (CNN) with an edge-preserving Markov random field (MRF) model for PolSAR image classification, abbreviated to \u201cDCCNN-MRF\u201d. Firstly, a double-channel convolution network (DCCNN) is developed to combine complex matrix data and multiple scattering features. The DCCNN consists of two subnetworks: a Wishart-based complex matrix network and a multi-feature network. The Wishart-based complex matrix network focuses on learning the statistical characteristics and channel correlation, and the multi-feature network is designed to learn high-level semantic features well. Then, a unified network framework is designed to fuse two kinds of weighted features in order to enhance advantageous features and reduce redundant ones. Finally, an edge-preserving MRF model is integrated with the DCCNN network. In the MRF model, a sketch map-based edge energy function is designed by defining an adaptive weighted neighborhood for edge pixels. Experiments were conducted on four real PolSAR datasets with different sensors and bands. The experimental results demonstrate the effectiveness of the proposed DCCNN-MRF method.<\/jats:p>","DOI":"10.3390\/rs15235458","type":"journal-article","created":{"date-parts":[[2023,11,23]],"date-time":"2023-11-23T03:45:56Z","timestamp":1700711156000},"page":"5458","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Polarimetric Synthetic Aperture Radar Image Classification Based on Double-Channel Convolution Network and Edge-Preserving Markov Random Field"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1603-7698","authenticated-orcid":false,"given":"Junfei","family":"Shi","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Xi\u2019an University of Technology, Xi\u2019an 710048, China"},{"name":"Shaanxi Key Laboratory for Network Computing and Security Technology, Xi\u2019an University of Technology, Xi\u2019an 710048, China"}]},{"given":"Mengmeng","family":"Nie","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xi\u2019an University of Technology, Xi\u2019an 710048, China"},{"name":"Shaanxi Key Laboratory for Network Computing and Security Technology, Xi\u2019an University of Technology, Xi\u2019an 710048, China"}]},{"given":"Shanshan","family":"Ji","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xi\u2019an University of Technology, Xi\u2019an 710048, China"},{"name":"Shaanxi Key Laboratory for Network Computing and Security Technology, Xi\u2019an University of Technology, Xi\u2019an 710048, China"}]},{"given":"Cheng","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xi\u2019an University of Technology, Xi\u2019an 710048, China"},{"name":"Shaanxi Key Laboratory for Network Computing and Security Technology, Xi\u2019an University of Technology, Xi\u2019an 710048, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5961-5569","authenticated-orcid":false,"given":"Hongying","family":"Liu","sequence":"additional","affiliation":[{"name":"Medical College, Tianjin University, Tianjin 300134, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3742-4029","authenticated-orcid":false,"given":"Haiyan","family":"Jin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Xi\u2019an University of Technology, Xi\u2019an 710048, China"},{"name":"Shaanxi Key Laboratory for Network Computing and Security Technology, Xi\u2019an University of Technology, Xi\u2019an 710048, China"}]}],"member":"1968","published-online":{"date-parts":[[2023,11,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1839","DOI":"10.1109\/TGRS.2017.2768619","article-title":"Unsupervised Fine Land Classification Using Quaternion Autoencoder-Based Polarization Feature Extraction and Self-Organizing Mapping","volume":"56","author":"Kim","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_2","unstructured":"Shi, J. (2021). Image Processing Model and Method of Full-Polarization Synthetic Aperture Radar, Publishing House of Electronics Industry."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2592","DOI":"10.1109\/JSTARS.2016.2526626","article-title":"Urban Area Extraction Using X-Band Fully Polarimetric SAR Imagery","volume":"9","author":"Susaki","year":"2016","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Zhang, W.T., Wang, M., and Guo, J. (2021, January 3\u20135). A Novel Multi-Scale CNN Model for Crop Classification with Time-Series Fully Polarization SAR Images. Proceedings of the 2021 2nd China International SAR Symposium (CISS), Shanghai, China.","DOI":"10.23919\/CISS51089.2021.9652315"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Wang, Y., Chen, W., Mao, X., and Lei, W. (2022, January 22\u201324). Terrain classification of polarimetric SAR images based on optimal polarization features. Proceedings of the 2022 International Conference on Computer Engineering and Artificial Intelligence (ICCEAI), Shijiazhuang, China.","DOI":"10.1109\/ICCEAI55464.2022.00089"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Gadhiya, T., and Roy, A.K. (2018, January 16\u201318). Classification of Polarimetrie Synthetic Aperture Radar Images Using Revised Wishart Distance. Proceedings of the 2018 15th IEEE India Council International Conference (INDICON), Coimbatore, India.","DOI":"10.1109\/INDICON45594.2018.8987089"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2299","DOI":"10.1080\/01431169408954244","article-title":"Classification of multi-look polarimetric SAR imagery based on complex Wishart distribution","volume":"15","author":"Lee","year":"1994","journal-title":"Int. J. Remote Sens."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Luo, S., and Tong, L. (2022, January 17\u201322). A Fast Algorithm for the Sample of PolSAR Data Generation Based on the Wishart Distribution and Chaotic Map. Proceedings of the IGARSS 2022\u20142022 IEEE International Geoscience and Remote Sensing Symposium, Kuala Lumpur, Malaysia.","DOI":"10.1109\/IGARSS46834.2022.9883540"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"40041","DOI":"10.1109\/ACCESS.2018.2852768","article-title":"POLSAR image classification via clustering-WAE classification model","volume":"6","author":"Xie","year":"2018","journal-title":"IEEE Access"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1786","DOI":"10.1109\/TAC.2020.2995674","article-title":"Variational adaptive Kalman filter with Gaussian-inverse-Wishart mixture distribution","volume":"66","author":"Huang","year":"2020","journal-title":"IEEE Trans. Autom. Control"},{"key":"ref_11","first-page":"5600","article-title":"Unsupervised classification of multilook polarimetric SAR data using spatially variant wishart mixture model with double constraints","volume":"56","author":"Liu","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2023.3334492","article-title":"Unified Classification Framework for Multipolarization and Dual-Frequency SAR","volume":"61","author":"Liu","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1109\/TGRS.2018.2852633","article-title":"Variational learning of mixture wishart model for PolSAR image classification","volume":"57","author":"Wu","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Li, M., Shen, Q., Xiao, Y., Liu, X., and Chen, Q. (2023). PolSAR Image Building Extraction with G0 Statistical Texture Using Convolutional Neural Network and Superpixel. Remote Sens., 15.","DOI":"10.3390\/rs15051451"},{"key":"ref_15","first-page":"1829","article-title":"High-resolution polarized SAR image level set segmentation","volume":"19","author":"Zou","year":"2014","journal-title":"J. Image Graph."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"498","DOI":"10.1109\/36.485127","article-title":"A review of target decomposition theorems in radar polarimetry","volume":"34","author":"Cloude","year":"1996","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_17","unstructured":"Fang, C., Wen, H., and Yirong, W. (2006, January 16\u201319). An improved Cloude-Pottier decomposition using H-\u03b1-span and complex Wishart classifier for polarimetric SAR classification. Proceedings of the 2006 CIE International Conference on Radar, Shanghai, China."},{"key":"ref_18","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":"1998","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1090","DOI":"10.1109\/LGRS.2011.2157078","article-title":"Four-component decomposition of polarimetric SAR images with deorientation","volume":"8","author":"An","year":"2011","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_20","first-page":"1","article-title":"Unsupervised classification for Mini-RF SAR using m-\u03b4 decomposition and Wishart classification","volume":"Volume 1","author":"Zhang","year":"2006","journal-title":"Proceedings of the 2019 International Applied Computational Electromagnetics Society Symposium-China (ACES)"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Deng, J.W., Li, H.L., Cui, X.C., and Chen, S.W. (2022, January 25\u201327). Multi-Temporal PolSAR Image Classification Based on Polarimetric Scattering Tensor Eigenvalue Decomposition and Deep CNN Model. Proceedings of the 2022 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC), Xi\u2019an, China.","DOI":"10.1109\/ICSPCC55723.2022.9984546"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"905","DOI":"10.1109\/TGRS.2017.2756621","article-title":"Mixture WG\u0393-MRF Model for PolSAR Image Classification","volume":"56","author":"Song","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Qu, J., Qiu, X., Ding, C., and Lei, B. (2021). Unsupervised classification of polarimetric SAR image based on geodesic distance and non-Gaussian distribution feature. Sensors, 21.","DOI":"10.3390\/s21041317"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Li, Z.C., Li, H.C., Hu, W.S., and Pan, L. (2022, January 17\u201322). Spatially Variant Gamma-WMM with Extended Variational Inference for Unsupervised PolSAR Classification. Proceedings of the IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium, Kuala Lumpur, Malaysia.","DOI":"10.1109\/IGARSS46834.2022.9884637"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"3273","DOI":"10.1109\/TIP.2016.2567069","article-title":"Wishart deep stacking network for fast POLSAR image classification","volume":"25","author":"Jiao","year":"2016","journal-title":"IEEE Trans. Image Process."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"6362","DOI":"10.1109\/TGRS.2020.2976694","article-title":"Automatic design of CNNs via differentiable neural architecture search for PolSAR image classification","volume":"58","author":"Dong","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1016\/j.neucom.2020.01.020","article-title":"PolSAR image classification via a novel semi-supervised recurrent complex-valued convolution neural network","volume":"388","author":"Xie","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1580","DOI":"10.1109\/LGRS.2020.3005076","article-title":"Active ensemble deep learning for polarimetric synthetic aperture radar image classification","volume":"18","author":"Liu","year":"2020","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_29","first-page":"1","article-title":"Adaptive graph convolutional network for PolSAR image classification","volume":"60","author":"Liu","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Luo, J., Lv, Y., and Guo, J. (2022, January 2\u20134). Multi-temporal PolSAR Image Classification Using F-SAE-CNN. Proceedings of the 2022 3rd China International SAR Symposium (CISS), Shanghai, China.","DOI":"10.1109\/CISS57580.2022.9971318"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Ren, Y., Jiang, W., and Liu, Y. (2023). A New Architecture of a Complex-Valued Convolutional Neural Network for PolSAR Image Classification. Remote Sens., 15.","DOI":"10.3390\/rs15194801"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"8796","DOI":"10.1109\/TGRS.2019.2922978","article-title":"CNN-based polarimetric decomposition feature selection for PolSAR image classification","volume":"57","author":"Yang","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Bi, H., Santos-Rodriguez, R., and Flach, P. (October, January 6). Polsar Image Classification via Robust Low-Rank Feature Extraction and Markov Random Field. Proceedings of the IGARSS 2020\u20142020 IEEE International Geoscience and Remote Sensing Symposium, Waikoloa, HI, USA.","DOI":"10.1109\/IGARSS39084.2020.9324175"},{"key":"ref_34","first-page":"1","article-title":"Attention-based polarimetric feature selection convolutional network for PolSAR image classification","volume":"19","author":"Dong","year":"2020","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_35","first-page":"1","article-title":"A Statistical-Spatial Feature Learning Network for PolSAR Image Classification","volume":"19","author":"Wu","year":"2021","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Shi, J., and Jin, H. (2022, January 17\u201322). Complex Matrix and Polarimetric Feature Joint Learning for Polarimetric Sar Image Classification. Proceedings of the IGARSS 2022\u20142022 IEEE International Geoscience and Remote Sensing Symposium, Kuala Lumpur, Malaysia.","DOI":"10.1109\/IGARSS46834.2022.9884297"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Liang, W., Wu, Y., Li, M., Cao, Y., and Hu, X. (2021). High-resolution SAR image classification using multi-scale deep feature fusion and covariance pooling manifold network. Remote Sens., 13.","DOI":"10.3390\/rs13020328"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"49","DOI":"10.4236\/ars.2022.112004","article-title":"Simulated Annealing for Land Cover Classification in PolSAR Images","volume":"11","author":"Koukiou","year":"2022","journal-title":"Adv. Remote Sens."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Ni, L., Zhang, B., Shen, Q., Gao, L., Sun, X., Li, S., and Wu, H. (2014, January 24\u201327). Edge constrained MRF method for classification of hyperspectral imagery. Proceedings of the 2014 6th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), Lausanne, Switzerland.","DOI":"10.1109\/WHISPERS.2014.8077498"},{"key":"ref_40","first-page":"19","article-title":"Fully Polarimetric Land Cover Classification Based on Markov Chains","volume":"10","author":"Koukiou","year":"2021","journal-title":"Adv. Remote Sens."},{"key":"ref_41","first-page":"13","article-title":"Fully Polarimetric Land Cover Classification Based on Hidden Markov Models Trained with Multiple Observations","volume":"10","author":"Karachristos","year":"2021","journal-title":"Prog. Remote Sens. Technol."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"025008","DOI":"10.1117\/1.JRS.10.025008","article-title":"Unsupervised polarimetric synthetic aperture radar image classification based on sketch map and adaptive Markov random field","volume":"10","author":"Shi","year":"2016","journal-title":"J. Appl. Remote Sens."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1016\/j.patcog.2016.02.020","article-title":"Hierarchical semantic model and scattering mechanism based PolSAR image classification","volume":"59","author":"Liu","year":"2016","journal-title":"Pattern Recognit."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"2363","DOI":"10.1109\/36.789635","article-title":"Polarimetric SAR speckle filtering and its implication for classification","volume":"37","author":"Lee","year":"1999","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"30491","DOI":"10.1109\/ACCESS.2020.2973246","article-title":"A Novel Multi-feature Joint Learning Method for Fast Polarimetric SAR Terrain Classification","volume":"8","author":"Shi","year":"2020","journal-title":"IEEE Access"},{"key":"ref_46","first-page":"1","article-title":"Superpixel-based Cropland Classification of SAR Image with Statistical Texture and Polarization Features","volume":"19","author":"Chen","year":"2021","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_47","first-page":"1","article-title":"Polarimetric Multipath Convolutional Neural Network for PolSAR Image Classification","volume":"60","author":"Cui","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Li, R., Zheng, S., Duan, C., Yang, Y., and Wang, X. (2020). Classification of Hyperspectral Image Based on Double-Branch Dual-Attention Mechanism Network. Remote Sens., 12.","DOI":"10.20944\/preprints201912.0059.v2"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Fan, Z., Ji, Z., Fu, P., Wang, T., and Sun, Q. (October, January 26). Complex-Valued Spatial-Scattering Separated Attention Network for Polsar Image Classification. Proceedings of the IGARSS 2020-2020 IEEE International Geoscience and Remote Sensing Symposium, Waikoloa, HI, USA.","DOI":"10.1109\/IGARSS39084.2020.9323951"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"7177","DOI":"10.1109\/TGRS.2017.2743222","article-title":"Complex-Valued Convolutional Neural Network and Its Application in Polarimetric SAR Image Classification","volume":"55","author":"Zhang","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/23\/5458\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:27:40Z","timestamp":1760131660000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/23\/5458"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,22]]},"references-count":50,"journal-issue":{"issue":"23","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["rs15235458"],"URL":"https:\/\/doi.org\/10.3390\/rs15235458","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,22]]}}}