Abstract
Convolutional residual networks have shown great success for classification of polarimetric synthetic aperture radar (PolSAR) images especially when the depth of network is increased and limited training samples are available. But, the ability of convolutional kernels is in extraction of spatial features from neighboring pixels. They may not sufficiently able to extract the radar’s physical features from the PolSAR images. To deal with this difficulty, a residual network is proposed in this work. In addition to the feature maps extracted by convolutional kernels of previous layers, the proposed network injects the physical feature maps extracted by the H-A-\(\mathrm{\alpha }\) decomposition to each addition layer. Moreover, the use of a convolutional autoencoder behind the residual blocks is proposed to reduce the speckle noise. The proposed method provides more accurate classification maps compared to conventional residual networks and several state-of-the-art methods. However, it needs more running time for implementation.
Similar content being viewed by others
Data availability
No new data is used in this paper. The datasets used for the experiments are benchmark datasets.
References
Basso D, Colnago M, Azevedo S et al (2021) Combining morphological filtering, anisotropic diffusion and block-based data replication for automatically detecting and recovering unscanned gaps in remote sensing images. Earth Sci Inform 14:1145–1158
Bosma DA, Krasnov OA, Yarovoy A (2022) Polarimetric signatures of moving automotive vehicles based on H/A/α-decomposition: preliminary results with PARSAX radar data. 2022 23rd International Radar Symposium (IRS), pp 414–419
Chen Y, Li L, Jiao L, Li Y, Liu X, Chai X (2021) Nonlinear Projective Dictionary Pair Learning for PolSAR Image Classification. IEEE Access 9:70650–70661
Cloude SR, Pottier E (1996) A review of target decomposition theorems in radar polarimetry. IEEE Trans Geosci Remote Sens 34(2):498–518
Cloude SR, Pottier E (1997) An entropy-based classification scheme for land applications of polarimetric SAR. IEEE Trans Geosci Remote Sens 35(1):68–78
Dhingra G, Kumar V, Joshi HD (2021) Quality assessment of leaves quality using texture and DWT based local feature extraction analysis. Chemom Intell Lab Syst 208:104195
Gaglione D, Clemente C, Pallotta L, Proudler I, De Maio A, Soraghan JJ (2014) Krogager decomposition and Pseudo-Zernike moments for polarimetric distributed ATR. 2014 Sensor Signal Processing for Defence (SSPD), pp 1–5
Gui R, Xu X, Wang L, Yang R, Pu F (2020) Eigenvalue statistical components-based PU-learning for PolSAR built-up areas extraction and cross-domain analysis. IEEE J Sel Top Appl Earth Obs Remote Sens 13:3192–3203
Huang X, Liao C, Xing M, Ziniti B, Wang J, Shang J, Liu J, Dong T, Xie Q, Torbick N (2019) A multi-temporal binary-tree classification using polarimetric RADARSAT-2 imagery. Remote Sens Environ 235:111478
Imani M (2021) Integration of the k-nearest neighbours and patch-based features for PolSAR image classification by using a two-branch residual network. Remote Sens Lett 12(11):1112–1122
Imani M (2022a) Low frequency and radar’s physical based features for improvement of convolutional neural networks for PolSAR image classification. Egypt J Remote Sens Space Sci 25:55–62
Imani M (2022b) Entropy/Anisotropy/Alpha Based 3DGabor Filter Bank for PolSAR Image Classification. Geocarto Int. https://doi.org/10.1080/10106049.2022.2142963
Kalaiselvi S, Gomathi V (2020) α-cut induced fuzzy deep neural network for change detection of SAR images. Appl Soft Comput 95:106510
Kang X, Li S, Benediktsson JA (2014) Spectral-spatial hyperspectral image classification with edge-preserving filtering. IEEE Trans Geosci Remote Sens 52(5):2666–2677
Khankeshizadeh E, Mohammadzadeh A, Moghimi A et al (2022) FCD-R2U-net: forest change detection in bi-temporal satellite images using the recurrent residual-based U-net. Earth Sci Inform 15:2335–2347
Kouroupis G, Anastassopoulos V (2016) A Markov chain model based on Cameron's CTD ship detection scheme. 2016 IEEE International Conference on Imaging Systems and Techniques (IST), pp 100–105
Liu G, Li Y, Jiao L, Chen Y, Shang R (2021) Multiobjective evolutionary algorithm assisted stacked autoencoder for PolSAR image classification. Swarm Evol Comput 60:100794
Li L, Zeng J, Jiao L, Liang P, Liu F, Yang S (2020a) Online active extreme learning machine with discrepancy sampling for PolSAR classification. IEEE Trans Geosci Remote Sens 58(3):2027–2041
Li X et al (2020b) SSCV-GANs: semi-supervised complex-valued GANs for PolSAR image classification. IEEE Access 8:146560–146576
Li L, Ma L, Jiao L, Liu F, Sun Q, Zhao J (2020c) Complex Contourlet-CNN for polarimetric SAR image classification. Pattern Recogn 100:107110
Liu G, Liu B, Zheng G, Li X (2022) Environment monitoring of Shanghai Nanhui intertidal zone with dual-polarimetric SAR data based on deep learning. IEEE Trans Geosci Remote Sens 60(Art no. 4208918):1–18
Maia DS, Pham M-T, Lefèvre S (2022) Watershed-based attribute profiles with semantic prior knowledge for remote sensing image analysis. IEEE J Sel Top Appl Earth Obs Remote Sens 15:2574–2591
Mohammadi Asiyabi R, Sahebi MR, Ghorbanian A (2022) Segment-based bag of visual words model for urban land cover mapping using polarimetric SAR data. Adv Space Res 70(12):3784–3797
Nie X, Ding S, Huang X, Qiao H, Zhang B, Jiang Z-P (2019) An online multiview learning algorithm for PolSAR data real-time classification. IEEE J Sel Top Appl Earth Obs Remote Sens 12(1):302–320
Qin X, Zou H, Yu W, Wang P (2021) Superpixel-oriented classification of PolSAR images using complex-valued convolutional neural network driven by hybrid data. IEEE Trans Geosci Remote Sens 59(12):10094–10111
Ren S, Zhou F (2021) Semi-supervised classification for PolSAR data with multi-scale evolving weighted graph convolutional network. IEEE J Sel Top Appl Earth Obs Remote Sens 14:2911–2927
Shakin Banu A, Vasuki P, Md Mansoor Roomi S (2020) Target detection in SAR images using bayesian saliency and morphological attribute profiles. Comput Commun 160:738–748
Shang R, He J, Wang J, Xu K, Jiao L, Stolkin R (2020) Dense connection and depthwise separable convolution based CNN for polarimetric SAR image classification. Knowl-Based Syst 194:105542
Song W, Wu Y, Guo P (2021) Composite Kernel and hybrid discriminative random field model based on feature fusion for PolSAR image classification. IEEE Geosci Remote Sens Lett 18(6):1069–1073
Tan X, Li M, Zhang P, Wu Y, Song W (2020) Complex-valued 3-D convolutional neural network for PolSAR image classification. IEEE Geosci Remote Sens Lett 17(6):1022–1026
Upreti M, Kumar D (2021) Investigating capability of open archive multispectral and SAR datasets for Wheat crop monitoring and acreage estimation studies. Earth Sci Inform 14:2017–2035
Wang L, Hong H, Zhang Y, Wu J, Ma L, Zhu Y (2022) PolSAR-SSN: an end-to-end superpixel sampling network for PolSAR image classification. IEEE Geosci Remote Sens Lett 19(Art no. 4505305):1–5
Xiang D, Wang W, Tang T, Su Y (2017) Multiple-component polarimetric decomposition with new volume scattering models for PolSAR urban areas. IET Radar Sonar Navig 11(3):410–419
Xie W, Ma G, Zhao F, Liu H, Zhang L (2020) PolSAR image classification via a novel semi-supervised recurrent complex-valued convolution neural network. Neurocomputing 388:255–268
Yang R, Hu Z, Liu Y, Xu Z (2020) A novel polarimetric SAR classification method integrating pixel-based and patch-based classification. IEEE Geosci Remote Sens Lett 17(3):431–435
Yang L, Liu H, Chen F (2022) Just-in-time updating soft sensor model of endpoint carbon content and temperature in BOF steelmaking based on deep residual supervised autoencoder. Chemom Intell Lab Syst 231:104679
Zhang Z, Wang H, Xu F, Jin Y-Q (2017) Complex-valued convolutional neural network and its application in polarimetric SAR image classification. IEEE Trans Geosci Remote Sens 55(12):7177–7188
Zhang A, Yang X, Fang S, Ai J (2020) Region level SAR image classification using deep features and spatial constraints. ISPRS J Photogramm Remote Sens 163:36–48
Zhang P, Ban Y, Nascetti A (2021) Learning U-Net without forgetting for near real-time wildfire monitoring by the fusion of SAR and optical time series. Remote Sens Environ 261:112467
Zhao J, Datcu M, Zhang Z, Xiong H, Yu W (2019) Contrastive-regulated CNN in the Complex domain: a method to learn physical scattering signatures from flexible PolSAR images. IEEE Trans Geosci Remote Sens 57(12):10116–10135
Zhao F, Tian M, Xie W, Liu H (2020) A new parallel dual-channel fully convolutional network via semi-supervised FCM for PolSAR image classification. IEEE J Sel Top Appl Earth Obs Remote Sens 13:4493–4505
Zou B, Xu X, Zhang L (2020) Object-based classification of PolSAR images based on spatial and semantic features. IEEE J Sel Top Appl Earth Obs Remote Sens 13:609–619
Author information
Authors and Affiliations
Contributions
Amir Hossein Ghazvinizadeh: Data Assessment and Experiments Discussion.
Maryam Imani: Development of Ideas, Conceptualization, Software, Writing, and Supervision.
Hassan Ghassemian: Review and Supervision.
Corresponding author
Ethics declarations
Ethics approval
Not applicable.
Consent to participate
Not applicable.
Consent for publication
Not applicable.
Competing interests
The authors declare that there is no financial or non-financial interests. There is no conflict of interest.
Additional information
Communicated by: H. Babaie
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Ghazvinizadeh, A.H., Imani, M. & Ghassemian, H. Residual network based on entropy-anisotropy-alpha target decomposition for polarimetric SAR image classification. Earth Sci Inform 16, 357–366 (2023). https://doi.org/10.1007/s12145-023-00944-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12145-023-00944-6