Polarimetric Multipath Convolutional Neural Network for PolSAR Image Classification
- 5 May 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 60 (01962892) , 1-18
Abstract
Scatter targets of complex land covers in polarimetric synthetic aperture radar (PolSAR) images are often randomly oriented and cause randomly fluctuating echoes, which brings a challenge to PolSAR image classification. Therefore, many existing methods have alleviated this problem through orientation compensation. However, there are still two obstacles that limit the improvement of classification accuracy. On the one hand, generally, these methods process PolSAR images with fixed polarization rotation angles, which is experience-dependent and inflexible. On the other hand, for the different land covers of a PolSAR image, the existing methods do not consider these rotation angles separately. For the first obstacle, we design a group of convolution kernels called polarization rotation kernels (PRKs) and utilize them to build the polarimetric convolutional neural network (CNN) (PolCNN). The PolCNN is the base network of our final model, and it can learn polarization rotation angles adaptively. For the second obstacle, we extend the PolCNN into a multipath structure, the final model polarimetric multipath CNN (PolMPCNN). The polarization rotation angles of different land covers are directly related to the networks of different paths within the PolMPCNN. Furthermore, we also put forward the two-scale sampling and the stagewise training algorithm in order that our PolMPCNN can fit different scales of PolSAR targets and pays more attention to difficult training samples. Experiments on real PolSAR images show that the proposed model achieves the best classification results with an extremely low sampling rate of 0.1%.Keywords
Funding Information
- State Key Program of National Natural Science of China (61836009)
- National Natural Science Foundation of China (62076192)
- Key Research and Development Program in Shaanxi Province of China (2019ZDLGY03-06)
- Program for Cheung Kong Scholars and Innovative Research Team in University (IRT_15R53)
- the Fund for Foreign Scholars in University Research and Teaching Programs (B07048)
- Key Scientific Technological Innovation Research Project by Ministry of Education
- National Key Research and Development Program of China
- CAAI-Huawei MindSpore Open Fund
This publication has 48 references indexed in Scilit:
- An Adaptive General Four-Component Scattering Power Decomposition With Unitary Transformation of Coherency Matrix (AG4U)IEEE Geoscience and Remote Sensing Letters, 2015
- Improved POLSAR Image Classification by the Use of Multi-Feature CombinationRemote Sensing, 2015
- Uniform Polarimetric Matrix Rotation Theory and Its ApplicationsIEEE Transactions on Geoscience and Remote Sensing, 2013
- Polarimetric SAR speckle filtering and its implication for classificationIEEE Transactions on Geoscience and Remote Sensing, 1999
- Unsupervised classification using polarimetric decomposition and the complex Wishart classifierIEEE Transactions on Geoscience and Remote Sensing, 1999
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- A review of target decomposition theorems in radar polarimetryIEEE Transactions on Geoscience and Remote Sensing, 1996
- Symmetrization of cross-polarized responses in polarimetric radar images using reciprocityIEEE Transactions on Geoscience and Remote Sensing, 1993
- Speckle analysis and smoothing of synthetic aperture radar imagesComputer Graphics and Image Processing, 1981
- A Coefficient of Agreement for Nominal ScalesEducational and Psychological Measurement, 1960