Riemannian Complex Matrix Convolution Network for PolSAR Image Classification

TL;DR

This paper introduces a novel Riemannian complex matrix convolution network that directly models the structure of PolSAR data in Riemannian space, leading to improved classification performance over existing methods.

Contribution

It pioneers the use of Riemannian geometry for complex matrix convolution in PolSAR classification, preserving data structure and channel correlation.

Findings

Outperforms state-of-the-art methods on real PolSAR datasets.

Effectively learns class-specific features with reduced computation time.

Demonstrates superior accuracy across different sensors and bands.

Abstract

Recently, deep learning methods have achieved superior performance for Polarimetric Synthetic Aperture Radar(PolSAR) image classification. Existing deep learning methods learn PolSAR data by converting the covariance matrix into a feature vector or complex-valued vector as the input. However, all these methods cannot learn the structure of complex matrix directly and destroy the channel correlation. To learn geometric structure of complex matrix, we propose a Riemannian complex matrix convolution network for PolSAR image classification in Riemannian space for the first time, which directly utilizes the complex matrix as the network input and defines the Riemannian operations to learn complex matrix's features. The proposed Riemannian complex matrix convolution network considers PolSAR complex matrix endowed in Riemannian manifold, and defines a series of new Riemannian convolution, ReLu and LogEig operations in Riemannian space, which breaks through the Euclidean constraint of conventional networks. Then, a CNN module is appended to enhance contextual Riemannian features. Besides, a fast kernel learning method is developed for the proposed method to learn class-specific features and reduce the computation time effectively. Experiments are conducted on three sets of real PolSAR data with different bands and sensors. Experiments results demonstrates the proposed method can obtain superior performance than the state-of-the-art methods.