Hyperspectral Unmixing with 3D Convolutional Sparse Coding and Projected Simplex Volume Maximization

TL;DR

This paper introduces a novel hyperspectral unmixing method using a 3D convolutional sparse coding network within an autoencoder framework, combined with a projected simplex volume maximization for endmember estimation, demonstrating superior performance on multiple datasets.

Contribution

The paper proposes a new 3D convolutional sparse coding network for hyperspectral unmixing, integrating deep algorithm unrolling and a novel endmember initialization method, advancing the state-of-the-art.

Findings

Outperforms existing hyperspectral unmixing methods on real datasets.

Effectively captures spectral and spatial features through 3D CSC.

Demonstrates robustness across different SNR levels.

Abstract

Hyperspectral unmixing (HSU) aims to separate each pixel into its constituent endmembers and estimate their corresponding abundance fractions. This work presents an algorithm-unrolling-based network for the HSU task, named the 3D Convolutional Sparse Coding Network (3D-CSCNet), built upon a 3D CSC model. Unlike existing unrolling-based networks, our 3D-CSCNet is designed within the powerful autoencoder (AE) framework. Specifically, to solve the 3D CSC problem, we propose a 3D CSC block (3D-CSCB) derived through deep algorithm unrolling. Given a hyperspectral image (HSI), 3D-CSCNet employs the 3D-CSCB to estimate the abundance matrix. The use of 3D CSC enables joint learning of spectral and spatial relationships in the 3D HSI data cube. The estimated abundance matrix is then passed to the AE decoder to reconstruct the HSI, and the decoder weights are extracted as the endmember matrix. Additionally, we propose a projected simplex volume maximization (PSVM) algorithm for endmember estimation, and the resulting endmembers are used to initialize the decoder weights of 3D-CSCNet. Extensive experiments on three real datasets and one simulated dataset with three different signal-to-noise ratio (SNR) levels demonstrate that our 3D-CSCNet outperforms state-of-the-art methods.