EndNet: Sparse AutoEncoder Network for Endmember Extraction and Hyperspectral Unmixing

TL;DR

EndNet introduces a novel autoencoder-based approach for hyperspectral unmixing that incorporates spectral angle distance, a specialized loss function, and sparsity constraints, significantly improving endmember extraction accuracy.

Contribution

The paper presents a new two-stage autoencoder architecture with a unique loss function and spectral angle distance for enhanced hyperspectral unmixing and endmember extraction.

Findings

Outperforms state-of-the-art methods on multiple datasets.

Improves accuracy of endmember spectral signature estimation.

Enhances sparsity and non-linearity modeling in unmixing process.

Abstract

Data acquired from multi-channel sensors is a highly valuable asset to interpret the environment for a variety of remote sensing applications. However, low spatial resolution is a critical limitation for previous sensors and the constituent materials of a scene can be mixed in different fractions due to their spatial interactions. Spectral unmixing is a technique that allows us to obtain the material spectral signatures and their fractions from hyperspectral data. In this paper, we propose a novel endmember extraction and hyperspectral unmixing scheme, so called \textit{EndNet}, that is based on a two-staged autoencoder network. This well-known structure is completely enhanced and restructured by introducing additional layers and a projection metric (i.e., spectral angle distance (SAD) instead of inner product) to achieve an optimum solution. Moreover, we present a novel loss function that is composed of a Kullback-Leibler divergence term with SAD similarity and additional penalty terms to improve the sparsity of the estimates. These modifications enable us to set the common properties of endmembers such as non-linearity and sparsity for autoencoder networks. Lastly, due to the stochastic-gradient based approach, the method is scalable for large-scale data and it can be accelerated on Graphical Processing Units (GPUs). To demonstrate the superiority of our proposed method, we conduct extensive experiments on several well-known datasets. The results confirm that the proposed method considerably improves the performance compared to the state-of-the-art techniques in literature.