Semiblind Hyperspectral Unmixing in the Presence of Spectral Library Mismatches

07/07/2015
by   Xiao Fu, et al.
0

The dictionary-aided sparse regression (SR) approach has recently emerged as a promising alternative to hyperspectral unmixing (HU) in remote sensing. By using an available spectral library as a dictionary, the SR approach identifies the underlying materials in a given hyperspectral image by selecting a small subset of spectral samples in the dictionary to represent the whole image. A drawback with the current SR developments is that an actual spectral signature in the scene is often assumed to have zero mismatch with its corresponding dictionary sample, and such an assumption is considered too ideal in practice. In this paper, we tackle the spectral signature mismatch problem by proposing a dictionary-adjusted nonconvex sparsity-encouraging regression (DANSER) framework. The main idea is to incorporate dictionary correcting variables in an SR formulation. A simple and low per-iteration complexity algorithm is tailor-designed for practical realization of DANSER. Using the same dictionary correcting idea, we also propose a robust subspace solution for dictionary pruning. Extensive simulations and real-data experiments show that the proposed method is effective in mitigating the undesirable spectral signature mismatch effects.

READ FULL TEXT

page 19

page 21

page 22

research
02/26/2019

A Dictionary-Based Generalization of Robust PCA Part II: Applications to Hyperspectral Demixing

We consider the task of localizing targets of interest in a hyperspectra...
research
08/06/2013

Spatial-Aware Dictionary Learning for Hyperspectral Image Classification

This paper presents a structured dictionary-based model for hyperspectra...
research
02/26/2019

Target-based Hyperspectral Demixing via Generalized Robust PCA

Localizing targets of interest in a given hyperspectral (HS) image has a...
research
11/03/2017

Distributed Unmixing of Hyperspectral Data With Sparsity Constraint

Spectral unmixing (SU) is a data processing problem in hyperspectral rem...
research
10/29/2018

An Augmented Linear Mixing Model to Address Spectral Variability for Hyperspectral Unmixing

Hyperspectral imagery collected from airborne or satellite sources inevi...
research
04/06/2020

Detecting the Saliency of Remote Sensing Images Based on Sparse Representation of Contrast-weighted Atoms

Object detection is an important task in remote sensing (RS) image analy...
research
09/20/2019

Deep Generative Models for Library Augmentation in Multiple Endmember Spectral Mixture Analysis

Multiple Endmember Spectral Mixture Analysis (MESMA) is one of the leadi...

Please sign up or login with your details

Forgot password? Click here to reset