Automatic Target Detection for Sparse Hyperspectral Images

TL;DR

This paper introduces a novel hyperspectral target detection method that leverages a modified RPCA to separate targets from background without needing prior background models, showing effectiveness in real experiments.

Contribution

A new target detector based on a modified RPCA approach that is distributionally free, background-independent, and effective in large dimensions.

Findings

Effective detection of targets in hyperspectral images.

Robust performance without background dictionary.

Works well when targets match surroundings.

Abstract

In this work, a novel target detector for hyperspectral imagery is developed. The detector is independent on the unknown covariance matrix, behaves well in large dimensions, distributional free, invariant to atmospheric effects, and does not require a background dictionary to be constructed. Based on a modification of the robust principal component analysis (RPCA), a given hyperspectral image (HSI) is regarded as being made up of the sum of a low-rank background HSI and a sparse target HSI that contains the targets based on a pre-learned target dictionary specified by the user. The sparse component is directly used for the detection, that is, the targets are simply detected at the non-zero entries of the sparse target HSI. Hence, a novel target detector is developed, which is simply a sparse HSI generated automatically from the original HSI, but containing only the targets with the background is suppressed. The detector is evaluated on real experiments, and the results of which demonstrate its effectiveness for hyperspectral target detection especially when the targets are well matched to the surroundings.