Anomaly Detection in Hyperspectral Imagery Based on Low-Rank Representation Incorporating a Spatial Constraint

Kun Tan,Donglei Ma,Yu Chen,Qian Du,Zengfu Hou

doi:10.3390/rs11131578

Kun Tan, Donglei Ma + Show 3 more

Open Access

https://doi.org/10.3390/rs11131578

Copy DOI

Abstract

Hyperspectral imagery contains abundant spectral information. Each band contains some specific characteristics closely related to target objects. Therefore, using these characteristics, hyperspectral imagery can be used for anomaly detection. Recently, with the development of compressed sensing, low-rank-representation-based methods have been applied to hyperspectral anomaly detection. In this study, novel low-rank representation methods were developed for anomaly detection from hyperspectral images based on the assumption that hyperspectral pixels can be effectively decomposed into a low-rank component (for background) and a sparse component (for anomalies). In order to improve detection performance, we imposed a spatial constraint on the low-rank representation coefficients, and single or multiple local window strategies was applied to smooth the coefficients. Experiments on both simulated and real hyperspectral datasets demonstrated that the proposed approaches can effectively improve hyperspectral anomaly detection performance.

Highlights

Due to the high spectral resolution and abundant spectral information in a large number of spectral bands, hyperspectral image (HSI) data have been widely used to distinguish different targets on the ground
When the entire image is considered for background modeling, this is known as the global RX detector (GRXD)
We developed two novel anomaly detection methods based on single or multiple local windows and the low-rank representation sum-to-one model (SLW_LRRSTO/MLW_LRRSTO)

Summary

Introduction

Due to the high spectral resolution and abundant spectral information in a large number of spectral bands, hyperspectral image (HSI) data have been widely used to distinguish different targets on the ground. If the RX detector estimates the background using local statistics, it is referred to as the local RX detector (LRXD) [6] Neither of these two algorithms can exclude the influence of anomalous features on covariance. Some enhanced RX-based algorithms such as the weighted-RXD (WRXD) [10] and the linear filter-based RXD [10] were proposed. They aim at increasing the probability of anomaly detection by improving the estimation of background statistics to exclude the influence of anomalous features on covariance

Methods

Discussion

Conclusion