Hyperspectral Target Detection Using a Bilinear Sparse Binary Hypothesis Model

The binary hypothesis testing (BHT) is one of the most important models in hyperspectral target detection (HTD). However, this model is generally based on a linear mixture model (LMM) and might be inaccurate to reflect target and background characterizations in some scenes. This article presents a bilinear sparse target detector (BSTD) by applying the bilinear sparse mixture model (BSMM) to a popular BHT-based detection algorithm termed adaptive matched subspace detector (AMSD), which takes bilinear target–background interaction and sparse abundance into account. Moreover, as AMSD relies heavily on background subspace, we design a robust background subspace construction method. Specifically, we first classify each pixel into noise, border, or other particular instances according to its density, which is measured by jointly spatial–spectral distance. With the coarse classification map, a class-guided automatic background generation (CABG) process is introduced to reliably generate pure background samples. Detection statistics and component analysis on five real-world hyperspectral images verify the effectiveness of our BSTD method.

I. Introduction

Significant progress has been made in the use of hyperspectral remote sensing techniques to recognize various substances of interest in the past few decades. Such technique is termed hyperspectral target detection (HTD), which estimates the probability that the interested target prior is present in each test pixel and has held the researchers’ attention in many engineering applications, such as Earth observation [1], deep space exploration [2], and health hazards recognition [3].