Hyperspectral Detection and Unmixing of Subpixel Target Using Iterative Constrained Sparse Representation

Abstract

With great significance in military and civilian applications, subpixel target detection is of great interest in hyperspectral remote sensing. The subpixel targets usually also need to be unmixed to identify their components. Traditionally, these subpixel targets are first detected and then unmixed to obtain their corresponding abundances. Therefore, target detection and target unmixing are independently performed. However, there are potential relations between these two processes that need to be investigated. In this paper, we integrate these two processes using iterative constrained sparse representation (ICSR). The main idea of this algorithm is that each pixel can be linearly and sparsely represented by the prior target spectra and several background endmembers extracted from its neighborhood. Moreover, the sum-to-one and non-negativity constraints are introduced to ensure the sparse representation coefficients to have physical meaning. Specifically, the background endmembers are automatically extracted from the local background based on an iterative process. Then, the test pixel is represented by these extracted endmembers. Finally, the detection output is determined by the total target abundance and the residuals. The main innovation of this method is, it implements detection and unmixing of subpixel target simultaneously, even if the local background is contaminated by target signals. Experiments conducted on both synthetic and real hyperspectral datasets demonstrate that the proposed detector achieves an outstanding performance on detection and unmixing.

Adaptive Background Endmember Extraction for Hyperspectral Subpixel Object Detection

“…These images play a vital role in providing diagnostic spectral insights that can discriminate between distinct objects [5], rendering them invaluable for detection purposes [6][7][8][9][10][11]. However, owing to the spectral diversity intrinsic to natural substances and the limited spatial resolution of spectral sensors, small-sized objects may only occupy a fraction of an individual pixel, becoming enmeshed within the background [12,13]. Under such circumstances, the spectral signature of a mixed pixel reflects the absorption features corresponding to multiple endmembers, potentially deviating from those of the pure objects.…”

Regularized Tensor Representative Coefficient Model for Hyperspectral Target Detection

“…The sparse representation detection (SRD) algorithms belong to the representative-based model category, which assumes each pixel lies in a subspace that can be sparsely represented by the dictionary, having been successfully applied for TD [12], [13]. Considering the essential of the dictionary construction, Cheng et al [12] proposed a decomposition model (DM) with background dictionary learning (BDL) for hyperspectral TD to recover a satisfactory background.…”

“…Considering the essential of the dictionary construction, Cheng et al [12] proposed a decomposition model (DM) with background dictionary learning (BDL) for hyperspectral TD to recover a satisfactory background. After that, [13] assumes that each pixel can be linearly and sparsely represented by the prior target spectra and several background endmembers extracted from its neighborhood.…”