Two Linear Unmixing Algorithms to Recognize Targets Using Supervised Classification and Orthogonal Rotation in Airborne Hyperspectral Images

Abstract

The goal of the paper is to detect pixels that contain targets of known spectra. The target can be present in a sub-or above pixel. Pixels without targets are classified as background pixels. Each pixel is treated via the content of its neighborhood. A pixel whose spectrum is different from its neighborhood is classified as a "suspicious point". In each suspicious point there is a mix of target(s) and background. The main objective in a supervised detection (also called "target detection") is to search for a specific given spectral material (target) in hyperspectral imaging (HSI) where the spectral signature of the target is known a priori from laboratory measurements. In addition, the fractional abundance of the target is computed. To achieve this we present two linear unmixing algorithms that recognize targets with known (given) spectral signatures. The CLUN is based on automatic feature extraction from the target's spectrum. These features separate the target from the background. The ROTU algorithm is based on embedding the spectra space into a special space by random orthogonal transformation and on the statistical properties of the embedded result. Experimental results demonstrate that the targets' locations were extracted correctly and these algorithms are robust and efficient.

Analysis of MODIS LST Compared with WRF Model and in situ Data over the Waimakariri River Basin, Canterbury, New Zealand

“…The linear mixing model assumes that the observed reflectance spectrum of a given pixel is generated by a linear combination of a small number of unique constituent deterministic spectral signatures [43]. This model calculates the final LST values of each pixel based on the fractional abundance of each LC type (or endmember) in that pixel.…”

“…where M is the number of endmembers, a i (i from 1 to M ) is the fractional abundance vector, w is the additive observation noise, x is the value of the pixel after unmixing [43][44][45]. x is calculated through summation of the weighted values of the endmembers (s…”

Unmixing and Target Recognition in Airborne Hyper-Spectral Images

“…Experimental results demonstrate their robustness. This paper is a complementary extension to Averbuch & Zheludev (2012). …”

ℓ0-Norm Sparse Hyperspectral Unmixing Using Arctan Smoothing

“…Hyperspectral remote sensing has a wide range of applications, from food quality inspection to military functions [1][2][3][4][5][6]. The hyperspectral imaging data are collected by means of hyperspectral imaging sensors and contain two-dimensional spatial images over many contiguous bands of high spectral resolution [3,4].…”