Recursive Band Processing of Automatic Target Generation Process for Finding Unsupervised Targets in Hyperspectral Imagery

Abstract

Automatic target generation process (ATGP) has been widely used for unsupervised target detection. However, as designed, it detects targets using full-band information. Unfortunately, on many occasions, various targets can be detected using varying bands, and ATGP can only provide one-shot target detection with all bands being used. This paper develops a new approach which can implement ATGP bandwise in a progressive manner, called progressive band processing of ATGP (PBP-ATGP) so that ATGP can be carried out band by band. Since PBP-ATGP must repeatedly implement orthogonal projections, recursive equations are further derived for PBP-ATGP, to be called recursive band processing of ATGP (RBP-ATGP) which can implement PBP-ATGP recursively. As a result, many advantages can be benefited from RBP-ATGP. Most importantly, RBP-ATGP can generate 3-D interband progressive profiles from band to band that can be used for progressive target detection, a task for which no target detection techniques using full-band information can provide.Index Terms-Automatic target generation process (ATGP), progressive band processing of ATGP (PBP-ATGP), recursive band processing of ATGP (RBP-ATGP).

Improving hyperspectral sub-pixel target detection in multiple target signatures using a revised replacement signal model

“…The Automatic Target Generation Procedure (ATGP) is an unsupervised endmember extraction method in the target detection task, where can provide more accurate initial points to identify endmembers (Ren & Chang, 2003). Compared to conventional supervised and unsupervised endmember extraction approaches, such as the Pixel Purity Index (PPI) that require a very large number of skewers to find maximal/minimal orthogonal projections (Chang & Li, 2016), ATGP method requires less prior information to extract pure pixel vectors as the endmember spectrum from the hyperspectral data cube (Cao et al, 2018). ATGP method works by iterative orthogonal projections of the hyperspectral data cube then finding the largest magnitude vector in a sequence of orthogonal projection subspaces (Q.…”

An Endmember Initialization Scheme for Nonnegative Matrix Factorization and Its Application in Hyperspectral Unmixing

“…To evaluate the computational efficiency of the particular algorithm, the computing time was often used as an important measure in many related studies [35]. The computational efficiency of an algorithm can be defined as a numerical function T(n): time versus the input size n. In this study, since the input data are the same, we used the average computing time (in seconds) of each algorithm's application on synthetic data, the Berlin HyMap image, and Hyperion image to evaluate their computational efficiency.…”

“…Further studies still need to be done to verify their applicability in solving the mixed pixel problem of a hyperspectral image. Compared to traditional supervised endmember extraction methods, such as the pixel purity index (PPI), ATGP requires less prior information to extract pure pixel vectors as the endmember spectrum from the target image [35]. Moreover, most of the ATGP-generated target pixels turn out to be endmembers [36].…”

A Hyperspectral Image Classification Method Using Multifeature Vectors and Optimized KELM

“…Liu et al [14] proposed a new semisupervised active learning approach. Chang et al [15] proposed a new approach which can implement automatic target generation process bandwise in a progressive manner. Zhong et al [16] proposed a new spectralspatial approach, called spectralspatial feedback close network system.…”