Abstract
Abstract. Endmember extraction is a process to identify the hidden pure source signals from the mixture. Endmember finding has become increasingly important in hyperspectral data exploitation because endmembers can be used to specify unknown particular spectral classes. This paper evaluates the change detection problem in bi-temporal hyperspectral remote sensing images using the unmixing process. A complete spectral unmixing process contains estimating the number of endmembers, endmember extraction and abundance estimation. Endmember extraction is a vital step in spectral unmixing of hyperspectral images. Hyperspectral change detection by unmixing has the potential to provide subpixel information from hyperspectral images. In this study, four methods including Simplex Identification via variable Splitting and Augmented Lagrangian (SISAL), N-finder algorithm (N-FINDR), Vertex Component Analysis (VCA), and Fast algorithm for linearly Unmixing (FUN) are used to produce multiple change detection maps. This paper explores and compares the performance of these methods in multiple change detection. The empirical results reveal the superiority of the FUN method in providing multiple change map with an overall accuracy of 87% and a kappa coefficient of 0.70.
Highlights
The availability of images acquired on the same geographical area by satellite sensors at different times makes it possible to identify and label possible changes that have occurred on the ground (Bovolo et al, 2007)
Change detection (CD) is one of the most important uses of remote sensing, and it plays a key role in many applications (Jafarzadeh et al, 2019; Liu et al, 2015)
Endmember extraction is a vital step in spectral unmixing of hyperspectral images (HSIs) (Guerra et al, 2015)
Summary
The availability of images acquired on the same geographical area by satellite sensors at different times makes it possible to identify and label possible changes that have occurred on the ground (Bovolo et al, 2007). By the advent of new hyperspectral satellite sensors, hyperspectral images (HSIs) can be obtained by very high spectral resolution and each pixel is generally mixed by a number of materials present in the scene Pixels containing more than one material are called mixed pixels (Arai et al, 2009), in contrast to pure pixels, which only contain one material. To solve this problem, spectral unmixing techniques were developed, aiming to detect the materials (termed endmembers) in the mixed pixels and to estimate their corresponding fractions (termed abundances) (Liu et al, 2016). Endmember extraction is a vital step in spectral unmixing of HSIs (Guerra et al, 2015). Several algorithms have been proposed for the purpose of endmember selection from hyperspectral scenes (Plaza et al, 2004)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
