Abstract
Endmember extraction algorithms (EEAs) are among the most commonly discussed types of hyperspectral image processing in the past three decades. This article proposes a spatial energy prior constrained maximum simplex volume (SENMAV) approach for spatial-spectral endmember extraction of hyperspectral images. SENMAV investigates the spatial information from the perspective of the spatial energy prior of a Markov random field (MRF), which is used as a regularization term of the traditional maximum volume simplex model to simultaneously constrain the selection of the endmembers in both the spatial and spectral viewpoints. This article sheds new light on spatial-spectral-based EEAs, as SENMAV well balances the tradeoff between endmember extraction accuracy and spatial attribute requirements of endmembers. Based on the spectral angle distance and root-mean-square error, experimental results on both synthetic and real hyperspectral datasets indicate that the proposed approach significantly improves the endmember extraction performance over current state-of-the-art spatial-spectral-based EEAs.
Highlights
I F THE spatial resolution of a hyperspectral sensor is coarser than the scale of spatial heterogeneity of the ground surface, a mixture of disparate substances is inevitably contained in a pixel [1], [2]
Several experiments conducted on both synthetic and real hyperspectral datasets indicate that the proposed approach significantly improves upon current state-of-the-art Endmember extraction algorithms (EEAs)
We proposed a spatial energy constrained maximum simplex volume approach, SENMAV, for spatial-spectral endmember extraction
Summary
I F THE spatial resolution of a hyperspectral sensor is coarser than the scale of spatial heterogeneity of the ground surface, a mixture of disparate substances is inevitably contained in a pixel [1], [2]. Preliminary work in this field focused primarily on the PPI [12], in which entire spectral vectors are projected onto a large number of randomly generated skewers, and the number of times spectral vectors are found to have extreme projection values are used to determine desired endmembers. It may be difficult for the PPI to identify a final list of endmembers; it is generally used for preprocessing to obtain a set of endmember candidates. This is based on two important facts: the endmembers are the vertices of a simplex; and the affine transformation of a simplex is a simplex
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
