Abstract
Hyperspectral unmixing is a crucial task for hyperspectral images (HSIs) processing, which estimates the proportions of constituent materials of a mixed pixel. Usually, the mixed pixels can be approximated using a linear mixing model. Since each material only occurs in a few pixels in real HSI, sparse nonnegative matrix factorization (NMF), and its extensions are widely used as solutions. Some recent works assume that materials are distributed in certain structures, which can be added as constraints to sparse NMF model. However, they only consider the spatial distribution within a local neighborhood and define the distribution structure manually, while ignoring the real distribution of materials that is diverse in different images. In this article, we propose a new unmixing method that learns a subspace structure from the original image and incorporate it into the sparse NMF framework to promote unmixing performance. Based on the self-representation property of data points lying in the same subspace, the learned subspace structure can indicate the global similar graph of pixels that represents the real distribution of materials. Then the similar graph is used as a robust global spatial prior which is expected to be maintained in the decomposed abundance matrix. The experiments conducted on both simulated and real-world HSI datasets demonstrate the superior performance of our proposed method.
Highlights
H YPERSPECTRAL image (HSI) analysis [1]–[5] is one of the fastest-growing technologies in recent years
We propose a new method aimed at incorporating the subspace structure regularization into the sparse nonnegative matrix factorization (NMF)-based unmixing process
1) We propose a new hyperspectral unmixing (HU) method which learns the subspace structure of material reflectance to capture the global correlation of all pixels
Summary
H YPERSPECTRAL image (HSI) analysis [1]–[5] is one of the fastest-growing technologies in recent years. The second type of constraint incorporates information concerning the spatial distribution into abundance estimation, and has proved useful in improving the unmixing results This is due to the fact that endmembers are distributed to form coherent geometric structures, and two correlated pixels usually have similar fractional abundances for the same endmembers. The spatial distribution information can be captured by the subspace structure [43] This represents the global distribution of the materials but can be learned from the corresponding image. Motivated by this fact, we propose a new method aimed at incorporating the subspace structure regularization into the sparse NMF-based unmixing process.
Sign-in/Register to view highlights & summary 
Published Version (
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