Abstract
Hyperspectral unmixing, which intends to decompose mixed pixels into a collection of endmembers weighted by their corresponding fraction abundances, has been widely utilized for remote sensing image exploitation. Recent studies have revealed that spatial context of pixels is important complemental information for hyperspectral image processing. However, many well-known endmember finding (EF) algorithms identify spectrally pure spectra from hyperspectral images according to spectral information only, resulting in limited accuracy of hyperspectral unmixing application since they ignore spatial distribution or structure information in the image. Therefore, in this article, several novel spatial exploiting (SE) strategies are proposed to improve the performance of the well-known spectral-based EF (sEF) algorithms by integrating spatial information. Three different spatial exploiting strategies are designed to use pixel spatial context, by which the spectral variation of pixels can be alleviated to improve the performance of hyperspectral unmixing. Specifically, in pixel domain, the pixels are linearly reconstructed using their neighbors in which the spatially derived factor to weight the importance of the spectral information is generated using local linear representation and local sparse representation, while in the feature domain, pixels are revised using dominated features of neighboring pixels in singular value decomposition. The proposed spatial exploiting strategies can not only be used as a preprocessing stage to revise pixels for sEF algorithms, but also be used as a postprocessing step to revise endmembers found via sEF algorithms. Finally, experimental results on both synthetic and real hyperspectral datasets demonstrate that the proposed SE strategies can certainly improve the performance of several well-known sEF algorithms, and obtain more accurate unmixing results than several state-of-the-art spatial preprocessing methods.
Highlights
T HE development of imaging sensor technologies has made hyperspectral remote sensing data widely available, providing a large amount of detailed information about the spectral characteristics of the materials that are present in the scene [1]–[3]
We developed several novel spatial exploiting (SE) strategies, which can be utilized as either a preprocessing step or postprocessing step for the traditional spectral-based EF (sEF) algorithms
Three preprocessing SE algorithms based on local linear representation (LLR), local sparse representation (LSR), and singular value decomposition (SVD) are designed, in which each pixel in a hyperspectral image is modified by exploiting its spatial context
Summary
T HE development of imaging sensor technologies has made hyperspectral remote sensing data widely available, providing a large amount of detailed information about the spectral characteristics of the materials that are present in the scene [1]–[3]. Most of the pixels acquired by hyperspectral remote sensors are composed of several inhomogeneous ground objects, which are well known as mixed pixels or mixtures. The phenomenon is caused by low spatial resolution of the sensor, which would combine distinct materials into homogenous or intimate mixture, making it difficult to separate different pure ground objects [4], [5]. The wide presence of mixtures influences the performance of image classification and target recognition, and is an obstacle to quantitative analysis of hyperspectral images [6]. Spectral mixture unmixing (SMU) is proposed to solve such mixed-pixel problems for quantitative analysis of hyperspectral remote sensing images. By assuming the presence of pure pixels in the image, many EF algorithms aim to identify endmembers directly from the image, such as orthogonal subspace projection (OSP) algorithm
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callMore From: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
