Parallel unmixing of remotely sensed hyperspectral images on commodity graphics processing units

Abstract

SUMMARYHyperspectral imaging instruments are capable of collecting hundreds of images, corresponding to different wavelength channels, for the same area on the surface of the Earth. One of the main problems in the analysis of hyperspectral data cubes is the presence of mixed pixels, which arise when the spatial resolution of the sensor is not enough to separate spectrally distinct materials. Hyperspectral unmixing is one of the most popular techniques to analyze hyperspectral data. It comprises two stages: (i) automatic identification of pure spectral signatures (endmembers) and (ii) estimation of the fractional abundance of each endmember in each pixel. The spectral unmixing process is quite expensive in computational terms, mainly due to the extremely high dimensionality of hyperspectral data cubes. Although this process maps nicely to high performance systems such as clusters of computers, these systems are generally expensive and difficult to adapt to real-time data processing requirements introduced by several applications, such as wildland fire tracking, biological threat detection, monitoring of oil spills, and other types of chemical contamination. In this paper, we develop an implementation of the full hyperspectral unmixing chain on commodity graphics processing units (GPUs). The proposed methodology has been implemented, using the CUDA (compute device unified architecture), and tested on three different GPU architectures: NVidia Tesla C1060, NVidia GeForce GTX 275, and NVidia GeForce 9800 GX2, achieving near real-time unmixing performance in some configurations tested when analyzing two different hyperspectral images, collected over the World Trade Center complex in New York City and the Cuprite mining district in Nevada.

Parallel implementation of a hyperspectral unmixing chain: Graphic processing units versus multi-core processors

“…Since no reference information is available regarding the true abundance fractions of minerals in the AVIRIS Cuprite data, no quantitative experiments were conducted although the obtained mineral maps exhibit similar correlation with regards to previously published maps 4 . These results have been discussed in a previous work [6].…”

Hyperspectral Unmixing Overview: Geometrical, Statistical, and Sparse Regression-Based Approaches

“…Many of these applications require timely responses for swift decisions which depend upon (near) real-time performance of algorithm analysis [218]. Although the role of different types of HPC architectures depends heavily on the considered application, cluster-based parallel computing has been used for efficient information extraction from very large data archives using spectral unmixing technniques [219], while on-board and real-time hardware architectures such as field programmable gate arrays (FPGAs) [220] and graphics processing units (GPUs) [221] have also been used for efficient implementation and exploitation of spectral unmixing techniques. The HPC techniques, together with the recent discovery of theoretically correct methods for parallel Gibbs samplers and further coupled with the potential of the fully stochastic models represents an opportunity for huge advances in multi-modal unmixing.…”

Hyperspectral Remote Sensing Data Analysis and Future Challenges

“…In this case, speedups on the order of 15# were reported. A full spectral unmixing chain comprising the automatic estimation of the number of endmembers, the identification of the endmember signatures, and quantification of endmember fractional abundances has been reported in [182] with speedups superior to 50#. Additional efforts towards real-time and on-board hyperspectral target detection and classification [183], [184] using GPUs have also been recently available.…”