Abstract
Spectral unmixing is a vital procedure in hyperspectral remote sensing image exploitation. The linear mixture model has been widely utilized to unmix hyperspectral images by extracting a set of pure spectral signatures, called endmembers in hyperspectral jargon, and estimating their respective fractional abundances in each pixel of the scene. Many algorithms have been proposed to extract endmembers automatically, which is a critical step in the spectral unmixing chain. In recent years, the ant colony optimization (ACO) algorithm has been developed for endmember extraction from hyperspectral data, which was regarded as a combinatorial optimization problem. Although the ACO for endmember extraction (ACOEE) can acquire accurate endmember results, its high computational complexity has limited its application in the hyperspectral data analysis. The GPUs parallel computing technique can be utilized to improve the computational performance of ACOEE, but the architecture of GPUs determines that the ACOEE should be redesigned to take full advantage of computing resources on GPUs. In this paper, a multiple sub-ant-colony-based parallel design of ACOEE was proposed, in which an innovative mechanism of local pheromone for sub-ant-colonies is utilized to enable ACOEE to be preferably executed on the multi-GPU system. The proposed method can avoid much synchronization among different GPUs to affect the computational performance improvement. The experiments on two real hyperspectral datasets demonstrated that the computational performance of ACOEE significantly benefited from the proposed methods.
Highlights
Hyperspectral sensors can acquire hundreds of contiguous spectral bands for the same area, which provide abundant spectral information about the surface of the Earth
The proposed MG-ACO for endmember extraction (ACOEE) algorithm was carried out using CUDA C language, while original ACOEE (O-ACOEE) and G-ACOEE were carried out separately using MATLAB and CUDA C for comparison purposes
This paper proposes a multi-graphic processing units (GPUs)-based parallel design to the ACOEE algorithm aiming at improving its computing performance
Summary
Hyperspectral sensors can acquire hundreds of contiguous spectral bands for the same area, which provide abundant spectral information about the surface of the Earth. High-performance computing based on parallel computing architectures, especially commodity graphic processing units (GPUs), is an effective solution to these high computational complexity problems of hyperspectral endmember extraction algorithms [19,20,21,22,23,24,25,26]. Due to the low computational efficiency, many research works have been devoted to the parallel ACO algorithm based on the parallel technology of the multicore CPU, or the single GPU, or the combination of the two [27,28,29,30] Different from these methods, the most time-consuming task in ACOEE is the calculations of the objective function, e.g., the root-mean-squared error (RMSE) between the remixed image and the original image.
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 callDisclaimer: 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.
