| Title: | Multi-GPU Based Parallel Design of the Ant Colony Optimization Algorithm for Endmember Extraction from Hyperspectral Images |
| Author(s): | Gao J; Sun Y; Zhang B; Chen Z; Gao L; Zhang W; |
| Address: | "Institute of Remote Sensing and Digital Earth (RADI), Chinese Academy of Sciences (CAS), Beijing 100094, China. gaojw@radi.ac.cn. China Academy of Space Technology (CAST), Beijing 100081, China. zoesun99@126.com. Institute of Remote Sensing and Digital Earth (RADI), Chinese Academy of Sciences (CAS), Beijing 100094, China. zb@radi.ac.cn. University of Chinese Academy of Sciences, Beijing 100049, China. zb@radi.ac.cn. Institute of Remote Sensing and Digital Earth (RADI), Chinese Academy of Sciences (CAS), Beijing 100094, China. chenzc@radi.ac.cn. Institute of Remote Sensing and Digital Earth (RADI), Chinese Academy of Sciences (CAS), Beijing 100094, China. gaolr@radi.ac.cn. College of Computer Science and Software Engineering, Computer Vision Research Institute, Shenzhen University, Shenzhen 518060, China. gaolr@radi.ac.cn. Institute of Remote Sensing and Digital Earth (RADI), Chinese Academy of Sciences (CAS), Beijing 100094, China. zhangwj@radi.ac.cn" |
| ISSN/ISBN: | 1424-8220 (Electronic) 1424-8220 (Linking) |
| 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" |
| Keywords: | "Algorithms Image Interpretation, Computer-Assisted/*methods Linear Models Pheromones/metabolism Research Design ant colony optimization (ACO) endmember extraction hyperspectral images multi-GPU parallel computing;" |
| Notes: | "MedlineGao, Jianwei Sun, Yi Zhang, Bing Chen, Zhengchao Gao, Lianru Zhang, Wenjuan eng Research on the method and parallel implementation of endmember extraction from hyperspectral image based on firefly algorithm/Director Foundation for Young Scientists of Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences/ 2014LDE004/Open Research Fund of Key Laboratory of Digital Earth Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences/ 91638201, 41571349, 11571031/National Natural Science Foundation of China/ 2016YFB0500304/National Key Research and Development Program of China/ XDA19080302/Strategic Priority Research Program of the Chinese Academy of Sciences/ Switzerland 2019/02/03 Sensors (Basel). 2019 Jan 31; 19(3):598. doi: 10.3390/s19030598" |
