Multi-GPU Based Parallel Design of the Ant Colony Optimization Algorithm for Endmember Extraction from Hyperspectral Images
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 fract...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/3/598 |
| _version_ | 1811304092298903552 |
|---|---|
| author | Jianwei Gao Yi Sun Bing Zhang Zhengchao Chen Lianru Gao Wenjuan Zhang |
| author_facet | Jianwei Gao Yi Sun Bing Zhang Zhengchao Chen Lianru Gao Wenjuan Zhang |
| author_sort | Jianwei Gao |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-13T08:00:58Z |
| format | Article |
| id | doaj.art-1059b55120984ab2a330f562daad2fbb |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-13T08:00:58Z |
| publishDate | 2019-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-1059b55120984ab2a330f562daad2fbb2022-12-22T02:55:17ZengMDPI AGSensors1424-82202019-01-0119359810.3390/s19030598s19030598Multi-GPU Based Parallel Design of the Ant Colony Optimization Algorithm for Endmember Extraction from Hyperspectral ImagesJianwei Gao0Yi Sun1Bing Zhang2Zhengchao Chen3Lianru Gao4Wenjuan Zhang5Institute of Remote Sensing and Digital Earth (RADI), Chinese Academy of Sciences (CAS), Beijing 100094, ChinaChina Academy of Space Technology (CAST), Beijing 100081, ChinaInstitute of Remote Sensing and Digital Earth (RADI), Chinese Academy of Sciences (CAS), Beijing 100094, ChinaInstitute of Remote Sensing and Digital Earth (RADI), Chinese Academy of Sciences (CAS), Beijing 100094, ChinaInstitute of Remote Sensing and Digital Earth (RADI), Chinese Academy of Sciences (CAS), Beijing 100094, ChinaInstitute of Remote Sensing and Digital Earth (RADI), Chinese Academy of Sciences (CAS), Beijing 100094, ChinaSpectral 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.https://www.mdpi.com/1424-8220/19/3/598hyperspectral imagesendmember extractionmulti-GPUant colony optimization (ACO)parallel computing |
| spellingShingle | Jianwei Gao Yi Sun Bing Zhang Zhengchao Chen Lianru Gao Wenjuan Zhang Multi-GPU Based Parallel Design of the Ant Colony Optimization Algorithm for Endmember Extraction from Hyperspectral Images Sensors hyperspectral images endmember extraction multi-GPU ant colony optimization (ACO) parallel computing |
| title | Multi-GPU Based Parallel Design of the Ant Colony Optimization Algorithm for Endmember Extraction from Hyperspectral Images |
| title_full | Multi-GPU Based Parallel Design of the Ant Colony Optimization Algorithm for Endmember Extraction from Hyperspectral Images |
| title_fullStr | Multi-GPU Based Parallel Design of the Ant Colony Optimization Algorithm for Endmember Extraction from Hyperspectral Images |
| title_full_unstemmed | Multi-GPU Based Parallel Design of the Ant Colony Optimization Algorithm for Endmember Extraction from Hyperspectral Images |
| title_short | Multi-GPU Based Parallel Design of the Ant Colony Optimization Algorithm for Endmember Extraction from Hyperspectral Images |
| title_sort | multi gpu based parallel design of the ant colony optimization algorithm for endmember extraction from hyperspectral images |
| topic | hyperspectral images endmember extraction multi-GPU ant colony optimization (ACO) parallel computing |
| url | https://www.mdpi.com/1424-8220/19/3/598 |
| work_keys_str_mv | AT jianweigao multigpubasedparalleldesignoftheantcolonyoptimizationalgorithmforendmemberextractionfromhyperspectralimages AT yisun multigpubasedparalleldesignoftheantcolonyoptimizationalgorithmforendmemberextractionfromhyperspectralimages AT bingzhang multigpubasedparalleldesignoftheantcolonyoptimizationalgorithmforendmemberextractionfromhyperspectralimages AT zhengchaochen multigpubasedparalleldesignoftheantcolonyoptimizationalgorithmforendmemberextractionfromhyperspectralimages AT lianrugao multigpubasedparalleldesignoftheantcolonyoptimizationalgorithmforendmemberextractionfromhyperspectralimages AT wenjuanzhang multigpubasedparalleldesignoftheantcolonyoptimizationalgorithmforendmemberextractionfromhyperspectralimages |