Fast Endmember Extraction for Massive Hyperspectral Sensor Data on GPUs

Hyperspectral imaging sensor becomes increasingly important in multisensor collaborative observation. The spectral mixture problem seriously influences the efficiency of hyperspectral data exploitation, and endmember extraction is one of the key issues. Due to the high computational cost of algorith...

Full description

Saved in:
Bibliographic Details
Main Authors: Zebin Wu, Shun Ye, Jie Wei, Zhihui Wei, Le Sun, Jianjun Liu
Format: Article
Language:English
Published: Wiley 2013-10-01
Series:International Journal of Distributed Sensor Networks
Online Access:https://doi.org/10.1155/2013/217180
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832553253219336192
author Zebin Wu
Shun Ye
Jie Wei
Zhihui Wei
Le Sun
Jianjun Liu
author_facet Zebin Wu
Shun Ye
Jie Wei
Zhihui Wei
Le Sun
Jianjun Liu
author_sort Zebin Wu
collection DOAJ
description Hyperspectral imaging sensor becomes increasingly important in multisensor collaborative observation. The spectral mixture problem seriously influences the efficiency of hyperspectral data exploitation, and endmember extraction is one of the key issues. Due to the high computational cost of algorithm and massive quantity of the hyperspectral sensor data, high-performance computing is extremely demanded for those scenarios requiring real-time response. A method of parallel optimization for the well-known N-FINDR algorithm on graphics processing units (NFINDR-GPU) is proposed to realize fast endmember extraction for massive hyperspectral sensor data in this paper. The implements of the proposed method are described and evaluated using compute unified device architecture (CUDA) based on NVIDA Quadra 600 and Telsa C2050. Experimental results show the effectiveness of NFINDR-GPU. The parallel algorithm is stable for different image sizes, and the average speedup is over thirty times on Telsa C2050, which satisfies the real-time processing requirements.
format Article
id doaj-art-41ad8f67dd9e430e9b6902d1fbb6d46e
institution Kabale University
issn 1550-1477
language English
publishDate 2013-10-01
publisher Wiley
record_format Article
series International Journal of Distributed Sensor Networks
spelling doaj-art-41ad8f67dd9e430e9b6902d1fbb6d46e2025-02-03T05:54:32ZengWileyInternational Journal of Distributed Sensor Networks1550-14772013-10-01910.1155/2013/217180Fast Endmember Extraction for Massive Hyperspectral Sensor Data on GPUsZebin Wu0Shun Ye1Jie Wei2Zhihui Wei3Le Sun4Jianjun Liu5 Lianyungang Research Institute of NJUST, Lianyungang 222006, China School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China Jiangsu Key Lab of Spectral Imaging and Intelligent Sensing, Nanjing 210094, China School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaHyperspectral imaging sensor becomes increasingly important in multisensor collaborative observation. The spectral mixture problem seriously influences the efficiency of hyperspectral data exploitation, and endmember extraction is one of the key issues. Due to the high computational cost of algorithm and massive quantity of the hyperspectral sensor data, high-performance computing is extremely demanded for those scenarios requiring real-time response. A method of parallel optimization for the well-known N-FINDR algorithm on graphics processing units (NFINDR-GPU) is proposed to realize fast endmember extraction for massive hyperspectral sensor data in this paper. The implements of the proposed method are described and evaluated using compute unified device architecture (CUDA) based on NVIDA Quadra 600 and Telsa C2050. Experimental results show the effectiveness of NFINDR-GPU. The parallel algorithm is stable for different image sizes, and the average speedup is over thirty times on Telsa C2050, which satisfies the real-time processing requirements.https://doi.org/10.1155/2013/217180
spellingShingle Zebin Wu
Shun Ye
Jie Wei
Zhihui Wei
Le Sun
Jianjun Liu
Fast Endmember Extraction for Massive Hyperspectral Sensor Data on GPUs
International Journal of Distributed Sensor Networks
title Fast Endmember Extraction for Massive Hyperspectral Sensor Data on GPUs
title_full Fast Endmember Extraction for Massive Hyperspectral Sensor Data on GPUs
title_fullStr Fast Endmember Extraction for Massive Hyperspectral Sensor Data on GPUs
title_full_unstemmed Fast Endmember Extraction for Massive Hyperspectral Sensor Data on GPUs
title_short Fast Endmember Extraction for Massive Hyperspectral Sensor Data on GPUs
title_sort fast endmember extraction for massive hyperspectral sensor data on gpus
url https://doi.org/10.1155/2013/217180
work_keys_str_mv AT zebinwu fastendmemberextractionformassivehyperspectralsensordataongpus
AT shunye fastendmemberextractionformassivehyperspectralsensordataongpus
AT jiewei fastendmemberextractionformassivehyperspectralsensordataongpus
AT zhihuiwei fastendmemberextractionformassivehyperspectralsensordataongpus
AT lesun fastendmemberextractionformassivehyperspectralsensordataongpus
AT jianjunliu fastendmemberextractionformassivehyperspectralsensordataongpus