A parallel computing technique for complete modular eigenspace feature extraction of hyperspectral images

Yang Lang Chang, Jyh Perng Fang, Jia Pei Huang, Chun Chieh Lin, Hsuan Ren, Wen Yew Liang

研究成果: 書貢獻/報告類型會議論文篇章同行評審

2 引文 斯高帕斯(Scopus)

摘要

In this paper, we present a parallel computing technique for the feature extraction of hyperspectral images. The approach is based on the complete modular eigenspace (CME) scheme, which was designed to extract the simplest and most efficient feature modules by a newly defined multi-dimensional correlation matrix to optimize the modular eigenspace for high-dimensional datasets. The CME feature extraction scheme improves the performance of feature extraction by modifying the correlation coefficient operations. The proposed parallel CME (PCME) scheme is introduced to reduce the computational load of CME feature extraction using the parallel computing technique. It is implemented by parallel virtual machine (PVM) to solve the huge matrix problems of CME feature extraction. The performance of the proposed method is evaluated by applying to hyperspectral images of MODIS/ASTER (MASTER) airborne simulator during the Paerim II project The experiments demonstrate the proposed PCME approach is an effective scheme not only for the feature extraction but also for the band selection of high-dimensional datasets. It can improve the precision of hyperspectral image classification compared to conventional multispectral classification schemes.

原文???core.languages.en_GB???
主出版物標題2006 IEEE International Geoscience and Remote Sensing Symposium, IGARSS
發行者Institute of Electrical and Electronics Engineers Inc.
頁面952-955
頁數4
ISBN(列印)0780395107, 9780780395107
DOIs
出版狀態已出版 - 2006
事件2006 IEEE International Geoscience and Remote Sensing Symposium, IGARSS - Denver, CO, United States
持續時間: 31 7月 20064 8月 2006

出版系列

名字International Geoscience and Remote Sensing Symposium (IGARSS)

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???2006 IEEE International Geoscience and Remote Sensing Symposium, IGARSS
國家/地區United States
城市Denver, CO
期間31/07/064/08/06

指紋

深入研究「A parallel computing technique for complete modular eigenspace feature extraction of hyperspectral images」主題。共同形成了獨特的指紋。

引用此