A complete modular eigenspace feature extraction technique for hyperspectral images

Yang Lang Chang, Hsuan Ren

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

A novel study of feature extraction technique for hyperspectral images of remote sensing is proposed. The approach is based on the greedy modular eigenspace (GME) scheme, which was designed to extract the simplest and most efficient feature modules for high-dimensional datasets. It presents a framework for hyperspectral images, which consists of two algorithms, referred to as the complete modular eigenspace (CME) and the feature scale uniformity transformation (FSUT). The CME scheme is introduced to improve the performance of GME feature extraction optimally by modifying the correlation coefficient operations. It is designed to extract features by a new defined multi-dimensional correlation matrix to optimize the modular eigenspace, while FSUT is performed to fuse most correlated features from different spectrums associated with different data sources. The performance of the proposed method is evaluated by applying to hyperspectral images of MODIS/ASTER (MASTER) airborne simulator during the Pacrim II campaign. The experiments demonstrate the proposed CME/FSUT 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25th Anniversary IGARSS 2005
主出版物子標題IEEE International Geoscience and Remote Sensing Symposium
頁面1253-1256
頁數4
DOIs
出版狀態已出版 - 2005
事件2005 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2005 - Seoul, Korea, Republic of
持續時間: 25 7月 200529 7月 2005

出版系列

名字International Geoscience and Remote Sensing Symposium (IGARSS)
2

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

???event.eventtypes.event.conference???2005 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2005
國家/地區Korea, Republic of
城市Seoul
期間25/07/0529/07/05

指紋

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

引用此