A Multi-Dimensional Correlation Matrix Feature Extraction Technique for Hyperspectral Images

碩士 === 國立臺北科技大學 === 電機工程系研究所 === 95 === A novel study of feature extraction technique for hyperspectral images of remote sensing is proposed. The method is based on the greedy modular eigenspace (GME) scheme, which was designed to extract the simplest and the most efficient feature modules for high-...

Full description

Bibliographic Details
Main Authors: Yun-Ming Liu, 劉原銘
Other Authors: Jyh-Perng Fang
Format: Others
Language:zh-TW
Published: 2007
Online Access:http://ndltd.ncl.edu.tw/handle/38z36g
id ndltd-TW-095TIT05442064
record_format oai_dc
spelling ndltd-TW-095TIT054420642019-06-27T05:10:22Z http://ndltd.ncl.edu.tw/handle/38z36g A Multi-Dimensional Correlation Matrix Feature Extraction Technique for Hyperspectral Images 多維模組特徵空間方法應用於高維遙測影像特徵萃取 Yun-Ming Liu 劉原銘 碩士 國立臺北科技大學 電機工程系研究所 95 A novel study of feature extraction technique for hyperspectral images of remote sensing is proposed. The method is based on the greedy modular eigenspace (GME) scheme, which was designed to extract the simplest and the most efficient feature modules for high-dimensional datasets. It presents a framework which consists of two algorithms, referred to as multi-dimensional correlation matrix feature extraction (MD-CMFE) and the feature scale uniformity transformation (FSUT). The MD-CMFE scheme, also known as the complete modular eigenspace (CME), can improve the performance of GME feature extraction optimally by modifying the conventional correlation coefficient operations. It is designed to extract features by a new defined three dimensional correlation matrix (3D-CM) to optimize the modular eigenspace, while FSUT is performed to fuse most correlated features from different spectrums associated with different data sources. In this paper, we also present a parallel computing technique for the feature extraction of hyperspectral images. 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 Pacrim II project. The experiments demonstrate the proposed MD-CMFE/FSUT and 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. Jyh-Perng Fang Yang-Lang Chang 方志鵬 張陽郎 2007 學位論文 ; thesis 46 zh-TW
collection NDLTD
language zh-TW
format Others
sources NDLTD
description 碩士 === 國立臺北科技大學 === 電機工程系研究所 === 95 === A novel study of feature extraction technique for hyperspectral images of remote sensing is proposed. The method is based on the greedy modular eigenspace (GME) scheme, which was designed to extract the simplest and the most efficient feature modules for high-dimensional datasets. It presents a framework which consists of two algorithms, referred to as multi-dimensional correlation matrix feature extraction (MD-CMFE) and the feature scale uniformity transformation (FSUT). The MD-CMFE scheme, also known as the complete modular eigenspace (CME), can improve the performance of GME feature extraction optimally by modifying the conventional correlation coefficient operations. It is designed to extract features by a new defined three dimensional correlation matrix (3D-CM) to optimize the modular eigenspace, while FSUT is performed to fuse most correlated features from different spectrums associated with different data sources. In this paper, we also present a parallel computing technique for the feature extraction of hyperspectral images. 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 Pacrim II project. The experiments demonstrate the proposed MD-CMFE/FSUT and 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.
author2 Jyh-Perng Fang
author_facet Jyh-Perng Fang
Yun-Ming Liu
劉原銘
author Yun-Ming Liu
劉原銘
spellingShingle Yun-Ming Liu
劉原銘
A Multi-Dimensional Correlation Matrix Feature Extraction Technique for Hyperspectral Images
author_sort Yun-Ming Liu
title A Multi-Dimensional Correlation Matrix Feature Extraction Technique for Hyperspectral Images
title_short A Multi-Dimensional Correlation Matrix Feature Extraction Technique for Hyperspectral Images
title_full A Multi-Dimensional Correlation Matrix Feature Extraction Technique for Hyperspectral Images
title_fullStr A Multi-Dimensional Correlation Matrix Feature Extraction Technique for Hyperspectral Images
title_full_unstemmed A Multi-Dimensional Correlation Matrix Feature Extraction Technique for Hyperspectral Images
title_sort multi-dimensional correlation matrix feature extraction technique for hyperspectral images
publishDate 2007
url http://ndltd.ncl.edu.tw/handle/38z36g
work_keys_str_mv AT yunmingliu amultidimensionalcorrelationmatrixfeatureextractiontechniqueforhyperspectralimages
AT liúyuánmíng amultidimensionalcorrelationmatrixfeatureextractiontechniqueforhyperspectralimages
AT yunmingliu duōwéimózǔtèzhēngkōngjiānfāngfǎyīngyòngyúgāowéiyáocèyǐngxiàngtèzhēngcuìqǔ
AT liúyuánmíng duōwéimózǔtèzhēngkōngjiānfāngfǎyīngyòngyúgāowéiyáocèyǐngxiàngtèzhēngcuìqǔ
AT yunmingliu multidimensionalcorrelationmatrixfeatureextractiontechniqueforhyperspectralimages
AT liúyuánmíng multidimensionalcorrelationmatrixfeatureextractiontechniqueforhyperspectralimages
_version_ 1719210503212892160