多變數轉化偵測法(MAD)應用於多光譜影像 變遷偵測之研究;A Study of Change Detection in Multi-spectral Imagery Using Multivariate Alteration Detection(MAD)

NCUIR > College of Earth Sciences > Graduate Institute of Space Science > Department of Earth Sciences > Item 987654321/5209

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/5209

Title:	多變數轉化偵測法(MAD)應用於多光譜影像變遷偵測之研究;A Study of Change Detection in Multi-spectral Imagery Using Multivariate Alteration Detection(MAD)
Authors:	洪志賢;Chih-Hsien Hung
Contributors:	太空科學研究所
Keywords:	典型相關分析;變遷偵測;主成分分析;change detection;canonical correlation analysis;principal component analysis
Date:	2005-06-20
Issue Date:	2009-09-22 09:47:11 (UTC+8)
Publisher:	國立中央大學圖書館
Abstract:	最簡單的變遷偵測方式為影像相減法，係將前、後期影像相對應像元相減，得灰度值為-255~255的差值影像，差值影像中，灰度值接近零的像元視為無變遷，接近-255或255的像元視為變遷。本研究中由於使用多光譜影像，毎個波段都包含了資訊，為了將全部波段的資訊結合起來，會將差值影像做主軸的轉換。傳統主軸轉換是使用差值影像的共變異矩陣所進行的主成分分析(Principal Component Analysis)。本論文中使用多變數轉化偵測法(Multivariate Alteration Detection)，以典型相關分析(Canonical Correlations Analysis)為基礎，於主軸轉換時，考慮了前、後期影像之間的交叉共變異矩陣。而此方法的特色在於具有線性轉換的不變性，相當於自動做了相對的輻測校正。再以轉換後影像，利用卡方統計檢定法(Chi-Square Test)，判斷變遷區域，使變遷偵測的結果能更加接近實際的變遷。 When analyzing changes in panchromatic images takenat different points in time, it is coustomary to analyze the difference between two images. Areas with little or no change have zero or low absolute values, and areaas with large changes have large absolute values in the difference image. If our image data gave more than two channels, it is difficult to visualize changes in all channels simultaneously. To overcome this problem and to collect information on change, linear transformations of the image data can be considered. Traditionally, we make linear transformation by using principal componint analysis by the covariance matrix of difference between two images. Therefore, we magelinear transformation by applying multivarite alteration detection(MAD) by cross-matrix between two images. The property of the multivarite alteration detection transformation is the linear scale invariance. So, if we use MAD, preprocessing by linear radiometric normalization is superfluous. To detect the change areas by Chi-Square test, and the major effectiveness fo changes is relative to material, not seasonal.
Appears in Collections:	[Graduate Institute of Space Science] Department of Earth Sciences

Files in This Item:

File	Size	Format

社群 sharing

Loading...