Full-Text Search:
Home|About CNKI|User Service|中文
Add to Favorite Get Latest Update

Study on the Relationships Between Endmember Variance and Decomposition Accuracy of Mixture Pixel

WU Bo①,②,ZHOU Xiao-cheng①,②,ZHAO Yin-di③(①Key lab of Data Mining and Information Sharing of Ministry of Education,Fuzhou University;②Spatial Information Research Center of Fujian Province,Fuzhou University,Fuzhou,350002;③School of Environment Science and Spatial Informatics,China Unviersity of Mining and Technology,Xuzhou 221116,P.R.China).  
The error analysis of linear spectral mixture model based on error propagation law and value simulation has investigated to exposure their relationships.And the relationship between constrained least square unmixed accuracy and within endmember variances was analyzed with simulation data.The error propagation law shows the abundance estimation error can be reduced and hence improve the unmixed accuracy by reducing within endmember variances and increasing between endmember variances.The propagation law also exposures that less selection of endmember would lead to blunder model error,but over selection of endmember is still unbiased estimation of abundances.Suggestions for improving abundance estimation of linear spectral mixture model are then proposed according to the theory deduction.
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©CNKI All Rights Reserved