<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0//ENhttp://www.w3.org/TR/REC-html40/strict.dtd"><html><head><metaname="qrichtext"content="1"/><styletype="text/css">p,li{white-space:pre-wrap;}</style></head><bodystyle=" font-family:'Sans Serif'; font-size:9pt; font-weight:400; font-style:normal;"></style></head><bodystyle=" font-family:'Sans Serif'; font-size:9pt; font-weight:400; font-style:normal;"><palign="center"style=" margin-top:16px; margin-bottom:12px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px; font-size:x-large; font-weight:600;"><spanstyle=" font-size:x-large;">Hyperspectral data unmixing</span></p><pstyle=" margin-top:14px; margin-bottom:12px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px; font-size:large; font-weight:600;"><spanstyle=" font-size:large;">Brief Description</span></p><pstyle=" margin-top:0px; margin-bottom:0px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px;">Estimate abundance maps from an hyperspectral image and a set of endmembers.</p><pstyle=" margin-top:14px; margin-bottom:12px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px; font-size:large; font-weight:600;"><spanstyle=" font-size:large;">Tags</span></p><pstyle=" margin-top:0px; margin-bottom:0px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px;">Hyperspectral</p><pstyle=" margin-top:14px; margin-bottom:12px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px; font-size:large; font-weight:600;"><spanstyle=" font-size:large;">Long Description</span></p><pstyle=" margin-top:0px; margin-bottom:0px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px;">The application applies a linear unmixing algorithm to an hyperspectral data cube. This method supposes that the mixture between materials in the scene is macroscopic and simulate a linear mixing model of spectra.
The Linear Mixing Model (LMM) acknowledges that reflectance spectrum associated with each pixel is a linear combination of pure materials in the recovery area, commonly known as endmembers.Endmembers can be estimated using the VertexComponentAnalysis application.
The application allows to estimate the abundance maps with several algorithms : Unconstrained Least Square (ucls), Fully Constrained Least Square (fcls),Image Space Reconstruction Algorithm (isra) and Non-negative constrained Least Square (ncls) and Minimum Dispersion Constrained Non Negative Matrix Factorization (MDMDNMF).
</p><pstyle=" margin-top:14px; margin-bottom:12px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px; font-size:large; font-weight:600;"><spanstyle=" font-size:large;">Parameters</span></p><ul><li><pstyle=" margin-top:0px; margin-bottom:0px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px;"><spanstyle=" font-family:'Courier New, courier'; font-weight:600;";>[param] Input Image Filename (-in): </span>The hyperspectral data cube to unmix</p></li><li><pstyle=" margin-top:0px; margin-bottom:0px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px;"><spanstyle=" font-family:'Courier New, courier'; font-weight:600;";>[param] Output Image (-out): </span>The output abundance map</p></li><li><pstyle=" margin-top:0px; margin-bottom:0px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px;"><spanstyle=" font-family:'Courier New, courier'; font-weight:600;";>[param] Input endmembers (-ie): </span>The endmembers (estimated pure pixels) to use for unmixing. Must be stored as a multispectral image, where each pixel is interpreted as an endmember</p></li><li><pstyle=" margin-top:0px; margin-bottom:0px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px;"><spanstyle=" font-family:'Courier New, courier'; font-weight:600;";>[choice] Unmixing algorithm (-ua): </span>The algorithm to use for unmixing</p><ul><li><pstyle=" margin-top:0px; margin-bottom:0px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px;"><spanstyle=" font-family:'Courier New, courier'; font-weight:600;";>[group] UCLS: </span>Unconstrained Least Square</p><ul></ul></li><li><pstyle=" margin-top:0px; margin-bottom:0px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px;"><spanstyle=" font-family:'Courier New, courier'; font-weight:600;";>[group] FCLS: </span>Fully constrained Least Square</p><ul></ul></li><li><pstyle=" margin-top:0px; margin-bottom:0px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px;"><spanstyle=" font-family:'Courier New, courier'; font-weight:600;";>[group] NCLS: </span>Non-negative constrained Least Square</p><ul></ul></li><li><pstyle=" margin-top:0px; margin-bottom:0px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px;"><spanstyle=" font-family:'Courier New, courier'; font-weight:600;";>[group] ISRA: </span>Image Space Reconstruction Algorithm</p><ul></ul></li><li><pstyle=" margin-top:0px; margin-bottom:0px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px;"><spanstyle=" font-family:'Courier New, courier'; font-weight:600;";>[group] MDMDNMF: </span>Minimum Dispersion Constrained Non Negative Matrix Factorization</p><ul></ul></li></ul></li><br/></ul><pstyle=" margin-top:14px; margin-bottom:12px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px; font-size:large; font-weight:600;"><spanstyle=" font-size:large;">Limitations</span></p><pstyle=" margin-top:0px; margin-bottom:0px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px;">None</p><pstyle=" margin-top:14px; margin-bottom:12px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px; font-size:large; font-weight:600;"><spanstyle=" font-size:large;">Authors</span></p><pstyle=" margin-top:0px; margin-bottom:0px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px;">OTB-Team</p><pstyle=" margin-top:14px; margin-bottom:12px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px; font-size:large; font-weight:600;"><spanstyle=" font-size:large;">See also</span></p><pstyle=" margin-top:0px; margin-bottom:0px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px;">VertexComponentAnalysis</p><pstyle=" margin-top:14px; margin-bottom:12px; margin-left:0px; margin-right:0px; -qt-block-indent:0; text-indent:0px; font-size:large; font-weight:600;"><spanstyle=" font-size:large;">Example of use</span></p><ul><pstyle="margin-top:0px;margin-bottom:0px;margin-l
