Detection of misallocated endmembers through the network based method

Dimitris, S; Vassilia, K

dc.contributor.author	Dimitris, S	en
dc.contributor.author	Vassilia, K	en
dc.date.accessioned	2014-03-01T02:46:45Z
dc.date.available	2014-03-01T02:46:45Z
dc.date.issued	2010	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/32826
dc.subject	Endmembers	en
dc.subject	Mixed pixel classification	en
dc.subject	Networks	en
dc.subject	Sum to one constraint	en
dc.subject.other	Constraint least squares	en
dc.subject.other	Distributed components	en
dc.subject.other	Endmembers	en
dc.subject.other	HyperSpectral	en
dc.subject.other	Image scene	en
dc.subject.other	Mixed pixel classification	en
dc.subject.other	Natural targets	en
dc.subject.other	Network-based	en
dc.subject.other	Networks	en
dc.subject.other	Spectral components	en
dc.subject.other	Sum to one constraint	en
dc.subject.other	Experiments	en
dc.subject.other	Pixels	en
dc.subject.other	Remote sensing	en
dc.subject.other	Signal processing	en
dc.subject.other	Space optics	en
dc.subject.other	Signal detection	en
dc.title	Detection of misallocated endmembers through the network based method	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/WHISPERS.2010.5594857	en
heal.identifier.secondary	http://dx.doi.org/10.1109/WHISPERS.2010.5594857	en
heal.identifier.secondary	5594857	en
heal.publicationDate	2010	en
heal.abstract	Recently, a new logarithmic mixed pixel classification method has been developed through the establishment of appropriate networks. Based on the fact that natural targets do not consist of equally distributed components, the Network Based Method (NBM) alerts the user for non-sampled endmembers in the image scene. In this paper, detection of misallocated endmembers in the hyperspectral space is investigated through the Network Based Method. Detection relies on the fact that misallocation of an endmember in the hyperspectral space affects its signature because the endmember includes spectral components from other endmembers, mainly from the one which is approached mostly. Three experiments were implemented and their results were compared with the Sum to One Constraint Least Square (SCLS) method's results. Experiments showed efficiency of the method to detect two endmembers with common components. ©2010 IEEE.	en
heal.journalName	2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2010 - Workshop Program	en
dc.identifier.doi	10.1109/WHISPERS.2010.5594857	en