ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., III-7, 17-23, 2016
http://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/III-7/17/2016/
doi:10.5194/isprs-annals-III-7-17-2016
 
07 Jun 2016
VIRTUAL DIMENSIONALITY ESTIMATION IN HYPERSPECTRAL IMAGERY BASED ON UNSUPERVISED FEATURE SELECTION
M. Ghamary Asl1 and B. Mojaradi2 1Dept. of Remote Sensing, Faculty of Geodesy and Geomatics Engineering, K.N. Toosi University of Technology, Tehran 19967-15433, Iran
2Dept. of Geomatics Engineering, School of Civil Engineering, Iran University of Science and Technology, Tehran 16846- 13114, Iran
Keywords: Hyperspectral Imagery, Unsupervised Feature Selection, Signal Subspace Identification, Virtual Dimensionality, Partition Space Abstract. Virtual Dimensionality (VD) is a concept developed to estimate the number of distinct spectral signatures in hyperspectral imagery. Intuitively, detecting the number of spectrally distinct signatures depends on determining the number of distinct bands of the data. Considering this idea, the current paper aims at estimating the VD based on finding independent bands in the image partition space. Eventually, the number of independent selected bands is accepted as the VD estimate. The proposed method is automatic and distribution-free. In addition, no tuning parameters and noise estimation processes are needed. This method is compared with three well-known VD estimation methods using synthetic and real datasets. Experimental results show high speed and reliability in the performance of the proposed method.
Conference paper (PDF, 836 KB)


Citation: Ghamary Asl, M. and Mojaradi, B.: VIRTUAL DIMENSIONALITY ESTIMATION IN HYPERSPECTRAL IMAGERY BASED ON UNSUPERVISED FEATURE SELECTION, ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., III-7, 17-23, doi:10.5194/isprs-annals-III-7-17-2016, 2016.

BibTeX EndNote Reference Manager XML