SEMINAR
Date: 4 May 2016 Wednesday,
Time: 14:30
Class: E-2000
Speaker: Behçet Uğur Töreyin (Assoc. Prof.)
Title: Hyperspectral Data Compression
Abstract: Hyperspectral data is composed of a set of correlated band images. In order to efficiently compress the hyperspectral imagery, this inherent correlation may be exploited by means of spectral decorrelators. In the first part of the talk, wavelet transform based spectral decorrelators will be discussed. On the other hand, sparse models provide data representations in the fewest possible number of nonzero elements. This inherent characteristic enables sparse models to be utilized for data compression purposes. In the second half of the talk, a framework for sparsity-based hyperspectral image compression methods using online learning will be presented. This research is funded by the Scientific and Technical Research Council of Turkey (TÜBİTAK), National Young Researchers Career Development Program (3501 TÜBİTAK CAREER) with project number 114E200.