Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/107639
Citations
Scopus Web of Science® Altmetric
?
?
Type: Conference paper
Title: Cluster sparsity field for hyperspectral imagery denoising
Author: Zhang, L.
Wei, W.
Zhang, Y.
Shen, C.
Van Den Hengel, A.
Shi, Q.
Citation: Proceedings of the 14th European Conference on Computer Vision, 2016 / Leibe, B., Matas, J., Sebe, N., Welling, M. (ed./s), vol.9909, pp.631-647
Publisher: Springer International Publishing AG
Issue Date: 2016
Series/Report no.: Lecture Notes in Computer Science
ISBN: 9783319464534
ISSN: 0302-9743
1611-3349
Conference Name: 14th European Conference on Computer Vision (ECCV) (08 Oct 2016 - 16 Oct 2016 : Amsterdam, Netherlands)
Statement of
Responsibility: 
Lei Zhang, Wei Wei, B, Yanning Zhang, Chunhua Shen, Anton van den Hengel, and Qinfeng Shi
Abstract: Hyperspectral images (HSIs) can facilitate extensive computer vision applications with the extra spectra information. However, HSIs often suffer from noise corruption during the practical imaging procedure. Though it has been testified that intrinsic correlation across spectrum and spatial similarity (i.e., local similarity in locally smooth areas and non-local similarity among recurrent patterns) in HSIs are useful for denoising, how to fully exploit them together to obtain a good denoising model is seldom studied. In this study, we present an effective cluster sparsity field based HSIs denoising (CSFHD) method by exploiting those two characteristics simultaneously. Firstly, a novel Markov random field prior, named cluster sparsity field (CSF), is proposed for the sparse representation of an HSI. By grouping pixels into several clusters with spectral similarity, the CSF prior defines both a structured sparsity potential and a graph structure potential on each cluster to model the correlation across spectrum and spatial similarity in the HSI, respectively. Then, the CSF prior learning and the image denoising are unified into a variational framework for optimization, where all unknown variables are learned directly from the noisy observation. This guarantees to learn a data-dependent image model, thus producing satisfying denoising results. Plenty experiments on denoising synthetic and real noisy HSIs validated that the proposed CSFHD outperforms several state-of-the-art methods.
Keywords: Hyperspectral; Denoising; Structured sparsity; Spatial similarity
Rights: © Springer International Publishing AG 2016
RMID: 0030057240
DOI: 10.1007/978-3-319-46454-1_38
Grant ID: http://purl.org/au-research/grants/arc/DP140102270
http://purl.org/au-research/grants/arc/DP160100703
http://purl.org/au-research/grants/arc/FT120100969
Appears in Collections:Computer Science publications

Files in This Item:
File Description SizeFormat 
RA_hdl_107639.pdfRestricted Access3.88 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.