Jocelyn Chanussot
University of Grenoble
713 Papers
4.8K Citations
Jocelyn Chanussot is an academic researcher from University of Grenoble. The author has contributed to research in topics: Hyperspectral imaging & Computer science. The author has an hindex of 73, co-authored 614 publications. Previous affiliations of Jocelyn Chanussot include German Aerospace Center & University of Savoy.
Chat about Author
Papers
A Bayesian Procedure for Full-Resolution Quality Assessment of Pansharpened Products
TL;DR: The FR assessment is focused on the FR assessment proposing an approach for estimating an overall quality index at FR by using multiscale FR measurements and has demonstrated its superiority with respect to the benchmark consisting of state-of-the-art quality assessment procedures.
A New Pansharpening Method Based on Spatial and Spectral Sparsity Priors
TL;DR: A new variational model based on spatial and spectral sparsity priors for the fusion of panchromatic and fused multispectral images is introduced and results show the effectiveness of the proposed pansharpening method compared with the state-of-the-art.
Unsupervised nonlinear spectral unmixing by means of NLPCA applied to hyperspectral imagery
Giorgio Licciardi,Xavier Ceamanos,Sylvain Douté,Jocelyn Chanussot +3 more
- 22 Jul 2012
TL;DR: In this article, the potentialities of nonlinear principal component analysis (NLPCA) as an approach to perform a nonlinear unmixing for the unsupervised extraction and quantification of the end-members.
•Posted Content
A General Framework for Fast Image Deconvolution with Incomplete Observations. Applications to Unknown Boundaries, Inpainting, Superresolution, and Demosaicing.
TL;DR: A new deconvolution framework for images with incomplete observations that allows us to work with diagonalized convolution operators, and therefore is very fast, is proposed and an implementation of this framework is proposed, based on the alternating direction method of multipliers (ADMM).
Class-Specific Sparse Multiple Kernel Learning for Spectral–Spatial Hyperspectral Image Classification
TL;DR: The experimental results show that the proposed CS-SMKL achieves better performances for hyperspectral image classification compared with several state-of-the-art algorithms, and the results confirm the capability of the method in selecting the useful features.