DocumentCode :
3155505
Title :
Hyperspectral image compressed sensing via low-rank and joint-sparse matrix recovery
Author :
Golbabaee, Mohammad ; Vandergheynst, Pierre
Author_Institution :
Signal Process. Inst., Ecole Polytech. Fed. de Lausanne (EPFL), Lausanne, Switzerland
fYear :
2012
fDate :
25-30 March 2012
Firstpage :
2741
Lastpage :
2744
Abstract :
We propose a novel approach to reconstruct Hyperspectral images from very few number of noisy compressive measurements. Our reconstruction approach is based on a convex minimization which penalizes both the nuclear norm and the ℓ2,1 mixed-norm of the data matrix. Thus, the solution tends to have a simultaneous low-rank and joint-sparse structure. We explain how these two assumptions fit Hyperspectral data, and by severals simulations we show that our proposed reconstruction scheme significantly enhances the state-of-the-art tradeoffs between the reconstruction error and the required number of CS measurements.
Keywords :
convex programming; geophysical image processing; image coding; image reconstruction; sparse matrices; CS measurements; convex minimization; data matrix; hyperspectral data; hyperspectral image compressed sensing; hyperspectral image reconstruction; joint-sparse matrix recovery; joint-sparse structure; low-rank matrix recovery; low-rank structure; mixed-norm; noisy compressive measurements; nuclear norm; reconstruction approach; reconstruction error; reconstruction scheme; state-of-the-art tradeoffs; Compressed sensing; Correlation; Hyperspectral imaging; Image coding; Image reconstruction; Sparse matrices; Compressed sensing; Hyperspectral images; Joint sparse signals; Low rank matrix recovery; Nuclear norm;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on
Conference_Location :
Kyoto
ISSN :
1520-6149
Print_ISBN :
978-1-4673-0045-2
Electronic_ISBN :
1520-6149
Type :
conf
DOI :
10.1109/ICASSP.2012.6288484
Filename :
6288484
Link To Document :
بازگشت