Pansharpening via Locality-Constrained Sparse Representation

Songze Tang, Nan zhou and Liang Xiao

Abstract

Recently, sparse representation based approaches have been shown an effective performance for pansharpening. However, these methods imposed (cid:96)0 or (cid:96)1 -norm constraints on the sparse coefficients. The local similarity of sparse coefficients was ignored. Motivated by the importance of data locality, in this paper, we propose a locality-constrained sparse representation algorithm for pansharpening, which keeps the data locality during the sparse representation process. The learned dictionary is able to preserve local data structure, resulting in improved data representation. During the sparse coding stage, analytical solutions are provided based on the basis of mathematic deduction.

Session

Posters

Files

PDF iconPaper (PDF)

DOI

10.5244/C.31.180
https://dx.doi.org/10.5244/C.31.180

Citation

Songze Tang, Nan zhou and Liang Xiao. Pansharpening via Locality-Constrained Sparse Representation. In T.K. Kim, S. Zafeiriou, G. Brostow and K. Mikolajczyk, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 180.1-180.11. BMVA Press, September 2017.

Bibtex

            @inproceedings{BMVC2017_180,
                title={Pansharpening via Locality-Constrained Sparse Representation},
                author={Songze Tang, Nan zhou and Liang Xiao},
                year={2017},
                month={September},
                pages={180.1-180.11},
                articleno={180},
                numpages={11},
                booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
                publisher={BMVA Press},
                editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
                doi={10.5244/C.31.180},
                isbn={1-901725-60-X},
                url={https://dx.doi.org/10.5244/C.31.180}
            }