OPTIMAL TRANSPORT FOR DATA FUSION IN REMOTE SENSING

被引:11
作者
Courty, Nicolas [1 ]
Flamary, Remi [2 ]
Tuia, Devis [3 ]
Corpetti, Thomas [4 ]
机构
[1] Univ Bretagne Sud, IRISA, Vannes, France
[2] UNS, OCA, CNRS, Lagrange, Nice, France
[3] Univ Zurich, MMRS, Zurich, Switzerland
[4] CNRS, LETG, Rennes, France
来源
2016 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS) | 2016年
基金
瑞士国家科学基金会;
关键词
Optimal transport; domain adaptation; time series analysis; change detection; LIDAR;
D O I
10.1109/IGARSS.2016.7729925
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
One of the main objective of data fusion is the integration of several acquisition of the same physical object, in order to build a new consistent representation that embeds all the information from the different modalities. In this paper, we propose the use of optimal transport theory as a powerful mean of establishing correspondences between the modalities. After reviewing important properties and computational aspects, we showcase its application to three remote sensing fusion problems: domain adaptation, time series averaging and change detection in LIDAR data.
引用
收藏
页码:3571 / 3574
页数:4
相关论文
共 20 条
[1]   ITERATIVE BREGMAN PROJECTIONS FOR REGULARIZED TRANSPORTATION PROBLEMS [J].
Benamou, Jean-David ;
Carlier, Guillaume ;
Cuturi, Marco ;
Nenna, Luca ;
Peyre, Gabriel .
SIAM JOURNAL ON SCIENTIFIC COMPUTING, 2015, 37 (02) :A1111-A1138
[2]  
Bonneel N., 2014, J MATH IMAG IN PRESS
[3]   Displacement Interpolation Using Lagrangian Mass Transport [J].
Bonneel, Nicolas ;
van de Panne, Michiel ;
Paris, Sylvain ;
Heidrich, Wolfgang .
ACM TRANSACTIONS ON GRAPHICS, 2011, 30 (06)
[4]  
Camps-Valls G, 2014, IEEE SIGNAL PROC MAG, V31, P45, DOI 10.1109/MSP.2013.2279179
[5]  
Courty N., 2014, P ECML
[6]  
Cuturi M., 2015, SIAM J IMAGING S DEC
[7]  
Cuturi M., 2013, ADV NEURAL INFORM PR, V2, P4, DOI DOI 10.48550/ARXIV.1306.0895
[8]  
Cuturi M., 2014, P ICML JUN
[9]  
Ferradans S., 2014, SIAM J IMAGING SCI, V7
[10]   Multimodal Classification of Remote Sensing Images: A Review and Future Directions [J].
Gomez-Chova, Luis ;
Tuia, Devis ;
Moser, Gabriele ;
Camps-Valls, Gustau .
PROCEEDINGS OF THE IEEE, 2015, 103 (09) :1560-1584