Title :
Conditional mixed-state model for structural change analysis from very high resolution optical images
Author :
Belmudez, Benjamin ; Prinet, Véronique ; Yao, Jian-Feng ; Bouthemy, Patrick ; Descombes, Xavier
Author_Institution :
Inst. of Autom., Chinese Acad. of Sci., Beijing, China
Abstract :
The present work concerns the analysis of dynamic scenes from earth observation images. We are interested in building a map which, on one hand locates places of change, on the other hand, reconstructs a unique visual information of the non-change areas. We show in this paper that such a problem can naturally be takled with conditional mixed-state random field modeling (mixed-state CRF), where the ¿mixed state¿ refers to the symbolic or continous nature of the unknown variable. The maximum a posteriori (MAP) estimation of the CRF is, through the Hammersley-Clifford theorem, turned into an energy minimisation problem. We tested the model on several Quickbird images and illustrate the quality of the results.
Keywords :
geophysical image processing; image reconstruction; maximum likelihood estimation; Hammersley-Clifford theorem; Quickbird images; conditional mixed-state model; earth observation images; maximum a posteriori estimation; random field modeling; structural change analysis; very high resolution optical images; visual information reconstruction; Earth; Energy resolution; Image analysis; Image reconstruction; Image resolution; Image segmentation; Layout; Random variables; Remote sensing; Satellites; Change detection; Conditional random fields; Image analysis; Mixed-state model; Remote sensing;
Conference_Titel :
Geoscience and Remote Sensing Symposium,2009 IEEE International,IGARSS 2009
Conference_Location :
Cape Town
Print_ISBN :
978-1-4244-3394-0
Electronic_ISBN :
978-1-4244-3395-7
DOI :
10.1109/IGARSS.2009.5418267
