Semantic analysis of satellite image time series

Large archives of satellite images have been created over time. The existence of these archives enables us to extract evolutions of the same of same geographic area over time, creating satellite image time series (SITS). As SITS represent an amount of information far greater than individual images, their analysis is complex and difficult. In this paper we propose a new unsupervised SITS analysis method based on the latent Dirichlet allocation (LDA) model, a hierarchical model originally developed for text analysis. In this model documents are represented as random mixture of latent topics, each topic being characterized by a distribution over words. This paper extends the use of LDA model for satellite image time series analysis by proposing a description language for SITS modeling according to the LDA model, and is applied on a SITS of 11 Landsat TM scenes acquired in 2007.