Earth Observation Image Semantics: Latent Dirichlet Allocation Based Information Discovery

Land cover maps are among the most important products of Remote Sensing (RS) imagery. Despite remarkable advancements in land cover classification techniques, abundant detailed information in the very high-resolution RS images necessitates further improvements to harness the data and discover detailed semantic information. Moreover, scarcity of the labelled data and its quality is a major limitation in RS land cover mapping. In the present study, Latent Dirichlet Allocation is employed for semantic discovery in RS images and a novel kernel-based Bag of Visual Words model is proposed for land cover mapping.