Multimodal context modeling and classification using TBM

This paper presents a novel supervised method for context modeling and classification based on Transferable Belief Model (TBM). The task of context classification is to identify, among predefined context types, the one that is currently active in the video-surveillance footage of multipurpose halls. Context is spatially modeled by extracting five discriminative semantic features according to depth zones. These zones are provided by depth-based scene segmentation method. Using mathematical TBM tools, the structured semantic features are processed and the mass functions are modeled on three levels in order to propose classification. In addition to video document indexing and retrieval, this work can improve the machine vision capability in behavior analysis.