Modeling and querying videos by content trajectories
Z. Aghari, Kunihiko Kaneko, Akifumi Makinouchi · 2002
We present a hierarchical approach to model video shots in three levels: object level (OL), frame level (FL), and shot level (SL). The model captures the visual features of individual objects at OL, visual-spatio-temporal (VST) relationships between objects at FL, and time-varying visual features and time-varying VST relationships at SL. We call the combination of the time-varying visual features and the time-varying VST relationships a content trajectory that is used to represent and index a video shot. A novel query interface, that allows users to describe queries, by sketch and feature specification, is presented. Our experimental results prove the effectiveness of modeling and querying video shots using the content trajectory approach.