Hierarchical Graphical Models for Simultaneous Tracking and Recognition in Wide-Area Scenes
Abstract— Hierarchical Graphical Models for Simultaneous Tracking and Recognition in Wide-Area Scenes. A uniﬁed framework to track multiple people, as well localize, and label their activities, in complex long-duration video sequences. To do this, we focus on two aspects: 1) the inﬂuence of tracks on the activities performed by the< Final Year Projects 2016 > corresponding actors and 2) the structural relationships across activities. We propose a two-level hierarchical graphical model, which learns the relationship between tracks, relationship between tracks, and their corresponding activity segments, as well as the spatiotemporal relationships across activity segments. Such contextual relationships between tracks and activity segments are exploited at both the levels in the hierarchy for increased robustness.