Modelling Activity Global Temporal Dependencies using Time Delayed Probabilistic Graphical Model

We present a novel approach for detecting global behaviour anomalies in multiple disjoint cameras by learning time delayed dependencies between activities cross camera views. Specifically, we propose to model multi-camera activities using a Time Delayed Probabilistic Graphical Model (TD-PGM) with different nodes representing activities in different semantically decomposed regions from different camera views, and the directed links between nodes encoding causal relationships between the activities. A novel two-stage structure learning algorithm is formulated to learn globally optimised time-delayed dependencies. A new cumulative abnormality score is also introduced to replace the conventional log-likelihood score for gaining significantly more robust and reliable real-time anomaly detection. The effectiveness of the proposed approach is validated using a camera network installed at a busy underground station.

• Type: Conference
• Year: 2009
• Where: ICCV
• Authors: Chen Change Loy, Tao Xiang and Shaogang Gong
• Keywords: Computer Vision, Human Activity Recognition, ICCV 2009