Sciweavers

ICCV
2009
IEEE

Modelling Activity Global Temporal Dependencies using Time Delayed Probabilistic Graphical Model

15 years 4 months ago
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.
Chen Change Loy, Tao Xiang and Shaogang Gong
Added 13 Jul 2009
Updated 07 Jan 2012
Type Conference
Year 2009
Where ICCV
Authors Chen Change Loy, Tao Xiang and Shaogang Gong
Comments (0)