Learning Higher-order Transition Models in Medium-scale Camera Networks

We present a Bayesian framework for learning higherorder transition models in video surveillance networks. Such higher-order models describe object movement between cameras in the network and have a greater predictive power for multi-camera tracking than camera adjacency alone. These models also provide inherent resilience to camera failure, filling in gaps left by single or even multiple non-adjacent camera failures. Our approach to estimating higher-order transition models relies on the accurate assignment of camera observations to the underlying trajectories of objects moving through the network. We addresses this data association problem by gathering the observations and evaluating alternative partitions of the observation set into individual object trajectories. Searching the complete partition space is intractable, so an incremental approach is taken, iteratively adding observations and pruning unlikely partitions. Partition likelihood is determined by the evaluation of a probab...

• Type: Conference
• Year: 2007
• Where: ICCV
• Authors: Ryan Farrell, David S. Doermann, Larry S. Davis
• Keywords: Camera Observations, Computer Vision, ICCV 2007, Individual Object Trajectories, Medium-scale Smart Camera, Non-adjacent Camera Failures, True Object Trajectories