Bayesian Inference of Recursive Sequences of Group Activities from Tracks
This addresses the problem of analyzing complex group activities in video surveillance for applications like security or behavior analysis, but it is incremental as it builds on existing probabilistic and nonparametric methods.
The paper tackles the problem of inferring recursively structured group activities from individual trajectories by developing a probabilistic generative model with a nonparametric Gaussian Process for trajectories and an MCMC sampling framework for joint inference. The result is demonstrated on simulated and real-world video datasets (VIRAT and UCLA Aerial Event), showing the model's expressive power.
We present a probabilistic generative model for inferring a description of coordinated, recursively structured group activities at multiple levels of temporal granularity based on observations of individuals' trajectories. The model accommodates: (1) hierarchically structured groups, (2) activities that are temporally and compositionally recursive, (3) component roles assigning different subactivity dynamics to subgroups of participants, and (4) a nonparametric Gaussian Process model of trajectories. We present an MCMC sampling framework for performing joint inference over recursive activity descriptions and assignment of trajectories to groups, integrating out continuous parameters. We demonstrate the model's expressive power in several simulated and complex real-world scenarios from the VIRAT and UCLA Aerial Event video data sets.