A method for online incremental mining of activity patterns from the surveillance video stream is presented in this paper. The framework consists of a learning block in which Dirichlet process mixture model is employed for the incremental clustering of trajectories. Stochastic trajectory pattern models are formed using the Gaussian process regression of the corresponding flow functions. Moreover, a sequential Monte Carlo method based on Rao-Blackwellized particle filter is proposed for tracking and online classification as well as the detection of abnormality during the observation of an object. Experimental results on real surveillance video data are provided to show the performance of the proposed algorithm in different tasks of trajectory clustering, classification, and abnormality detection.
The problem of behavior assessment in video surveillance is approached using trajectory classification. Lagrangian state dynamic is used for probabilistic modeling of trajectory patterns and an off-line parameter learning method for the model is proposed. For classification purpose, an on-line sequential maximum a posterior trajectory classifier is introduced based on particle filter. Finally, the performance of this method is evaluated using a traffic video data set
Perceiving crowd emotions and understand the situation is vital to control the situations in surveillance applications. This paper introduces the evolution of methods for crowd emotion perception based on bio-inspired probabilistic models. The emotions have been perceived both in an offline and online manner from the crowd. We focus on the perception of emotion from crowd behavior and dynamics. The paper explains few probabilistic algorithms and compares these for detection of emotion of crowds and proposes a probabilistic modelling approach which is trained on data to perceive the emotions of the crowd in an area under surveillance. Emotions are defined as evolving dynamic patterns arising due to interaction of people in an environment with their relationships to the past interaction patterns. Camera sensors are used to track the motion of the individuals within a crowd scenario under observation. The data mining techniques are used to distinguish between different behaviors and events into positive and negative emotions. The results have been evaluated using simulated data from a proposed office environmen
In this paper we present a trajectory clustering method based on nonparametric Bayesian approach proposed for analyzing dynamic systems. Our method uses a modified hierarchical Dirichlet process-hidden Markov model in order to learn trajectory patterns into its parameter variables in an unsupervised way. Due to inherited Bayesian structure, this model resolves some limitations in trajectory clustering problem such as sequential analysis, incremental learning and non-uniform sampling. In this paper we introduce this model and its learning algorithm and finally we evaluate its performance.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.