Learning Methods for Dynamic Topic Modeling in Automated Behaviour Analysis
This work addresses the need for automated behavior analysis in areas such as transportation and surveillance, offering incremental improvements in learning algorithms for dynamic topic models.
The paper tackles the problem of analyzing activities and behaviors in video data by proposing new learning algorithms for dynamic topic modeling, achieving performance comparable to existing methods like Gibbs sampling on real video data.
Semi-supervised and unsupervised systems provide operators with invaluable support and can tremendously reduce the operators load. In the light of the necessity to process large volumes of video data and provide autonomous decisions, this work proposes new learning algorithms for activity analysis in video. The activities and behaviours are described by a dynamic topic model. Two novel learning algorithms based on the expectation maximisation approach and variational Bayes inference are proposed. Theoretical derivations of the posterior of model parameters are given. The designed learning algorithms are compared with the Gibbs sampling inference scheme introduced earlier in the literature. A detailed comparison of the learning algorithms is presented on real video data. We also propose an anomaly localisation procedure, elegantly embedded in the topic modeling framework. The proposed framework can be applied to a number of areas, including transportation systems, security and surveillance.