Learn More
Human action recognition in video is often approached by means of sequential probabilistic models as they offer a natural match to the temporal dimension of the actions. However, effective estimation of the models' parameters is critical if one wants to achieve significant recognition accuracy. Parameter estimation is typically performed over a set of(More)
Human action recognition is often approached in terms of probabilistic models such as the hidden Markov model or other graphical models. When learning such models by way of Expectation-Maximisation algorithms, arbitrary choices must be made for their initial parameters. Often, solutions for the selection of the initial parameters are based on random(More)
The extraction of human features from videos is often inaccurate and prone to outliers. Such outliers can severely affect density modelling when the Gaussian distribution is used as the model since it is highly sensitive to outliers. The Gaussian distribution is also often used as base component of graphical models for recognising human actions in the(More)
Modern video surveillance requires addressing high-level concepts such as humans' actions and activities. In addition, surveillance applications need to be portable over a variety of platforms, from servers to mobile devices. In this paper, we explore the potential of the MPEG-7 standard to provide interfaces, descriptors, and architectures for human action(More)
  • 1