Sparse representations and invariant sequence-feature extraction for event detection

We address the problem of detecting unusual actions performed by a human in a video. Broadly speaking, we achieve our goal by matching the observed action to a set of a-priori known actions. If the observed action can not be matched to any of the known actions (representing the normal case), we conclude that an event has taken place. In this contribution we will show how sparse representations of actions can be used for event detection. Our input data are video sequences showing different actions. Special care is taken to extract features rom these sequences. The features are chosen such that the sparse-representations paradigm can be applied and they exhibit a set of invariance properties needed for detecting unusual human actions. We test our methods on sequences showing different people performing various actions such as walking or running.