Activity Detection Using Regular Expressions

In this paper we propose a new method for trajectory analysis in surveillance scenarios using Context-Free Grammars. Starting from a predefined set of activities, we provide a tool to compare the incoming paths with the stored templates, analyzing the sequence of samples at a syntactic level. Using this approach it is possible to perform the matching of trajectories at different abstraction layers, retrieving for example recurrent motion patterns or anomalous activities. The implemented system has been validated in indoor, considering as the main objective activity monitoring for assisted living applications. The results demonstrate the capability of the framework in recognizing known motion patterns, as well as in determining the presence of unknown actions, classified as anomalous.