Sparse representations and invariant sequence-feature extraction for event detection

A. P. Condurache, A. Mertins


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.
Original languageEnglish
Title of host publicationProc. of Intl. Conf. on Comp. Vis. Theory and App. (VISAPP)
Number of pages6
Place of PublicationRome, Italy
Publication date01.12.2012
ISBN (Print)978-989856503-7
Publication statusPublished - 01.12.2012
EventInternational Conference on Computer Vision Theory and Applications - Rome, Italy
Duration: 24.02.201226.02.2012
Conference number: 90194


Dive into the research topics of 'Sparse representations and invariant sequence-feature extraction for event detection'. Together they form a unique fingerprint.

Cite this