Local descriptors for spatio-temporal recognition
2006 (English)In: Spatial Coherence For Visual Motion Analysis: First International Workshop, SCVMA 2004, Prague, Czech Republic, May 15, 2004. Revised Papers / [ed] MacLean, WJ, Springer Berlin/Heidelberg, 2006, Vol. 3667, 91-103 p.Conference paper (Refereed)
This paper presents and investigates a set of local space-time descriptors for representing and recognizing motion patterns in video. Following the idea of local features in the spatial domain, we use the notion of space-time interest points and represent video data in terms of local space-time events. To describe such events, we define several types of image descriptors over local spatio-temporal neighborhoods and evaluate these descriptors in the context of recognizing human activities. In particular, we compare motion representations in terms of spatio-temporal jets, position dependent histograms, position independent histograms, and principal component analysis computed for either spatio-temporal gradients or optic flow. An experimental evaluation on a video database with human actions shows that high classification performance can be achieved, and that there is a clear advantage of using local position dependent histograms, consistent with previously reported findings regarding spatial recognition.
Place, publisher, year, edition, pages
Springer Berlin/Heidelberg, 2006. Vol. 3667, 91-103 p.
, Lecture Notes in Computer Science, ISSN 0302-9743 ; 3667
Human Movement, Representation
Computer and Information Science
IdentifiersURN: urn:nbn:se:kth:diva-41720DOI: 10.1007/11676959_8ISI: 000237244700008ScopusID: 2-s2.0-33745757308ISBN: 3-540-32533-6OAI: oai:DiVA.org:kth-41720DiVA: diva2:445261
1st International Workshop on Spatial Coherence for Visual Motion Analysis, SCVMA 2004; Prague; 15 May 2004 through 15 May 2004
QC 201110032013-04-222011-09-302013-04-22Bibliographically approved