Change search
ReferencesLink to record
Permanent link

Direct link
Local velocity-adapted motion events for spatio-temporal recognition
KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.ORCID iD: 0000-0003-3439-0468
KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.ORCID iD: 0000-0002-9081-2170
2007 (English)In: Computer Vision and Image Understanding, ISSN 1077-3142, E-ISSN 1090-235X, Vol. 108, no 3, 207-229 p.Article in journal (Refereed) Published
Abstract [en]

In this paper, we address the problem of motion recognition using event-based local motion representations. We assume that similar patterns of motion contain similar events with consistent motion across image sequences. Using this assumption, we formulate the problem of motion recognition as a matching of corresponding events in image sequences. To enable the matching, we present and evaluate a set of motion descriptors that exploit the spatial and the temporal coherence of motion measurements between corresponding events in image sequences. As the motion measurements may depend on the relative motion of the camera, we also present a mechanism for local velocity adaptation of events and evaluate its influence when recognizing image sequences subjected to different camera motions. When recognizing motion patterns, we compare the performance of a nearest neighbor (NN) classifier with the performance of a support vector machine (SVM). We also compare event-based motion representations to motion representations in terms of global histograms. A systematic experimental evaluation on a large video database with human actions demonstrates that (i) local spatio-temporal image descriptors can be defined to carry important information of space-time events for subsequent recognition, and that (ii) local velocity adaptation is an important mechanism in situations when the relative motion between the camera and the interesting events in the scene is unknown. The particular advantage of event-based representations and velocity adaptation is further emphasized when recognizing human actions in unconstrained scenes with complex and non-stationary backgrounds.

Place, publisher, year, edition, pages
Elsevier, 2007. Vol. 108, no 3, 207-229 p.
Keyword [en]
motion, local features, motion descriptors, matching, velocity adaptation, action recognition, learning, SVM, human movement, representation, scale
National Category
Computer Vision and Robotics (Autonomous Systems) Computer Science Mathematics
URN: urn:nbn:se:kth:diva-17110DOI: 10.1016/j.cviu.2006.11.023ISI: 000250942900002ScopusID: 2-s2.0-35548930762OAI: diva2:335153
Swedish Research Council

QC 20100525 QC 20111115

Available from: 2013-04-22 Created: 2010-08-05 Last updated: 2013-04-22Bibliographically approved

Open Access in DiVA

fulltext(2159 kB)354 downloads
File information
File name FULLTEXT01.pdfFile size 2159 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopusSciencedirect

Search in DiVA

By author/editor
Laptev, IvanSchüldt, ChristianLindeberg, Tony
By organisation
Computer Vision and Active Perception, CVAP
In the same journal
Computer Vision and Image Understanding
Computer Vision and Robotics (Autonomous Systems)Computer ScienceMathematics

Search outside of DiVA

GoogleGoogle Scholar
Total: 354 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 415 hits
ReferencesLink to record
Permanent link

Direct link