Change search
ReferencesLink to record
Permanent link

Direct link
Velocity adaptation of spatio-temporal receptive fields for direct recognition of activities: an experimental study
KTH, Superseded Departments, Numerical Analysis and Computer Science, NADA.
KTH, Superseded Departments, Numerical Analysis and Computer Science, NADA.ORCID iD: 0000-0002-9081-2170
2004 (English)In: Image and Vision Computing, ISSN 0262-8856, Vol. 22, no 2, 105-116 p.Article in journal (Refereed) Published
Abstract [en]

This article presents an experimental study of the influence of velocity adaptation when recognizing spatio-temporal patterns using a histogram-based statistical framework. The basic idea consists of adapting the shapes of the filter kernels to the local direction of motion, so as to allow the computation of image descriptors that are invariant to the relative motion in the image plane between the camera and the objects or events that are studied. Based on a framework of recursive spatio-temporal scale-space, we first outline how a straightforward mechanism for local velocity adaptation can be expressed. Then, for a test problem of recognizing activities, we present an experimental evaluation, which shows the advantages of using velocity-adapted spatio-temporal receptive fields, compared to directional derivatives or regular partial derivatives for which the filter kernels have not been adapted to the local image motion.

Place, publisher, year, edition, pages
Elsevier, 2004. Vol. 22, no 2, 105-116 p.
Keyword [en]
motion, spatio-temporal filtering, scale-space, recognition, scale-space, selection, affine, shape
National Category
Computer and Information Science
URN: urn:nbn:se:kth:diva-23131DOI: 10.1016/j.imavis.2003.07.002ISI: 000188612000004ScopusID: 2-s2.0-0346340840OAI: diva2:341829

QC 20100525 QC 20111019

Available from: 2013-04-22 Created: 2010-08-10 Last updated: 2013-04-22Bibliographically approved

Open Access in DiVA

fulltext(1083 kB)181 downloads
File information
File name FULLTEXT01.pdfFile size 1083 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopusSciencedirect

Search in DiVA

By author/editor
Laptev, IvanLindeberg, Tony
By organisation
Numerical Analysis and Computer Science, NADA
In the same journal
Image and Vision Computing
Computer and Information Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 181 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: 148 hits
ReferencesLink to record
Permanent link

Direct link