Change search
ReferencesLink to record
Permanent link

Direct link
Interest point detection and scale selection in space-time
KTH, Superseded Departments, Numerical Analysis and Computer Science, NADA.
KTH, School of Computer Science and Communication (CSC), Computational Biology, CB.ORCID iD: 0000-0002-9081-2170
2003 (English)In: Scale Space Methods in Computer Vision: 4th International Conference, Scale Space 2003 Isle of Skye, UK, June 10–12, 2003 Proceedings, Springer Berlin/Heidelberg, 2003, Vol. 2695, 372-387 p.Conference paper (Refereed)
Abstract [en]

Several types of interest point detectors have been proposed for spatial images. This paper investigates how this notion can be generalised to the detection of interesting events in space-time data. Moreover, we develop a mechanism for spatio-temporal scale selection and detect events at scales corresponding to their extent in both space and time. To detect spatio-temporal events, we build on the idea of the Harris and Forstner interest point operators and detect regions in space-time where the image structures have significant local variations in both space and time. In this way, events that correspond to curved space-time structures are emphasised, while structures with locally constant motion are disregarded. To construct this operator, we start from a multi-scale windowed second moment matrix in space-time, and combine the determinant and the trace in a similar way as for the spatial Harris operator. All space-time maxima of this operator are then adapted to characteristic scales by maximising a scale-normalised space-time Laplacian operator over both spatial scales and temporal scales. The motivation for performing temporal scale selection as a complement to previous approaches of spatial scale selection is to be able to robustly capture spatio-temporal events of different temporal extent. It is shown that the resulting approach is truly scale invariant with respect to both spatial scales and temporal scales. The proposed concept is tested on synthetic and real image sequences. It is shown that the operator responds to distinct and stable points in space-time that often correspond to interesting events. The potential applications of the method are discussed.

Place, publisher, year, edition, pages
Springer Berlin/Heidelberg, 2003. Vol. 2695, 372-387 p.
, Lecture Notes in Computer Science, ISSN 0302-9743 ; 2695
National Category
Computer Science Computer Vision and Robotics (Autonomous Systems)
URN: urn:nbn:se:kth:diva-41560DOI: 10.1007/3-540-44935-3_26ISI: 000185043200026ISBN: 978-3-540-40368-5OAI: diva2:444655
Scale-Space Methods in Computer Vision

QC 20110929

Available from: 2013-04-22 Created: 2011-09-29 Last updated: 2013-04-22Bibliographically approved

Open Access in DiVA

fulltext(1090 kB)611 downloads
File information
File name FULLTEXT01.pdfFile size 1090 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Publisher's full textAt authors' home pageThe final publication is available at

Search in DiVA

By author/editor
Laptev, IvanLindeberg, Tony
By organisation
Numerical Analysis and Computer Science, NADAComputational Biology, CB
Computer ScienceComputer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar
Total: 611 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: 151 hits
ReferencesLink to record
Permanent link

Direct link