Linear spatio-temporal scale-space
1997 (English)In: Scale-Space Theory in Computer Vision: Proceedings of First International Conference, Scale-Space'97 Utrecht, The Netherlands, July 2–4, 1997, Springer Berlin/Heidelberg, 1997, Vol. 1252, 113-127 p.Conference paper (Refereed)
This article shows how a linear scale-space formulation previously expressed for spatial domains extends to spatio-temporal data. Starting from the main assumptions that: (i) the scale-space should be generated by convolution with a semi-group of filter kernels and that (ii) local extrema must not be enhanced when the scale parameter increases, a complete taxonomy is given of the linear scale-space concepts that satisfy these conditions on spatial, temporal and spatio-temporal domains, including the cases with continuous as well as discrete data.
Key aspects captured by this theory include that: (i) time-causal scale-space kernels must not extend into the future, (ii) filter shapes can be tuned from specific context information, permitting mechanisms such local shifting, shape adaptation and velocity adaptation, all expressed in terms of local diffusion operations.
Receptive field profiles generated by the proposed theory show high qualitative similarities to receptive field profiles recorded from biological vision.
Place, publisher, year, edition, pages
Springer Berlin/Heidelberg, 1997. Vol. 1252, 113-127 p.
, Lecture Notes in Computer Science, ISSN 0302-9743 ; 1252
Computer and Information Science Mathematics Computer Vision and Robotics (Autonomous Systems)
IdentifiersURN: urn:nbn:se:kth:diva-40223DOI: 10.1007/3-540-63167-4_44OAI: oai:DiVA.org:kth-40223DiVA: diva2:442085
1st International Conference on Scale-Space Theory in Computer Vision, Scale-Space'97 Utrecht, The Netherlands, July 2–4, 1997
QC 201109202013-04-192011-09-132013-04-19Bibliographically approved