Change search
ReferencesLink to record
Permanent link

Direct link
Time-causal and time-recursive spatio-temporal receptive fields
KTH, School of Computer Science and Communication (CSC), Computational Biology, CB. (Computational Brain Science Laboratory)ORCID iD: 0000-0002-9081-2170
2015 (English)Manuscript (preprint) (Other academic)
Abstract [en]

We present an improved model and theory for time-causal and time-recursive spatio-temporal receptive fields, obtained by a combination of Gaussian receptive fields over the spatial domain and first-order integrators or equivalently truncated exponential filters coupled in cascade over the temporal domain. 

Compared to previous spatio-temporal scale-space formulations in terms of non-enhancement of local extrema or scale invariance, these receptive fields are based on different scale-space axiomatics over time by ensuring non-creation of new local extrema or zero-crossings with increasing temporal scale. Specifically, extensions are presented about (i) parameterizing the intermediate temporal scale levels, (ii) analysing the resulting temporal dynamics, (iii) transferring the theory to a discrete implementation in terms of recursive filters over time, (iv) computing scale-normalized spatio-temporal derivative expressions for spatio-temporal feature detection and (v) computational modelling of receptive fields in the lateral geniculate nucleus (LGN) and the primary visual cortex (V1) in biological vision. 

We show that by distributing the intermediate temporal scale levels according to a logarithmic distribution, we obtain a new family of temporal scale-space kernels with better temporal characteristics compared to a more traditional approach of using a uniform distribution of the intermediate temporal scale levels. Specifically, the new family of time-causal kernels has much faster temporal response properties (shorter temporal delays) compared to the kernels obtained from a uniform distribution. When increasing the number of temporal scale levels, the temporal scale-space kernels in the new family do also converge very rapidly to a limit kernel possessing true self-similar scale-invariant properties over temporal scales. Thereby, the new representation allows for true scale invariance over variations in the temporal scale, although the underlying temporal scale-space representation is based on a discretized temporal scale parameter. 

We show how scale-normalized temporal derivatives can be defined for these time-causal scale-space kernels and how the composed theory can be used for computing basic types of scale-normalized spatio-temporal derivative expressions in a computationally efficient manner.

Place, publisher, year, edition, pages
Keyword [en]
Scale space, Receptive field, Scale, Spatial, Temporal, Spatio-temporal, Scale-normalized derivative, Scale invariance, Differential invariant, Natural image transformations, Feature detection, Computer vision, Computational modelling, Biological vision
National Category
Computer Vision and Robotics (Autonomous Systems) Bioinformatics (Computational Biology) Mathematics
URN: urn:nbn:se:kth:diva-180666OAI: diva2:895714
Scale-space theory for invariant and covariant visual receptive fields
Swedish Research Council, 2014-4083

A shortened version of this paper is published in Journal of Mathematical Imaging and Vision, doi:10.1007/s10851-015-0613-9 Dec 2015 .

QC 20160121

Available from: 2016-01-19 Created: 2016-01-19 Last updated: 2016-02-01Bibliographically approved

Open Access in DiVA

fulltext(5789 kB)14 downloads
File information
File name FULLTEXT01.pdfFile size 5789 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Preprint at arXiv:1504.02648

Search in DiVA

By author/editor
Lindeberg, Tony
By organisation
Computational Biology, CB
Computer Vision and Robotics (Autonomous Systems)Bioinformatics (Computational Biology)Mathematics

Search outside of DiVA

GoogleGoogle Scholar
Total: 14 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

Total: 191 hits
ReferencesLink to record
Permanent link

Direct link