Time-causal and time-recursive spatio-temporal receptive fields

DOI10.1007/S10851-015-0613-9zbMATH Open1334.94034DBLPjournals/jmiv/Lindeberg16arXiv1504.02648OpenAlexW1734554626WikidataQ55899952 ScholiaQ55899952MaRDI QIDQ275337FDOQ275337

Authors: Tony Lindeberg 

Publication date: 25 April 2016

Published in: Journal of Mathematical Imaging and Vision (Search for Journal in Brave)

Abstract: We present an improved model and theory for time-causal and time-recursive spatio-temporal receptive fields, based on 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, (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 much faster temporal response properties (shorter temporal delays) compared to a uniform distribution. Specifically, these kernels converge very rapidly to a limit kernel possessing true self-similar scale-invariant properties over temporal scales, thereby allowing 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.

Full work available at URL: https://arxiv.org/abs/1504.02648

Recommendations

• Separable time-causal and time-recursive spatio-temporal receptive fields
• scientific article; zbMATH DE number 1796933
• Generalized Gaussian scale-space axiomatics comprising linear scale-space, affine scale-space and spatio-temporal scale-space
• A time-causal and time-recursive scale-covariant scale-space representation of temporal signals and past time
• Scale-time

zbMATH Keywords

scale invariancebiological visioncomputational modellingcomputer visiondifferential invariantfeature detectionnatural image transformationsreceptive fieldscale spacescale-normalized derivativespatio-temporal

Mathematics Subject Classification ID

Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Machine vision and scene understanding (68T45)

Cites Work

• Title not available (Why is that?)
• Ten Lectures on Wavelets
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Axioms and fundamental equations of image processing
• Title not available (Why is that?)
• Scale-time
• Evidence for a generalized Laguerre transform of temporal events by the visual system
• On the simulation of large populations of neurons.
• Geometry-driven diffusion in computer vision
• Generalized Gaussian scale-space axiomatics comprising linear scale-space, affine scale-space and spatio-temporal scale-space
• A cortical-inspired geometry for contour perception and motion integration
• On the axioms of scale space theory
• Left-invariant evolutions of wavelet transforms on the similitude group
• Notes on discrete Gaussian scale space
• Image matching using generalized scale-space interest points
• The monogenic scale-space: a unifying approach to phase-based image processing in scale-space
• Scale selection properties of generalized scale-space interest point detectors
• Temporal scale spaces
• Time-causal and time-recursive spatio-temporal receptive fields
• Title not available (Why is that?)
• Scale-space theory for auditory signals
• Separable time-causal and time-recursive spatio-temporal receptive fields
• Wavelets and their Applications
• Uniqueness of the Gaussian Kernel for Scale-Space Filtering
• Scaling Theorems for Zero Crossings
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Continuous and Discrete Wavelet Transforms
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Learning the Lie Groups of Visual Invariance
• On Totally Positive Functions, LaPlace Integrals and Entire Functions of the LaGuerre-Polya-Schur Type
• Title not available (Why is that?)
• Title not available (Why is that?)
• On smoothing operations and their generating functions
• Linear scale-space has first been proposed in Japan
• A computational theory of visual receptive fields
• The structure of images
• Receptive field families

Cited In (15)

• Time-causal and time-recursive spatio-temporal receptive fields
• A computational theory of visual receptive fields
• Spatio-temporal scale selection in video data
• Temporal scale selection in time-causal scale space
• A time-causal and time-recursive scale-covariant scale-space representation of temporal signals and past time
• Local image structure and Procrustes metrics
• Spatiotemporal kernel of a three-component differential equation model with self-control mechanism in vision
• Generalized Gaussian scale-space axiomatics comprising linear scale-space, affine scale-space and spatio-temporal scale-space
• Scale-space theory for auditory signals
• Separable time-causal and time-recursive spatio-temporal receptive fields
• Provably scale-covariant continuous hierarchical networks based on scale-normalized differential expressions coupled in cascade
• Dynamic texture recognition using time-causal and time-recursive spatio-temporal receptive fields
• Dense scale selection over space, time, and space-time
• Local spatio-temporal representation using the 3D shearlet transform
• Emergence of spatiotemporal receptive fields and its application to motion detection

This page was built for publication: Time-causal and time-recursive spatio-temporal receptive fields

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q275337)