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

Tony Lindeberg

SSVM 2015: Scale Space and Variational Methods in Computer Vision, Springer LNCS vol 9087, pages 90-102, Lege Cap Ferret, France, May 31 - Jun 4, 2015.

Digitally published with DOI:10.1007/978-3-319-18461-6_8 in April 2015.

Abstract

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 parameterizing the intermediate temporal scale levels, analysing the resulting temporal dynamics and transferring the theory to a discrete implementation in terms of recursive filters over time.

PDF: (6.1 Mb)

On-line version: (At the official site of Springer LNCS)

PDF: (Longer journal paper with substantial extensions)

Background and related material: (Underlying computational theory for visual receptive fields) (General framework for invariant visual receptive fields under natural image transformations) (Underlying mathematical necessity results regarding scale covariant, affine covariant and Galilean covariant receptive fields)

---