Hierarchical Construction of Orientation and Velocity Selective Filters

Authors:
D. J. Fleet;A. D. Jepson
Affiliations:
Univ. of Toronto, Ont., Canada;Univ. of Toronto, Ont., Canada
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
1989

Citing 2
Cited 6

Digital Signal Processing

Digital Signal Processing
A representation for visual information with application to machine vision

A representation for visual information with application to machine vision

Multidimensional Orientation Estimation with Applications to Texture Analysis and Optical Flow

IEEE Transactions on Pattern Analysis and Machine Intelligence
Recursive Filters for Optical Flow

IEEE Transactions on Pattern Analysis and Machine Intelligence
Affine Invariant Texture Segmentation and Shape from Texture by Variational Methods

Journal of Mathematical Imaging and Vision
A Group-Theoretic Construction with Spatiotemporal Wavelets for the Analysis of Rotational Motion

Journal of Mathematical Imaging and Vision
Frequency Domain Analysis of Translations with Piecewise Cubic Trajectories

IEEE Transactions on Pattern Analysis and Machine Intelligence
The Hermite transform as an efficient model for local image analysis: An application to medical image fusion

Computers and Electrical Engineering

Quantified Score

Hi-index	0.14

Visualization

Abstract

As a step towards the early measurement of visual primitives, the authors outline design criteria for the extraction of orientation and velocity information, and present a variety of tools useful in the construction of simple linear filters. A hierarchical parallel-processing scheme is used in which nodes compute a weighted sum of inputs from within a small spatio-temporal neighborhood. The resulting scheme is easily analyzed and provides mechanisms sensitive to narrow ranges of both image velocity and orientation. The hierarchical approach in combination with separability in the first levels yields an efficient implementation.