Temporal Analysis of Motion in Video Sequences through Predictive Operators

Authors:
Philippe Burlina;Rama Chellappa
Affiliations:
Computer Vision Laboratory, University of Maryland, College Park, MD 20742-3275. E-mail: burlina@cfar.umd.edu, rama@cfar.umd.edu;Computer Vision Laboratory, University of Maryland, College Park, MD 20742-3275. E-mail: burlina@cfar.umd.edu, rama@cfar.umd.edu
Venue:
International Journal of Computer Vision
Year:
1998

Citing 9
Cited 2

Apparent area of a rigid moving body

Image and Vision Computing - Special issue: papers from the second Alvey Vision Conference
Tracking and data association

Tracking and data association
Obstacle Avoidance Using Flow Field Divergence

IEEE Transactions on Pattern Analysis and Machine Intelligence
Bounds on time-to-collision and rotational component from first-order derivatives of image flow

Computer Vision, Graphics, and Image Processing
Derivation of qualitative information in motion analysis

Image and Vision Computing - Special issue on the first ECCV 1990
Active Visual Inference of Surface Shape

Active Visual Inference of Surface Shape
On the Advantages of Polar and Log-Polar Mapping for Direct Estimation of Time-To-Impact from Optical Flow

IEEE Transactions on Pattern Analysis and Machine Intelligence
Electronic image stabilization using multiple visual cues

ICIP '95 Proceedings of the 1995 International Conference on Image Processing (Vol. 1)-Volume 1 - Volume 1
Green Theorems and Qualitative Properties of the Optical Flow

Green Theorems and Qualitative Properties of the Optical Flow

The Applicability of Green‘s Theorem to Computation of Rate of Approach

International Journal of Computer Vision
Automated visual surveillance in computer vision

AMTA'09 Proceedings of the 10th WSEAS international conference on Acoustics & music: theory & applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

We study the problem of recovering temporal parameterswhich act as predictiveoperators, generalize time-to-collision and have direct interpretation for navigational purposes for piecewise arbitrarilysmooth (polynomial) motion.A result stating that, for monocular observers undergoing arbitrarypolynomial laws, these parameters are visually observable, ispresented in the first part of this paper.This property suggests an alternate temporal representation of visual looming information.The second part of thispaper is concerned with algorithmic approaches for environments withmaneuvering agents. Amethod addressing model order determination, collision detection, andtemporal parameter estimation is proposed. Experimental results are reported.