Temporal Analysis of Motion in Video Sequences through Predictive Operators

Philippe Burlina, Rama Chellappa

Research output: Contribution to journalArticle

Abstract

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

Original languageEnglish (US)
Pages (from-to)175-192
Number of pages18
JournalInternational Journal of Computer Vision
Volume28
Issue number2
DOIs
StatePublished - Jan 1 1998
Externally publishedYes

Fingerprint

Polynomials
Parameter estimation

Keywords

  • Alternate motion/structure representations
  • Motion prediction and estimation
  • Predictive operators
  • Time-to-collision
  • Visual guidance

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Temporal Analysis of Motion in Video Sequences through Predictive Operators. / Burlina, Philippe; Chellappa, Rama.

In: International Journal of Computer Vision, Vol. 28, No. 2, 01.01.1998, p. 175-192.

Research output: Contribution to journalArticle

Burlina, Philippe ; Chellappa, Rama. / Temporal Analysis of Motion in Video Sequences through Predictive Operators. In: International Journal of Computer Vision. 1998 ; Vol. 28, No. 2. pp. 175-192.
@article{ba0f9392a41c49f58acc110a3ed98f36,
title = "Temporal Analysis of Motion in Video Sequences through Predictive Operators",
abstract = "We study the problem of recovering temporal parameters which act as predictive operators, generalize time-to-collision and have direct interpretation for navigational purposes for piecewise arbitrarily smooth (polynomial) motion. A result stating that, for monocular observers undergoing arbitrary polynomial laws, these parameters are visually observable, is presented in the first part of this paper. This property suggests an alternate temporal representation of visual looming information. The second part of this paper is concerned with algorithmic approaches for environments with maneuvering agents. A method addressing model order determination, collision detection, and temporal parameter estimation is proposed. Experimental results are reported.",
keywords = "Alternate motion/structure representations, Motion prediction and estimation, Predictive operators, Time-to-collision, Visual guidance",
author = "Philippe Burlina and Rama Chellappa",
year = "1998",
month = "1",
day = "1",
doi = "10.1023/A:1008067101494",
language = "English (US)",
volume = "28",
pages = "175--192",
journal = "International Journal of Computer Vision",
issn = "0920-5691",
publisher = "Springer Netherlands",
number = "2",

}

TY - JOUR

T1 - Temporal Analysis of Motion in Video Sequences through Predictive Operators

AU - Burlina, Philippe

AU - Chellappa, Rama

PY - 1998/1/1

Y1 - 1998/1/1

N2 - We study the problem of recovering temporal parameters which act as predictive operators, generalize time-to-collision and have direct interpretation for navigational purposes for piecewise arbitrarily smooth (polynomial) motion. A result stating that, for monocular observers undergoing arbitrary polynomial laws, these parameters are visually observable, is presented in the first part of this paper. This property suggests an alternate temporal representation of visual looming information. The second part of this paper is concerned with algorithmic approaches for environments with maneuvering agents. A method addressing model order determination, collision detection, and temporal parameter estimation is proposed. Experimental results are reported.

AB - We study the problem of recovering temporal parameters which act as predictive operators, generalize time-to-collision and have direct interpretation for navigational purposes for piecewise arbitrarily smooth (polynomial) motion. A result stating that, for monocular observers undergoing arbitrary polynomial laws, these parameters are visually observable, is presented in the first part of this paper. This property suggests an alternate temporal representation of visual looming information. The second part of this paper is concerned with algorithmic approaches for environments with maneuvering agents. A method addressing model order determination, collision detection, and temporal parameter estimation is proposed. Experimental results are reported.

KW - Alternate motion/structure representations

KW - Motion prediction and estimation

KW - Predictive operators

KW - Time-to-collision

KW - Visual guidance

UR - http://www.scopus.com/inward/record.url?scp=0032094343&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032094343&partnerID=8YFLogxK

U2 - 10.1023/A:1008067101494

DO - 10.1023/A:1008067101494

M3 - Article

AN - SCOPUS:0032094343

VL - 28

SP - 175

EP - 192

JO - International Journal of Computer Vision

JF - International Journal of Computer Vision

SN - 0920-5691

IS - 2

ER -