Motion recovery of moving objects under perspective stereo vision

Hiroyuki Kano, Hiroyuki Fujioka, Xinkai Chen, Takehito Sato

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We consider a problem of recovering motion of an object moving in space under perspective observation. It is assumed that the motion equation is described by a linear system with unknown constant motion parameters and that a single feature point on the object is perspectively observed by two cameras. Then we analyze the identifiability of motion parameters from the stereo image data observed over an interval of time. The identifiability problem is solved by employing theories on linear dynamical systems, and the condition, established as a necessary and sufficient condition, turns out to be the controllability of a modified linear system. Such an analysis is essential when we develop and use any algorithms involving motion parameter identification. Finally, we include numerical results by employing the extended Kalman filter.

Original languageEnglish
Title of host publicationProceedings of the IASTED International Conference on Modelling, Identification and Control
EditorsM.H. Hamza
Pages103-108
Number of pages6
Volume23
Publication statusPublished - 2004
Externally publishedYes
EventProceedings of the 23rd IASTED International Conference on Modelling, Identification, and Control - Grindelwald, Switzerland
Duration: 2004 Feb 232004 Feb 25

Other

OtherProceedings of the 23rd IASTED International Conference on Modelling, Identification, and Control
CountrySwitzerland
CityGrindelwald
Period04/2/2304/2/25

Fingerprint

Stereo vision
Linear systems
Recovery
Extended Kalman filters
Controllability
Equations of motion
Identification (control systems)
Dynamical systems
Cameras

Keywords

  • Controllability
  • Machine vision
  • Motion recovery
  • Perspective stereo vision

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Kano, H., Fujioka, H., Chen, X., & Sato, T. (2004). Motion recovery of moving objects under perspective stereo vision. In M. H. Hamza (Ed.), Proceedings of the IASTED International Conference on Modelling, Identification and Control (Vol. 23, pp. 103-108). [412-224]

Motion recovery of moving objects under perspective stereo vision. / Kano, Hiroyuki; Fujioka, Hiroyuki; Chen, Xinkai; Sato, Takehito.

Proceedings of the IASTED International Conference on Modelling, Identification and Control. ed. / M.H. Hamza. Vol. 23 2004. p. 103-108 412-224.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kano, H, Fujioka, H, Chen, X & Sato, T 2004, Motion recovery of moving objects under perspective stereo vision. in MH Hamza (ed.), Proceedings of the IASTED International Conference on Modelling, Identification and Control. vol. 23, 412-224, pp. 103-108, Proceedings of the 23rd IASTED International Conference on Modelling, Identification, and Control, Grindelwald, Switzerland, 04/2/23.
Kano H, Fujioka H, Chen X, Sato T. Motion recovery of moving objects under perspective stereo vision. In Hamza MH, editor, Proceedings of the IASTED International Conference on Modelling, Identification and Control. Vol. 23. 2004. p. 103-108. 412-224
Kano, Hiroyuki ; Fujioka, Hiroyuki ; Chen, Xinkai ; Sato, Takehito. / Motion recovery of moving objects under perspective stereo vision. Proceedings of the IASTED International Conference on Modelling, Identification and Control. editor / M.H. Hamza. Vol. 23 2004. pp. 103-108
@inproceedings{eaab3b6e1b5549bdb818c83bfcff47fe,
title = "Motion recovery of moving objects under perspective stereo vision",
abstract = "We consider a problem of recovering motion of an object moving in space under perspective observation. It is assumed that the motion equation is described by a linear system with unknown constant motion parameters and that a single feature point on the object is perspectively observed by two cameras. Then we analyze the identifiability of motion parameters from the stereo image data observed over an interval of time. The identifiability problem is solved by employing theories on linear dynamical systems, and the condition, established as a necessary and sufficient condition, turns out to be the controllability of a modified linear system. Such an analysis is essential when we develop and use any algorithms involving motion parameter identification. Finally, we include numerical results by employing the extended Kalman filter.",
keywords = "Controllability, Machine vision, Motion recovery, Perspective stereo vision",
author = "Hiroyuki Kano and Hiroyuki Fujioka and Xinkai Chen and Takehito Sato",
year = "2004",
language = "English",
volume = "23",
pages = "103--108",
editor = "M.H. Hamza",
booktitle = "Proceedings of the IASTED International Conference on Modelling, Identification and Control",

}

TY - GEN

T1 - Motion recovery of moving objects under perspective stereo vision

AU - Kano, Hiroyuki

AU - Fujioka, Hiroyuki

AU - Chen, Xinkai

AU - Sato, Takehito

PY - 2004

Y1 - 2004

N2 - We consider a problem of recovering motion of an object moving in space under perspective observation. It is assumed that the motion equation is described by a linear system with unknown constant motion parameters and that a single feature point on the object is perspectively observed by two cameras. Then we analyze the identifiability of motion parameters from the stereo image data observed over an interval of time. The identifiability problem is solved by employing theories on linear dynamical systems, and the condition, established as a necessary and sufficient condition, turns out to be the controllability of a modified linear system. Such an analysis is essential when we develop and use any algorithms involving motion parameter identification. Finally, we include numerical results by employing the extended Kalman filter.

AB - We consider a problem of recovering motion of an object moving in space under perspective observation. It is assumed that the motion equation is described by a linear system with unknown constant motion parameters and that a single feature point on the object is perspectively observed by two cameras. Then we analyze the identifiability of motion parameters from the stereo image data observed over an interval of time. The identifiability problem is solved by employing theories on linear dynamical systems, and the condition, established as a necessary and sufficient condition, turns out to be the controllability of a modified linear system. Such an analysis is essential when we develop and use any algorithms involving motion parameter identification. Finally, we include numerical results by employing the extended Kalman filter.

KW - Controllability

KW - Machine vision

KW - Motion recovery

KW - Perspective stereo vision

UR - http://www.scopus.com/inward/record.url?scp=11844255695&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=11844255695&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:11844255695

VL - 23

SP - 103

EP - 108

BT - Proceedings of the IASTED International Conference on Modelling, Identification and Control

A2 - Hamza, M.H.

ER -