Weighting observations: The use of kinematic models in object tracking

K. Nickels; S. Hutchinson

doi:10.1109/ROBOT.1998.677401

Weighting observations: The use of kinematic models in object tracking

K. Nickels, S. Hutchinson

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We describe a model-based object tracking system that updates the configuration parameters of an object model based upon information gathered from a sequence of monocular images. Realistic object and imaging models are used to determine the expected visibility of object features, and to determine the expected appearance of all visible features. We formulate the tracking problem as one of parameter estimation from partially observed data, and apply the extended Kalman filtering (EKF) algorithm. The models are also used to determine what point feature movement reveals about the configuration parameters of the object. This information is used by the EKF to update estimates for parameters, and for the uncertainty in the current estimates, based on observations of point features in monocular images.

Original language	English (US)
Title of host publication	Proceedings - 1998 IEEE International Conference on Robotics and Automation, ICRA 1998
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1677-1682
Number of pages	6
ISBN (Print)	078034300X
DOIs	https://doi.org/10.1109/ROBOT.1998.677401
State	Published - 1998
Externally published	Yes
Event	15th IEEE International Conference on Robotics and Automation, ICRA 1998 - Leuven, Belgium Duration: May 16 1998 → May 20 1998

Publication series

Name	Proceedings - IEEE International Conference on Robotics and Automation
Volume	2
ISSN (Print)	1050-4729

Other

Other	15th IEEE International Conference on Robotics and Automation, ICRA 1998
Country/Territory	Belgium
City	Leuven
Period	5/16/98 → 5/20/98

ASJC Scopus subject areas

Software
Artificial Intelligence
Electrical and Electronic Engineering
Control and Systems Engineering

Online availability

10.1109/ROBOT.1998.677401

Library availability

Discover UIUC Full Text

Cite this

Nickels, K., & Hutchinson, S. (1998). Weighting observations: The use of kinematic models in object tracking. In Proceedings - 1998 IEEE International Conference on Robotics and Automation, ICRA 1998 (pp. 1677-1682). Article 677401 (Proceedings - IEEE International Conference on Robotics and Automation; Vol. 2). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ROBOT.1998.677401

Weighting observations: The use of kinematic models in object tracking. / Nickels, K.; Hutchinson, S.
Proceedings - 1998 IEEE International Conference on Robotics and Automation, ICRA 1998. Institute of Electrical and Electronics Engineers Inc., 1998. p. 1677-1682 677401 (Proceedings - IEEE International Conference on Robotics and Automation; Vol. 2).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Nickels, K & Hutchinson, S 1998, Weighting observations: The use of kinematic models in object tracking. in Proceedings - 1998 IEEE International Conference on Robotics and Automation, ICRA 1998., 677401, Proceedings - IEEE International Conference on Robotics and Automation, vol. 2, Institute of Electrical and Electronics Engineers Inc., pp. 1677-1682, 15th IEEE International Conference on Robotics and Automation, ICRA 1998, Leuven, Belgium, 5/16/98. https://doi.org/10.1109/ROBOT.1998.677401

Nickels K, Hutchinson S. Weighting observations: The use of kinematic models in object tracking. In Proceedings - 1998 IEEE International Conference on Robotics and Automation, ICRA 1998. Institute of Electrical and Electronics Engineers Inc. 1998. p. 1677-1682. 677401. (Proceedings - IEEE International Conference on Robotics and Automation). doi: 10.1109/ROBOT.1998.677401

@inproceedings{4522fe12fb8e4528875392291f074e2a,

title = "Weighting observations: The use of kinematic models in object tracking",

abstract = "We describe a model-based object tracking system that updates the configuration parameters of an object model based upon information gathered from a sequence of monocular images. Realistic object and imaging models are used to determine the expected visibility of object features, and to determine the expected appearance of all visible features. We formulate the tracking problem as one of parameter estimation from partially observed data, and apply the extended Kalman filtering (EKF) algorithm. The models are also used to determine what point feature movement reveals about the configuration parameters of the object. This information is used by the EKF to update estimates for parameters, and for the uncertainty in the current estimates, based on observations of point features in monocular images.",

author = "K. Nickels and S. Hutchinson",

note = "Publisher Copyright: {\textcopyright} 1998 IEEE.; 15th IEEE International Conference on Robotics and Automation, ICRA 1998 ; Conference date: 16-05-1998 Through 20-05-1998",

year = "1998",

doi = "10.1109/ROBOT.1998.677401",

language = "English (US)",

isbn = "078034300X",

series = "Proceedings - IEEE International Conference on Robotics and Automation",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1677--1682",

booktitle = "Proceedings - 1998 IEEE International Conference on Robotics and Automation, ICRA 1998",

address = "United States",

}

TY - GEN

T1 - Weighting observations

T2 - 15th IEEE International Conference on Robotics and Automation, ICRA 1998

AU - Nickels, K.

AU - Hutchinson, S.

PY - 1998

Y1 - 1998

N2 - We describe a model-based object tracking system that updates the configuration parameters of an object model based upon information gathered from a sequence of monocular images. Realistic object and imaging models are used to determine the expected visibility of object features, and to determine the expected appearance of all visible features. We formulate the tracking problem as one of parameter estimation from partially observed data, and apply the extended Kalman filtering (EKF) algorithm. The models are also used to determine what point feature movement reveals about the configuration parameters of the object. This information is used by the EKF to update estimates for parameters, and for the uncertainty in the current estimates, based on observations of point features in monocular images.

AB - We describe a model-based object tracking system that updates the configuration parameters of an object model based upon information gathered from a sequence of monocular images. Realistic object and imaging models are used to determine the expected visibility of object features, and to determine the expected appearance of all visible features. We formulate the tracking problem as one of parameter estimation from partially observed data, and apply the extended Kalman filtering (EKF) algorithm. The models are also used to determine what point feature movement reveals about the configuration parameters of the object. This information is used by the EKF to update estimates for parameters, and for the uncertainty in the current estimates, based on observations of point features in monocular images.

UR - http://www.scopus.com/inward/record.url?scp=0031640848&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031640848&partnerID=8YFLogxK

U2 - 10.1109/ROBOT.1998.677401

DO - 10.1109/ROBOT.1998.677401

M3 - Conference contribution

AN - SCOPUS:0031640848

SN - 078034300X

T3 - Proceedings - IEEE International Conference on Robotics and Automation

SP - 1677

EP - 1682

BT - Proceedings - 1998 IEEE International Conference on Robotics and Automation, ICRA 1998

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 16 May 1998 through 20 May 1998

ER -

Weighting observations: The use of kinematic models in object tracking

Abstract

Publication series

Other

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this