Keeping your eye on the ball: Tracking occluding contours of unfamiliar objects without distraction

Kentaro Toyama, Gregory Hager

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

Abstract

Visual tracking is prone to distractions, where features similar to the target features guide the tracker away from its intended object. Global shape models and dynamic models are necessary for completely distraction-free contour tracking, but there are cases when component feature trackers alone can be expected to avoid distraction. We define the tracking problem in general and devise a method for local, window-based, feature trackers to track accurately in spite of background distractions. The algorithm is applied to a generic line tracker and a snake-like contour tracker which are then analyzed with respect to previous contour-trackers. We discuss the advantages and disadvantages of our approach and suggest that existing model-based trackers can be improved by incorporating similar techniques at the local level.

Original languageEnglish (US)
Title of host publicationIEEE International Conference on Intelligent Robots and Systems
Editors Anon
PublisherIEEE
Pages354-359
Number of pages6
Volume1
StatePublished - 1995
Externally publishedYes
EventProceedings of the 1995 IEEE/RSJ International Conference on Intelligent Robots and Systems. Part 3 (of 3) - Pittsburgh, PA, USA
Duration: Aug 5 1995Aug 9 1995

Other

OtherProceedings of the 1995 IEEE/RSJ International Conference on Intelligent Robots and Systems. Part 3 (of 3)
CityPittsburgh, PA, USA
Period8/5/958/9/95

Fingerprint

Dynamic models

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

Toyama, K., & Hager, G. (1995). Keeping your eye on the ball: Tracking occluding contours of unfamiliar objects without distraction. In Anon (Ed.), IEEE International Conference on Intelligent Robots and Systems (Vol. 1, pp. 354-359). IEEE.

Keeping your eye on the ball : Tracking occluding contours of unfamiliar objects without distraction. / Toyama, Kentaro; Hager, Gregory.

IEEE International Conference on Intelligent Robots and Systems. ed. / Anon. Vol. 1 IEEE, 1995. p. 354-359.

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

Toyama, K & Hager, G 1995, Keeping your eye on the ball: Tracking occluding contours of unfamiliar objects without distraction. in Anon (ed.), IEEE International Conference on Intelligent Robots and Systems. vol. 1, IEEE, pp. 354-359, Proceedings of the 1995 IEEE/RSJ International Conference on Intelligent Robots and Systems. Part 3 (of 3), Pittsburgh, PA, USA, 8/5/95.
Toyama K, Hager G. Keeping your eye on the ball: Tracking occluding contours of unfamiliar objects without distraction. In Anon, editor, IEEE International Conference on Intelligent Robots and Systems. Vol. 1. IEEE. 1995. p. 354-359
Toyama, Kentaro ; Hager, Gregory. / Keeping your eye on the ball : Tracking occluding contours of unfamiliar objects without distraction. IEEE International Conference on Intelligent Robots and Systems. editor / Anon. Vol. 1 IEEE, 1995. pp. 354-359
@inproceedings{9bd08021f9a346dfadb4f20a23043da6,
title = "Keeping your eye on the ball: Tracking occluding contours of unfamiliar objects without distraction",
abstract = "Visual tracking is prone to distractions, where features similar to the target features guide the tracker away from its intended object. Global shape models and dynamic models are necessary for completely distraction-free contour tracking, but there are cases when component feature trackers alone can be expected to avoid distraction. We define the tracking problem in general and devise a method for local, window-based, feature trackers to track accurately in spite of background distractions. The algorithm is applied to a generic line tracker and a snake-like contour tracker which are then analyzed with respect to previous contour-trackers. We discuss the advantages and disadvantages of our approach and suggest that existing model-based trackers can be improved by incorporating similar techniques at the local level.",
author = "Kentaro Toyama and Gregory Hager",
year = "1995",
language = "English (US)",
volume = "1",
pages = "354--359",
editor = "Anon",
booktitle = "IEEE International Conference on Intelligent Robots and Systems",
publisher = "IEEE",

}

TY - GEN

T1 - Keeping your eye on the ball

T2 - Tracking occluding contours of unfamiliar objects without distraction

AU - Toyama, Kentaro

AU - Hager, Gregory

PY - 1995

Y1 - 1995

N2 - Visual tracking is prone to distractions, where features similar to the target features guide the tracker away from its intended object. Global shape models and dynamic models are necessary for completely distraction-free contour tracking, but there are cases when component feature trackers alone can be expected to avoid distraction. We define the tracking problem in general and devise a method for local, window-based, feature trackers to track accurately in spite of background distractions. The algorithm is applied to a generic line tracker and a snake-like contour tracker which are then analyzed with respect to previous contour-trackers. We discuss the advantages and disadvantages of our approach and suggest that existing model-based trackers can be improved by incorporating similar techniques at the local level.

AB - Visual tracking is prone to distractions, where features similar to the target features guide the tracker away from its intended object. Global shape models and dynamic models are necessary for completely distraction-free contour tracking, but there are cases when component feature trackers alone can be expected to avoid distraction. We define the tracking problem in general and devise a method for local, window-based, feature trackers to track accurately in spite of background distractions. The algorithm is applied to a generic line tracker and a snake-like contour tracker which are then analyzed with respect to previous contour-trackers. We discuss the advantages and disadvantages of our approach and suggest that existing model-based trackers can be improved by incorporating similar techniques at the local level.

UR - http://www.scopus.com/inward/record.url?scp=0029194646&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029194646&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0029194646

VL - 1

SP - 354

EP - 359

BT - IEEE International Conference on Intelligent Robots and Systems

A2 - Anon, null

PB - IEEE

ER -