Feature point tracking for incomplete trajectories

D. Chetverikov, Judit Verestóy

Research output: Contribution to journalArticle

54 Citations (Scopus)

Abstract

A new algorithm is presented for feature point based motion tracking in long image sequences. Dynamic scenes with multiple, independently moving objects are considered in which feature points may temporarily disappear, enter and leave the view field. This situation is typical for surveillance and scene monitoring applications. Most of the existing approaches to feature point tracking have limited capabilities in handling incomplete trajectories, especially when the number of points and their speeds are large, and trajectory ambiguities are frequent. The proposed algorithm was designed to efficiently resolve these ambiguities. Correspondences between moving points are established in a competitive linking process that develops as the trajectories grow. Appearing and disappearing points are treated in a natural way as the points that do not link. The proposed algorithm compares favorably to efficient alternative algorithms selected and tested in a performance evaluation study.

Original languageEnglish
Pages (from-to)321-338
Number of pages18
JournalComputing
Volume62
Issue number4
DOIs
Publication statusPublished - 1999

Fingerprint

Feature Point
Trajectories
Trajectory
Motion Tracking
Image Sequence
Moving Objects
Surveillance
Linking
Performance Evaluation
Resolve
Correspondence
Monitoring
Alternatives
Ambiguity

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Theoretical Computer Science

Cite this

Feature point tracking for incomplete trajectories. / Chetverikov, D.; Verestóy, Judit.

In: Computing, Vol. 62, No. 4, 1999, p. 321-338.

Research output: Contribution to journalArticle

Chetverikov, D. ; Verestóy, Judit. / Feature point tracking for incomplete trajectories. In: Computing. 1999 ; Vol. 62, No. 4. pp. 321-338.
@article{bf572e8b62a64baf925d07a9da21edd8,
title = "Feature point tracking for incomplete trajectories",
abstract = "A new algorithm is presented for feature point based motion tracking in long image sequences. Dynamic scenes with multiple, independently moving objects are considered in which feature points may temporarily disappear, enter and leave the view field. This situation is typical for surveillance and scene monitoring applications. Most of the existing approaches to feature point tracking have limited capabilities in handling incomplete trajectories, especially when the number of points and their speeds are large, and trajectory ambiguities are frequent. The proposed algorithm was designed to efficiently resolve these ambiguities. Correspondences between moving points are established in a competitive linking process that develops as the trajectories grow. Appearing and disappearing points are treated in a natural way as the points that do not link. The proposed algorithm compares favorably to efficient alternative algorithms selected and tested in a performance evaluation study.",
author = "D. Chetverikov and Judit Verest{\'o}y",
year = "1999",
doi = "10.1007/s006070050027",
language = "English",
volume = "62",
pages = "321--338",
journal = "Computing (Vienna/New York)",
issn = "0010-485X",
publisher = "Springer Wien",
number = "4",

}

TY - JOUR

T1 - Feature point tracking for incomplete trajectories

AU - Chetverikov, D.

AU - Verestóy, Judit

PY - 1999

Y1 - 1999

N2 - A new algorithm is presented for feature point based motion tracking in long image sequences. Dynamic scenes with multiple, independently moving objects are considered in which feature points may temporarily disappear, enter and leave the view field. This situation is typical for surveillance and scene monitoring applications. Most of the existing approaches to feature point tracking have limited capabilities in handling incomplete trajectories, especially when the number of points and their speeds are large, and trajectory ambiguities are frequent. The proposed algorithm was designed to efficiently resolve these ambiguities. Correspondences between moving points are established in a competitive linking process that develops as the trajectories grow. Appearing and disappearing points are treated in a natural way as the points that do not link. The proposed algorithm compares favorably to efficient alternative algorithms selected and tested in a performance evaluation study.

AB - A new algorithm is presented for feature point based motion tracking in long image sequences. Dynamic scenes with multiple, independently moving objects are considered in which feature points may temporarily disappear, enter and leave the view field. This situation is typical for surveillance and scene monitoring applications. Most of the existing approaches to feature point tracking have limited capabilities in handling incomplete trajectories, especially when the number of points and their speeds are large, and trajectory ambiguities are frequent. The proposed algorithm was designed to efficiently resolve these ambiguities. Correspondences between moving points are established in a competitive linking process that develops as the trajectories grow. Appearing and disappearing points are treated in a natural way as the points that do not link. The proposed algorithm compares favorably to efficient alternative algorithms selected and tested in a performance evaluation study.

UR - http://www.scopus.com/inward/record.url?scp=0032686937&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032686937&partnerID=8YFLogxK

U2 - 10.1007/s006070050027

DO - 10.1007/s006070050027

M3 - Article

AN - SCOPUS:0032686937

VL - 62

SP - 321

EP - 338

JO - Computing (Vienna/New York)

JF - Computing (Vienna/New York)

SN - 0010-485X

IS - 4

ER -