Improving feature tracking with robust statistics

A. Fusiello, E. Trucco, T. Tommasini, V. Roberto

Research output: Contribution to journalArticle

Abstract

This paper addresses robust feature tracking. The aim is to track point features in a sequence of images and to identify unreliable features resulting from occlusions, perspective distortions and strong intensity changes. We extend the well-known Shi-Tomasi-Kanade tracker by introducing an automatic scheme for rejecting spurious features. We employ a simple and efficient outliers rejection rule, called X84, and prove that its theoretical assumptions are satisfied in the feature tracking scenario. Experiments with real and synthetic images confirm that our algorithm consistently discards unreliable features; we show a quantitative example of the benefits introduced by the algorithm for the case of fundamental matrix estimation. The complete code of the robust tracker is available via ftp. © 1999 Springer-Verlag London Limited.

Original languageEnglish
Pages (from-to)312-320
Number of pages9
JournalPattern Analysis and Applications
Volume2
Issue number4
Publication statusPublished - 1999

Fingerprint

Statistics
Experiments

Keywords

  • Feature tracking
  • Motion analysis
  • Optical flow
  • Registration
  • Robust statistics
  • X84

Cite this

Fusiello, A., Trucco, E., Tommasini, T., & Roberto, V. (1999). Improving feature tracking with robust statistics. Pattern Analysis and Applications, 2(4), 312-320.
Fusiello, A. ; Trucco, E. ; Tommasini, T. ; Roberto, V. / Improving feature tracking with robust statistics. In: Pattern Analysis and Applications. 1999 ; Vol. 2, No. 4. pp. 312-320.
@article{17b9f30100674aad971dc1567bbe28d8,
title = "Improving feature tracking with robust statistics",
abstract = "This paper addresses robust feature tracking. The aim is to track point features in a sequence of images and to identify unreliable features resulting from occlusions, perspective distortions and strong intensity changes. We extend the well-known Shi-Tomasi-Kanade tracker by introducing an automatic scheme for rejecting spurious features. We employ a simple and efficient outliers rejection rule, called X84, and prove that its theoretical assumptions are satisfied in the feature tracking scenario. Experiments with real and synthetic images confirm that our algorithm consistently discards unreliable features; we show a quantitative example of the benefits introduced by the algorithm for the case of fundamental matrix estimation. The complete code of the robust tracker is available via ftp. {\circledC} 1999 Springer-Verlag London Limited.",
keywords = "Feature tracking, Motion analysis, Optical flow, Registration, Robust statistics, X84",
author = "A. Fusiello and E. Trucco and T. Tommasini and V. Roberto",
year = "1999",
language = "English",
volume = "2",
pages = "312--320",
journal = "Pattern Analysis and Applications",
issn = "1433-7541",
publisher = "Springer",
number = "4",

}

Fusiello, A, Trucco, E, Tommasini, T & Roberto, V 1999, 'Improving feature tracking with robust statistics', Pattern Analysis and Applications, vol. 2, no. 4, pp. 312-320.

Improving feature tracking with robust statistics. / Fusiello, A.; Trucco, E.; Tommasini, T.; Roberto, V.

In: Pattern Analysis and Applications, Vol. 2, No. 4, 1999, p. 312-320.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Improving feature tracking with robust statistics

AU - Fusiello, A.

AU - Trucco, E.

AU - Tommasini, T.

AU - Roberto, V.

PY - 1999

Y1 - 1999

N2 - This paper addresses robust feature tracking. The aim is to track point features in a sequence of images and to identify unreliable features resulting from occlusions, perspective distortions and strong intensity changes. We extend the well-known Shi-Tomasi-Kanade tracker by introducing an automatic scheme for rejecting spurious features. We employ a simple and efficient outliers rejection rule, called X84, and prove that its theoretical assumptions are satisfied in the feature tracking scenario. Experiments with real and synthetic images confirm that our algorithm consistently discards unreliable features; we show a quantitative example of the benefits introduced by the algorithm for the case of fundamental matrix estimation. The complete code of the robust tracker is available via ftp. © 1999 Springer-Verlag London Limited.

AB - This paper addresses robust feature tracking. The aim is to track point features in a sequence of images and to identify unreliable features resulting from occlusions, perspective distortions and strong intensity changes. We extend the well-known Shi-Tomasi-Kanade tracker by introducing an automatic scheme for rejecting spurious features. We employ a simple and efficient outliers rejection rule, called X84, and prove that its theoretical assumptions are satisfied in the feature tracking scenario. Experiments with real and synthetic images confirm that our algorithm consistently discards unreliable features; we show a quantitative example of the benefits introduced by the algorithm for the case of fundamental matrix estimation. The complete code of the robust tracker is available via ftp. © 1999 Springer-Verlag London Limited.

KW - Feature tracking

KW - Motion analysis

KW - Optical flow

KW - Registration

KW - Robust statistics

KW - X84

UR - http://www.scopus.com/inward/record.url?scp=0033444570&partnerID=8YFLogxK

M3 - Article

VL - 2

SP - 312

EP - 320

JO - Pattern Analysis and Applications

JF - Pattern Analysis and Applications

SN - 1433-7541

IS - 4

ER -

Fusiello A, Trucco E, Tommasini T, Roberto V. Improving feature tracking with robust statistics. Pattern Analysis and Applications. 1999;2(4):312-320.