Cited by 4,560Video Surveillance and Tracking MethodsAdvanced Image and Video Retrieval TechniquesInfrared Target Detection Methodologies

Kernel-based object tracking

Comaniciu, D., Ramesh, V., Meer, P.·2003·IEEE Transactions on Pattern Analysis and Machine Intelligence

Abstract

A new approach toward target representation and localization, the central component in visual tracking of nonrigid objects, is proposed. The feature histogram-based target representations are regularized by spatial masking with an isotropic kernel. The masking induces spatially-smooth similarity functions suitable for gradient-based optimization, hence, the target localization problem can be formulated using the basin of attraction of the local maxima. We employ a metric derived from the Bhattacharyya coefficient as similarity measure, and use the mean shift procedure to perform the optimization. In the presented tracking examples, the new method successfully coped with camera motion, partial occlusions, clutter, and target scale variations. Integration with motion filters and data association techniques is also discussed. We describe only a few of the potential applications: exploitation of background information, Kalman tracking using motion models, and face tracking.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tpami.2003.1195991

Cites

87 of 87 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Although object tracking has been studied for several decades, and much progress has been made in recent years, it remains a very challenging problem.

    “Although object tracking has been studied for several decades, and much progress has been made in recent years [28, 16, 47, 5, 40, 26, 19], it remains a very challenging problem.”

    From Object Tracking Benchmark (2015) · cites this paper as [16]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

1 of the 88 references couldn’t be matched to a known paper.

Cited by

Sorted by citations

Authors
Comaniciu, D., Ramesh, V., & Meer, P.
Affiliations
  • Siemens (United States) (US)
  • Institute of Electrical and Electronics Engineers (US)
  • Rutgers, The State University of New Jersey (US)
Venue
IEEE Transactions on Pattern Analysis and Machine Intelligence
Published
2003-05
Volume
25
Issue
5
Pages
564-577
ISSN
0162-8828 (ISSN-L)
OpenAlex
W2132103241
Cited by
4,560
References
88
Citations by year
2026: 14 · 2025: 23 · 2024: 47 · 2023: 46 · 2022: 51 · 2021: 96 · 2020: 108 · 2019: 150 · 2018: 181 · 2017: 224 · 2016: 270 · 2015: 336 · 2014: 397 · 2013: 363 · 2012: 379
FWCI
134.18
Type
journal article
Language
en
Open access
closed
Locations
IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
  • Physical Sciences › Engineering › Aerospace Engineering › Infrared Target Detection Methodologies
Keywords
object tracking, kernel-based regularization, feature histograms, spatial masking, isotropic kernels, Bhattacharyya coefficient, mean shift, target localization, camera movement, partial occlusion, target scale variation, data association, face tracking

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review