Online object tracking: A benchmark

Yi Wu, Jongwoo Lim, Ming Hsuan Yang

Research output: Contribution to journalConference article

2344 Citations (Scopus)

Abstract

Object tracking is one of the most important components in numerous applications of computer vision. While much progress has been made in recent years with efforts on sharing code and datasets, it is of great importance to develop a library and benchmark to gauge the state of the art. After briefly reviewing recent advances of online object tracking, we carry out large scale experiments with various evaluation criteria to understand how these algorithms perform. The test image sequences are annotated with different attributes for performance evaluation and analysis. By analyzing quantitative results, we identify effective approaches for robust tracking and provide potential future research directions in this field.

Original languageEnglish
Article number6619156
Pages (from-to)2411-2418
Number of pages8
JournalProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
DOIs
Publication statusPublished - 2013 Nov 15
Event26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2013 - Portland, OR, United States
Duration: 2013 Jun 232013 Jun 28

Fingerprint

Computer vision
Gages
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Cite this

@article{b86c865dda1b4dd4bd50b87ecde3adf2,
title = "Online object tracking: A benchmark",
abstract = "Object tracking is one of the most important components in numerous applications of computer vision. While much progress has been made in recent years with efforts on sharing code and datasets, it is of great importance to develop a library and benchmark to gauge the state of the art. After briefly reviewing recent advances of online object tracking, we carry out large scale experiments with various evaluation criteria to understand how these algorithms perform. The test image sequences are annotated with different attributes for performance evaluation and analysis. By analyzing quantitative results, we identify effective approaches for robust tracking and provide potential future research directions in this field.",
author = "Yi Wu and Jongwoo Lim and Yang, {Ming Hsuan}",
year = "2013",
month = "11",
day = "15",
doi = "10.1109/CVPR.2013.312",
language = "English",
pages = "2411--2418",
journal = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
issn = "1063-6919",
publisher = "IEEE Computer Society",

}

Online object tracking : A benchmark. / Wu, Yi; Lim, Jongwoo; Yang, Ming Hsuan.

In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 15.11.2013, p. 2411-2418.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Online object tracking

T2 - A benchmark

AU - Wu, Yi

AU - Lim, Jongwoo

AU - Yang, Ming Hsuan

PY - 2013/11/15

Y1 - 2013/11/15

N2 - Object tracking is one of the most important components in numerous applications of computer vision. While much progress has been made in recent years with efforts on sharing code and datasets, it is of great importance to develop a library and benchmark to gauge the state of the art. After briefly reviewing recent advances of online object tracking, we carry out large scale experiments with various evaluation criteria to understand how these algorithms perform. The test image sequences are annotated with different attributes for performance evaluation and analysis. By analyzing quantitative results, we identify effective approaches for robust tracking and provide potential future research directions in this field.

AB - Object tracking is one of the most important components in numerous applications of computer vision. While much progress has been made in recent years with efforts on sharing code and datasets, it is of great importance to develop a library and benchmark to gauge the state of the art. After briefly reviewing recent advances of online object tracking, we carry out large scale experiments with various evaluation criteria to understand how these algorithms perform. The test image sequences are annotated with different attributes for performance evaluation and analysis. By analyzing quantitative results, we identify effective approaches for robust tracking and provide potential future research directions in this field.

UR - http://www.scopus.com/inward/record.url?scp=84887348427&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84887348427&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2013.312

DO - 10.1109/CVPR.2013.312

M3 - Conference article

AN - SCOPUS:84887348427

SP - 2411

EP - 2418

JO - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

JF - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SN - 1063-6919

M1 - 6619156

ER -