An experimental comparison of online object-tracking algorithms

Qing Wang, Feng Chen, Wenli Xu, Ming Hsuan Yang

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

59 Citations (Scopus)

Abstract

This paper reviews and evaluates several state-of-the-art online object tracking algorithms. Notwithstanding decades of efforts, object tracking remains a challenging problem due to factors such as illumination, pose, scale, deformation, motion blur, noise, and occlusion. To account for appearance change, most recent tracking algorithms focus on robust object representations and effective state prediction. In this paper, we analyze the components of each tracking method and identify their key roles in dealing with specific challenges, thereby shedding light on how to choose and design algorithms for different situations. We compare state-of-the-art online tracking methods including the IVT,1 VRT,2 FragT,3 BoostT, 4 SemiT,5 BeSemiT,6 L1T,7 MILT, 8 VTD9 and TLD10 algorithms on numerous challenging sequences, and evaluate them with different performance metrics. The qualitative and quantitative comparative results demonstrate the strength and weakness of these algorithms.

Original languageEnglish
Title of host publicationWavelets and Sparsity XIV
DOIs
Publication statusPublished - 2011 Nov 2
EventWavelets and Sparsity XIV - San Diego, CA, United States
Duration: 2011 Aug 212011 Aug 24

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume8138
ISSN (Print)0277-786X

Conference

ConferenceWavelets and Sparsity XIV
CountryUnited States
CitySan Diego, CA
Period11/8/2111/8/24

Fingerprint

Object Tracking
Object Representation
Motion Blur
Evaluate
Algorithm Design
Performance Metrics
Occlusion
occlusion
Illumination
Choose
Lighting
illumination
Prediction
Demonstrate
predictions

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Wang, Q., Chen, F., Xu, W., & Yang, M. H. (2011). An experimental comparison of online object-tracking algorithms. In Wavelets and Sparsity XIV [81381A] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 8138). https://doi.org/10.1117/12.895965
Wang, Qing ; Chen, Feng ; Xu, Wenli ; Yang, Ming Hsuan. / An experimental comparison of online object-tracking algorithms. Wavelets and Sparsity XIV. 2011. (Proceedings of SPIE - The International Society for Optical Engineering).
@inproceedings{3f20c0f1f5f84b598ce3c82f48f34924,
title = "An experimental comparison of online object-tracking algorithms",
abstract = "This paper reviews and evaluates several state-of-the-art online object tracking algorithms. Notwithstanding decades of efforts, object tracking remains a challenging problem due to factors such as illumination, pose, scale, deformation, motion blur, noise, and occlusion. To account for appearance change, most recent tracking algorithms focus on robust object representations and effective state prediction. In this paper, we analyze the components of each tracking method and identify their key roles in dealing with specific challenges, thereby shedding light on how to choose and design algorithms for different situations. We compare state-of-the-art online tracking methods including the IVT,1 VRT,2 FragT,3 BoostT, 4 SemiT,5 BeSemiT,6 L1T,7 MILT, 8 VTD9 and TLD10 algorithms on numerous challenging sequences, and evaluate them with different performance metrics. The qualitative and quantitative comparative results demonstrate the strength and weakness of these algorithms.",
author = "Qing Wang and Feng Chen and Wenli Xu and Yang, {Ming Hsuan}",
year = "2011",
month = "11",
day = "2",
doi = "10.1117/12.895965",
language = "English",
isbn = "9780819487483",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
booktitle = "Wavelets and Sparsity XIV",

}

Wang, Q, Chen, F, Xu, W & Yang, MH 2011, An experimental comparison of online object-tracking algorithms. in Wavelets and Sparsity XIV., 81381A, Proceedings of SPIE - The International Society for Optical Engineering, vol. 8138, Wavelets and Sparsity XIV, San Diego, CA, United States, 11/8/21. https://doi.org/10.1117/12.895965

An experimental comparison of online object-tracking algorithms. / Wang, Qing; Chen, Feng; Xu, Wenli; Yang, Ming Hsuan.

Wavelets and Sparsity XIV. 2011. 81381A (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 8138).

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

TY - GEN

T1 - An experimental comparison of online object-tracking algorithms

AU - Wang, Qing

AU - Chen, Feng

AU - Xu, Wenli

AU - Yang, Ming Hsuan

PY - 2011/11/2

Y1 - 2011/11/2

N2 - This paper reviews and evaluates several state-of-the-art online object tracking algorithms. Notwithstanding decades of efforts, object tracking remains a challenging problem due to factors such as illumination, pose, scale, deformation, motion blur, noise, and occlusion. To account for appearance change, most recent tracking algorithms focus on robust object representations and effective state prediction. In this paper, we analyze the components of each tracking method and identify their key roles in dealing with specific challenges, thereby shedding light on how to choose and design algorithms for different situations. We compare state-of-the-art online tracking methods including the IVT,1 VRT,2 FragT,3 BoostT, 4 SemiT,5 BeSemiT,6 L1T,7 MILT, 8 VTD9 and TLD10 algorithms on numerous challenging sequences, and evaluate them with different performance metrics. The qualitative and quantitative comparative results demonstrate the strength and weakness of these algorithms.

AB - This paper reviews and evaluates several state-of-the-art online object tracking algorithms. Notwithstanding decades of efforts, object tracking remains a challenging problem due to factors such as illumination, pose, scale, deformation, motion blur, noise, and occlusion. To account for appearance change, most recent tracking algorithms focus on robust object representations and effective state prediction. In this paper, we analyze the components of each tracking method and identify their key roles in dealing with specific challenges, thereby shedding light on how to choose and design algorithms for different situations. We compare state-of-the-art online tracking methods including the IVT,1 VRT,2 FragT,3 BoostT, 4 SemiT,5 BeSemiT,6 L1T,7 MILT, 8 VTD9 and TLD10 algorithms on numerous challenging sequences, and evaluate them with different performance metrics. The qualitative and quantitative comparative results demonstrate the strength and weakness of these algorithms.

UR - http://www.scopus.com/inward/record.url?scp=80055041061&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80055041061&partnerID=8YFLogxK

U2 - 10.1117/12.895965

DO - 10.1117/12.895965

M3 - Conference contribution

AN - SCOPUS:80055041061

SN - 9780819487483

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Wavelets and Sparsity XIV

ER -

Wang Q, Chen F, Xu W, Yang MH. An experimental comparison of online object-tracking algorithms. In Wavelets and Sparsity XIV. 2011. 81381A. (Proceedings of SPIE - The International Society for Optical Engineering). https://doi.org/10.1117/12.895965