Online object tracking with sparse prototypes

Dong Wang, Huchuan Lu, Ming Hsuan Yang

Research output: Contribution to journalArticle

378 Citations (Scopus)

Abstract

Online object tracking is a challenging problem as it entails learning an effective model to account for appearance change caused by intrinsic and extrinsic factors. In this paper, we propose a novel online object tracking algorithm with sparse prototypes, which exploits both classic principal component analysis (PCA) algorithms with recent sparse representation schemes for learning effective appearance models. We introduce ℓ1 regularization into the PCA reconstruction, and develop a novel algorithm to represent an object by sparse prototypes that account explicitly for data and noise. For tracking, objects are represented by the sparse prototypes learned online with update. In order to reduce tracking drift, we present a method that takes occlusion and motion blur into account rather than simply includes image observations for model update. Both qualitative and quantitative evaluations on challenging image sequences demonstrate that the proposed tracking algorithm performs favorably against several state-of-the-art methods.

Original languageEnglish
Article number6212358
Pages (from-to)314-325
Number of pages12
JournalIEEE Transactions on Image Processing
Volume22
Issue number1
DOIs
Publication statusPublished - 2013 Jan 2

Fingerprint

Principal Component Analysis
Principal component analysis
Learning
Intrinsic Factor
Noise

All Science Journal Classification (ASJC) codes

  • Software
  • Medicine(all)
  • Computer Graphics and Computer-Aided Design

Cite this

Wang, Dong ; Lu, Huchuan ; Yang, Ming Hsuan. / Online object tracking with sparse prototypes. In: IEEE Transactions on Image Processing. 2013 ; Vol. 22, No. 1. pp. 314-325.
@article{029562b10a7b47f3ac6074cd2fee7de4,
title = "Online object tracking with sparse prototypes",
abstract = "Online object tracking is a challenging problem as it entails learning an effective model to account for appearance change caused by intrinsic and extrinsic factors. In this paper, we propose a novel online object tracking algorithm with sparse prototypes, which exploits both classic principal component analysis (PCA) algorithms with recent sparse representation schemes for learning effective appearance models. We introduce ℓ1 regularization into the PCA reconstruction, and develop a novel algorithm to represent an object by sparse prototypes that account explicitly for data and noise. For tracking, objects are represented by the sparse prototypes learned online with update. In order to reduce tracking drift, we present a method that takes occlusion and motion blur into account rather than simply includes image observations for model update. Both qualitative and quantitative evaluations on challenging image sequences demonstrate that the proposed tracking algorithm performs favorably against several state-of-the-art methods.",
author = "Dong Wang and Huchuan Lu and Yang, {Ming Hsuan}",
year = "2013",
month = "1",
day = "2",
doi = "10.1109/TIP.2012.2202677",
language = "English",
volume = "22",
pages = "314--325",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "1",

}

Online object tracking with sparse prototypes. / Wang, Dong; Lu, Huchuan; Yang, Ming Hsuan.

In: IEEE Transactions on Image Processing, Vol. 22, No. 1, 6212358, 02.01.2013, p. 314-325.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Online object tracking with sparse prototypes

AU - Wang, Dong

AU - Lu, Huchuan

AU - Yang, Ming Hsuan

PY - 2013/1/2

Y1 - 2013/1/2

N2 - Online object tracking is a challenging problem as it entails learning an effective model to account for appearance change caused by intrinsic and extrinsic factors. In this paper, we propose a novel online object tracking algorithm with sparse prototypes, which exploits both classic principal component analysis (PCA) algorithms with recent sparse representation schemes for learning effective appearance models. We introduce ℓ1 regularization into the PCA reconstruction, and develop a novel algorithm to represent an object by sparse prototypes that account explicitly for data and noise. For tracking, objects are represented by the sparse prototypes learned online with update. In order to reduce tracking drift, we present a method that takes occlusion and motion blur into account rather than simply includes image observations for model update. Both qualitative and quantitative evaluations on challenging image sequences demonstrate that the proposed tracking algorithm performs favorably against several state-of-the-art methods.

AB - Online object tracking is a challenging problem as it entails learning an effective model to account for appearance change caused by intrinsic and extrinsic factors. In this paper, we propose a novel online object tracking algorithm with sparse prototypes, which exploits both classic principal component analysis (PCA) algorithms with recent sparse representation schemes for learning effective appearance models. We introduce ℓ1 regularization into the PCA reconstruction, and develop a novel algorithm to represent an object by sparse prototypes that account explicitly for data and noise. For tracking, objects are represented by the sparse prototypes learned online with update. In order to reduce tracking drift, we present a method that takes occlusion and motion blur into account rather than simply includes image observations for model update. Both qualitative and quantitative evaluations on challenging image sequences demonstrate that the proposed tracking algorithm performs favorably against several state-of-the-art methods.

UR - http://www.scopus.com/inward/record.url?scp=84871648489&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84871648489&partnerID=8YFLogxK

U2 - 10.1109/TIP.2012.2202677

DO - 10.1109/TIP.2012.2202677

M3 - Article

C2 - 22692912

AN - SCOPUS:84871648489

VL - 22

SP - 314

EP - 325

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

IS - 1

M1 - 6212358

ER -