Structure-aware local sparse coding for visual tracking

Yuankai Qi, Lei Qin, Jian Zhang, Shengping Zhang, Qingming Huang, Ming Hsuan Yang

Research output: Contribution to journalArticle

28 Citations (Scopus)

Abstract

Sparse coding has been applied to visual tracking and related vision problems with demonstrated success in recent years. Existing tracking methods based on local sparse coding sample patches from a target candidate and sparsely encode these using a dictionary consisting of patches sampled from target template images. The discriminative strength of existing methods based on local sparse coding is limited as spatial structure constraints among the template patches are not exploited. To address this problem, we propose a structure-aware local sparse coding algorithm, which encodes a target candidate using templates with both global and local sparsity constraints. For robust tracking, we show the local regions of a candidate region should be encoded only with the corresponding local regions of the target templates that are the most similar from the global view. Thus, a more precise and discriminative sparse representation is obtained to account for appearance changes. To alleviate the issues with tracking drifts, we design an effective template update scheme. Extensive experiments on challenging image sequences demonstrate the effectiveness of the proposed algorithm against numerous state-of-the-art methods.

Original languageEnglish
Pages (from-to)3857-3869
Number of pages13
JournalIEEE Transactions on Image Processing
Volume27
Issue number8
DOIs
Publication statusPublished - 2018 Aug

Fingerprint

Glossaries
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Graphics and Computer-Aided Design

Cite this

Qi, Yuankai ; Qin, Lei ; Zhang, Jian ; Zhang, Shengping ; Huang, Qingming ; Yang, Ming Hsuan. / Structure-aware local sparse coding for visual tracking. In: IEEE Transactions on Image Processing. 2018 ; Vol. 27, No. 8. pp. 3857-3869.
@article{c8d7f2e5fe3b481e98ab5f1aa5098c00,
title = "Structure-aware local sparse coding for visual tracking",
abstract = "Sparse coding has been applied to visual tracking and related vision problems with demonstrated success in recent years. Existing tracking methods based on local sparse coding sample patches from a target candidate and sparsely encode these using a dictionary consisting of patches sampled from target template images. The discriminative strength of existing methods based on local sparse coding is limited as spatial structure constraints among the template patches are not exploited. To address this problem, we propose a structure-aware local sparse coding algorithm, which encodes a target candidate using templates with both global and local sparsity constraints. For robust tracking, we show the local regions of a candidate region should be encoded only with the corresponding local regions of the target templates that are the most similar from the global view. Thus, a more precise and discriminative sparse representation is obtained to account for appearance changes. To alleviate the issues with tracking drifts, we design an effective template update scheme. Extensive experiments on challenging image sequences demonstrate the effectiveness of the proposed algorithm against numerous state-of-the-art methods.",
author = "Yuankai Qi and Lei Qin and Jian Zhang and Shengping Zhang and Qingming Huang and Yang, {Ming Hsuan}",
year = "2018",
month = "8",
doi = "10.1109/TIP.2018.2797482",
language = "English",
volume = "27",
pages = "3857--3869",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "8",

}

Structure-aware local sparse coding for visual tracking. / Qi, Yuankai; Qin, Lei; Zhang, Jian; Zhang, Shengping; Huang, Qingming; Yang, Ming Hsuan.

In: IEEE Transactions on Image Processing, Vol. 27, No. 8, 08.2018, p. 3857-3869.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Structure-aware local sparse coding for visual tracking

AU - Qi, Yuankai

AU - Qin, Lei

AU - Zhang, Jian

AU - Zhang, Shengping

AU - Huang, Qingming

AU - Yang, Ming Hsuan

PY - 2018/8

Y1 - 2018/8

N2 - Sparse coding has been applied to visual tracking and related vision problems with demonstrated success in recent years. Existing tracking methods based on local sparse coding sample patches from a target candidate and sparsely encode these using a dictionary consisting of patches sampled from target template images. The discriminative strength of existing methods based on local sparse coding is limited as spatial structure constraints among the template patches are not exploited. To address this problem, we propose a structure-aware local sparse coding algorithm, which encodes a target candidate using templates with both global and local sparsity constraints. For robust tracking, we show the local regions of a candidate region should be encoded only with the corresponding local regions of the target templates that are the most similar from the global view. Thus, a more precise and discriminative sparse representation is obtained to account for appearance changes. To alleviate the issues with tracking drifts, we design an effective template update scheme. Extensive experiments on challenging image sequences demonstrate the effectiveness of the proposed algorithm against numerous state-of-the-art methods.

AB - Sparse coding has been applied to visual tracking and related vision problems with demonstrated success in recent years. Existing tracking methods based on local sparse coding sample patches from a target candidate and sparsely encode these using a dictionary consisting of patches sampled from target template images. The discriminative strength of existing methods based on local sparse coding is limited as spatial structure constraints among the template patches are not exploited. To address this problem, we propose a structure-aware local sparse coding algorithm, which encodes a target candidate using templates with both global and local sparsity constraints. For robust tracking, we show the local regions of a candidate region should be encoded only with the corresponding local regions of the target templates that are the most similar from the global view. Thus, a more precise and discriminative sparse representation is obtained to account for appearance changes. To alleviate the issues with tracking drifts, we design an effective template update scheme. Extensive experiments on challenging image sequences demonstrate the effectiveness of the proposed algorithm against numerous state-of-the-art methods.

UR - http://www.scopus.com/inward/record.url?scp=85040996089&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040996089&partnerID=8YFLogxK

U2 - 10.1109/TIP.2018.2797482

DO - 10.1109/TIP.2018.2797482

M3 - Article

AN - SCOPUS:85040996089

VL - 27

SP - 3857

EP - 3869

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

IS - 8

ER -