Visual tracking via Boolean map representations

Kaihua Zhang, Qingshan Liu, Jian Yang, Ming Hsuan Yang

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

In this paper, we present a simple yet effective Boolean map based representation that exploits connectivity cues for visual tracking. We describe a target object with histogram of oriented gradients and raw color features, of which each one is characterized by a set of Boolean maps generated by uniformly thresholding their values. The Boolean maps effectively encode multi-scale connectivity cues of the target with different granularities. The fine-grained Boolean maps capture spatially structural details that are effective for precise target localization while the coarse-grained ones encode global shape information that are robust to large target appearance variations. Finally, all the Boolean maps form together a robust representation that can be approximated by an explicit feature map of the intersection kernel, which is fed into a logistic regression classifier with online update, and the target location is estimated within a particle filter framework. The proposed representation scheme is computationally efficient and facilitates achieving favorable performance in terms of accuracy and robustness against the state-of-the-art tracking methods on the OTB50 and VOT2016 benchmark datasets.

Original languageEnglish
Pages (from-to)147-160
Number of pages14
JournalPattern Recognition
Volume81
DOIs
Publication statusPublished - 2018 Sep

Fingerprint

Logistics
Classifiers
Color

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Zhang, Kaihua ; Liu, Qingshan ; Yang, Jian ; Yang, Ming Hsuan. / Visual tracking via Boolean map representations. In: Pattern Recognition. 2018 ; Vol. 81. pp. 147-160.
@article{93e6ffee9461414f96171325bd72aaff,
title = "Visual tracking via Boolean map representations",
abstract = "In this paper, we present a simple yet effective Boolean map based representation that exploits connectivity cues for visual tracking. We describe a target object with histogram of oriented gradients and raw color features, of which each one is characterized by a set of Boolean maps generated by uniformly thresholding their values. The Boolean maps effectively encode multi-scale connectivity cues of the target with different granularities. The fine-grained Boolean maps capture spatially structural details that are effective for precise target localization while the coarse-grained ones encode global shape information that are robust to large target appearance variations. Finally, all the Boolean maps form together a robust representation that can be approximated by an explicit feature map of the intersection kernel, which is fed into a logistic regression classifier with online update, and the target location is estimated within a particle filter framework. The proposed representation scheme is computationally efficient and facilitates achieving favorable performance in terms of accuracy and robustness against the state-of-the-art tracking methods on the OTB50 and VOT2016 benchmark datasets.",
author = "Kaihua Zhang and Qingshan Liu and Jian Yang and Yang, {Ming Hsuan}",
year = "2018",
month = "9",
doi = "10.1016/j.patcog.2018.03.029",
language = "English",
volume = "81",
pages = "147--160",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",

}

Visual tracking via Boolean map representations. / Zhang, Kaihua; Liu, Qingshan; Yang, Jian; Yang, Ming Hsuan.

In: Pattern Recognition, Vol. 81, 09.2018, p. 147-160.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Visual tracking via Boolean map representations

AU - Zhang, Kaihua

AU - Liu, Qingshan

AU - Yang, Jian

AU - Yang, Ming Hsuan

PY - 2018/9

Y1 - 2018/9

N2 - In this paper, we present a simple yet effective Boolean map based representation that exploits connectivity cues for visual tracking. We describe a target object with histogram of oriented gradients and raw color features, of which each one is characterized by a set of Boolean maps generated by uniformly thresholding their values. The Boolean maps effectively encode multi-scale connectivity cues of the target with different granularities. The fine-grained Boolean maps capture spatially structural details that are effective for precise target localization while the coarse-grained ones encode global shape information that are robust to large target appearance variations. Finally, all the Boolean maps form together a robust representation that can be approximated by an explicit feature map of the intersection kernel, which is fed into a logistic regression classifier with online update, and the target location is estimated within a particle filter framework. The proposed representation scheme is computationally efficient and facilitates achieving favorable performance in terms of accuracy and robustness against the state-of-the-art tracking methods on the OTB50 and VOT2016 benchmark datasets.

AB - In this paper, we present a simple yet effective Boolean map based representation that exploits connectivity cues for visual tracking. We describe a target object with histogram of oriented gradients and raw color features, of which each one is characterized by a set of Boolean maps generated by uniformly thresholding their values. The Boolean maps effectively encode multi-scale connectivity cues of the target with different granularities. The fine-grained Boolean maps capture spatially structural details that are effective for precise target localization while the coarse-grained ones encode global shape information that are robust to large target appearance variations. Finally, all the Boolean maps form together a robust representation that can be approximated by an explicit feature map of the intersection kernel, which is fed into a logistic regression classifier with online update, and the target location is estimated within a particle filter framework. The proposed representation scheme is computationally efficient and facilitates achieving favorable performance in terms of accuracy and robustness against the state-of-the-art tracking methods on the OTB50 and VOT2016 benchmark datasets.

UR - http://www.scopus.com/inward/record.url?scp=85045208965&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045208965&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2018.03.029

DO - 10.1016/j.patcog.2018.03.029

M3 - Article

AN - SCOPUS:85045208965

VL - 81

SP - 147

EP - 160

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

ER -