Visual tracking via locality sensitive histograms

Shengfeng He, Qingxiong Yang, Rynson W.H. Lau, Jiang Wang, Ming Hsuan Yang

Research output: Contribution to journalConference article

264 Citations (Scopus)

Abstract

This paper presents a novel locality sensitive histogram algorithm for visual tracking. Unlike the conventional image histogram that counts the frequency of occurrences of each intensity value by adding ones to the corresponding bin, a locality sensitive histogram is computed at each pixel location and a floating-point value is added to the corresponding bin for each occurrence of an intensity value. The floating-point value declines exponentially with respect to the distance to the pixel location where the histogram is computed, thus every pixel is considered but those that are far away can be neglected due to the very small weights assigned. An efficient algorithm is proposed that enables the locality sensitive histograms to be computed in time linear in the image size and the number of bins. A robust tracking framework based on the locality sensitive histograms is proposed, which consists of two main components: a new feature for tracking that is robust to illumination changes and a novel multi-region tracking algorithm that runs in real time even with hundreds of regions. Extensive experiments demonstrate that the proposed tracking framework outperforms the state-of-the-art methods in challenging scenarios, especially when the illumination changes dramatically.

Original languageEnglish
Article number6619158
Pages (from-to)2427-2434
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

Bins
Pixels
Lighting
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Cite this

@article{2be40cf211df46e687102f8ae35af38b,
title = "Visual tracking via locality sensitive histograms",
abstract = "This paper presents a novel locality sensitive histogram algorithm for visual tracking. Unlike the conventional image histogram that counts the frequency of occurrences of each intensity value by adding ones to the corresponding bin, a locality sensitive histogram is computed at each pixel location and a floating-point value is added to the corresponding bin for each occurrence of an intensity value. The floating-point value declines exponentially with respect to the distance to the pixel location where the histogram is computed, thus every pixel is considered but those that are far away can be neglected due to the very small weights assigned. An efficient algorithm is proposed that enables the locality sensitive histograms to be computed in time linear in the image size and the number of bins. A robust tracking framework based on the locality sensitive histograms is proposed, which consists of two main components: a new feature for tracking that is robust to illumination changes and a novel multi-region tracking algorithm that runs in real time even with hundreds of regions. Extensive experiments demonstrate that the proposed tracking framework outperforms the state-of-the-art methods in challenging scenarios, especially when the illumination changes dramatically.",
author = "Shengfeng He and Qingxiong Yang and Lau, {Rynson W.H.} and Jiang Wang and Yang, {Ming Hsuan}",
year = "2013",
month = "11",
day = "15",
doi = "10.1109/CVPR.2013.314",
language = "English",
pages = "2427--2434",
journal = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
issn = "1063-6919",
publisher = "IEEE Computer Society",

}

Visual tracking via locality sensitive histograms. / He, Shengfeng; Yang, Qingxiong; Lau, Rynson W.H.; Wang, Jiang; Yang, Ming Hsuan.

In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 15.11.2013, p. 2427-2434.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Visual tracking via locality sensitive histograms

AU - He, Shengfeng

AU - Yang, Qingxiong

AU - Lau, Rynson W.H.

AU - Wang, Jiang

AU - Yang, Ming Hsuan

PY - 2013/11/15

Y1 - 2013/11/15

N2 - This paper presents a novel locality sensitive histogram algorithm for visual tracking. Unlike the conventional image histogram that counts the frequency of occurrences of each intensity value by adding ones to the corresponding bin, a locality sensitive histogram is computed at each pixel location and a floating-point value is added to the corresponding bin for each occurrence of an intensity value. The floating-point value declines exponentially with respect to the distance to the pixel location where the histogram is computed, thus every pixel is considered but those that are far away can be neglected due to the very small weights assigned. An efficient algorithm is proposed that enables the locality sensitive histograms to be computed in time linear in the image size and the number of bins. A robust tracking framework based on the locality sensitive histograms is proposed, which consists of two main components: a new feature for tracking that is robust to illumination changes and a novel multi-region tracking algorithm that runs in real time even with hundreds of regions. Extensive experiments demonstrate that the proposed tracking framework outperforms the state-of-the-art methods in challenging scenarios, especially when the illumination changes dramatically.

AB - This paper presents a novel locality sensitive histogram algorithm for visual tracking. Unlike the conventional image histogram that counts the frequency of occurrences of each intensity value by adding ones to the corresponding bin, a locality sensitive histogram is computed at each pixel location and a floating-point value is added to the corresponding bin for each occurrence of an intensity value. The floating-point value declines exponentially with respect to the distance to the pixel location where the histogram is computed, thus every pixel is considered but those that are far away can be neglected due to the very small weights assigned. An efficient algorithm is proposed that enables the locality sensitive histograms to be computed in time linear in the image size and the number of bins. A robust tracking framework based on the locality sensitive histograms is proposed, which consists of two main components: a new feature for tracking that is robust to illumination changes and a novel multi-region tracking algorithm that runs in real time even with hundreds of regions. Extensive experiments demonstrate that the proposed tracking framework outperforms the state-of-the-art methods in challenging scenarios, especially when the illumination changes dramatically.

UR - http://www.scopus.com/inward/record.url?scp=84887381620&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84887381620&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2013.314

DO - 10.1109/CVPR.2013.314

M3 - Conference article

AN - SCOPUS:84887381620

SP - 2427

EP - 2434

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 - 6619158

ER -