Robust online tracking using orientation and color incorporated adaptive models in particle filter

Chengjiao Guo, Ying Lu, Takeshi Ikenaga

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

1 Citation (Scopus)

Abstract

Moving object tracking has received much interest in the field of computer vision due to the increasing need for automated video analysis. Particles Filter is a very promising object tracking method since it is suitable for non-linear and/or non-Gaussian applications. Most particle filter applies color information in target model which might fail in the presence of similar colored objects in the scene. This paper presents the integration of color and orientation features in particle filter to make full use of the distinctive target features. Also, an improved Gaussian weighting function for target models and an updating scheme with an adaptive updating ratio are proposed. The proposed approaches are applied in the real-time video sequences with different occlusion conditions to test the robustness of the proposal. Experiment results show that stable and accurate tracking performance is achieved even when the target is occluded by a similar colored object.

Original languageEnglish
Title of host publicationNISS2010 - 4th International Conference on New Trends in Information Science and Service Science
Pages281-286
Number of pages6
Publication statusPublished - 2010
Event4th International Conference on New Trends in Information Science and Service Science, NISS2010 - Gyeongju
Duration: 2010 May 112010 May 13

Other

Other4th International Conference on New Trends in Information Science and Service Science, NISS2010
CityGyeongju
Period10/5/1110/5/13

Fingerprint

Particle filter
Computer vision
Experiment
Weighting
Robustness

Keywords

  • Adaptive updating
  • Gradient orientation model
  • HSV color model
  • Object tracking
  • Particle filter

ASJC Scopus subject areas

  • Information Systems and Management

Cite this

Guo, C., Lu, Y., & Ikenaga, T. (2010). Robust online tracking using orientation and color incorporated adaptive models in particle filter. In NISS2010 - 4th International Conference on New Trends in Information Science and Service Science (pp. 281-286). [5488605]

Robust online tracking using orientation and color incorporated adaptive models in particle filter. / Guo, Chengjiao; Lu, Ying; Ikenaga, Takeshi.

NISS2010 - 4th International Conference on New Trends in Information Science and Service Science. 2010. p. 281-286 5488605.

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

Guo, C, Lu, Y & Ikenaga, T 2010, Robust online tracking using orientation and color incorporated adaptive models in particle filter. in NISS2010 - 4th International Conference on New Trends in Information Science and Service Science., 5488605, pp. 281-286, 4th International Conference on New Trends in Information Science and Service Science, NISS2010, Gyeongju, 10/5/11.
Guo C, Lu Y, Ikenaga T. Robust online tracking using orientation and color incorporated adaptive models in particle filter. In NISS2010 - 4th International Conference on New Trends in Information Science and Service Science. 2010. p. 281-286. 5488605
Guo, Chengjiao ; Lu, Ying ; Ikenaga, Takeshi. / Robust online tracking using orientation and color incorporated adaptive models in particle filter. NISS2010 - 4th International Conference on New Trends in Information Science and Service Science. 2010. pp. 281-286
@inproceedings{b25abb344a774d309b49e054da04b1f7,
title = "Robust online tracking using orientation and color incorporated adaptive models in particle filter",
abstract = "Moving object tracking has received much interest in the field of computer vision due to the increasing need for automated video analysis. Particles Filter is a very promising object tracking method since it is suitable for non-linear and/or non-Gaussian applications. Most particle filter applies color information in target model which might fail in the presence of similar colored objects in the scene. This paper presents the integration of color and orientation features in particle filter to make full use of the distinctive target features. Also, an improved Gaussian weighting function for target models and an updating scheme with an adaptive updating ratio are proposed. The proposed approaches are applied in the real-time video sequences with different occlusion conditions to test the robustness of the proposal. Experiment results show that stable and accurate tracking performance is achieved even when the target is occluded by a similar colored object.",
keywords = "Adaptive updating, Gradient orientation model, HSV color model, Object tracking, Particle filter",
author = "Chengjiao Guo and Ying Lu and Takeshi Ikenaga",
year = "2010",
language = "English",
isbn = "9788988678183",
pages = "281--286",
booktitle = "NISS2010 - 4th International Conference on New Trends in Information Science and Service Science",

}

TY - GEN

T1 - Robust online tracking using orientation and color incorporated adaptive models in particle filter

AU - Guo, Chengjiao

AU - Lu, Ying

AU - Ikenaga, Takeshi

PY - 2010

Y1 - 2010

N2 - Moving object tracking has received much interest in the field of computer vision due to the increasing need for automated video analysis. Particles Filter is a very promising object tracking method since it is suitable for non-linear and/or non-Gaussian applications. Most particle filter applies color information in target model which might fail in the presence of similar colored objects in the scene. This paper presents the integration of color and orientation features in particle filter to make full use of the distinctive target features. Also, an improved Gaussian weighting function for target models and an updating scheme with an adaptive updating ratio are proposed. The proposed approaches are applied in the real-time video sequences with different occlusion conditions to test the robustness of the proposal. Experiment results show that stable and accurate tracking performance is achieved even when the target is occluded by a similar colored object.

AB - Moving object tracking has received much interest in the field of computer vision due to the increasing need for automated video analysis. Particles Filter is a very promising object tracking method since it is suitable for non-linear and/or non-Gaussian applications. Most particle filter applies color information in target model which might fail in the presence of similar colored objects in the scene. This paper presents the integration of color and orientation features in particle filter to make full use of the distinctive target features. Also, an improved Gaussian weighting function for target models and an updating scheme with an adaptive updating ratio are proposed. The proposed approaches are applied in the real-time video sequences with different occlusion conditions to test the robustness of the proposal. Experiment results show that stable and accurate tracking performance is achieved even when the target is occluded by a similar colored object.

KW - Adaptive updating

KW - Gradient orientation model

KW - HSV color model

KW - Object tracking

KW - Particle filter

UR - http://www.scopus.com/inward/record.url?scp=77957767663&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77957767663&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9788988678183

SP - 281

EP - 286

BT - NISS2010 - 4th International Conference on New Trends in Information Science and Service Science

ER -