Tracking 3d pose of rigid object by sparse template matching

Yuki Oka, Toshiyuki Kuroda, Tsuyoshi Migita, Takeshi Shakunaga

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

5 Citations (Scopus)

Abstract

Tracking 3d pose of a known object is one of the most important problems in computer vision. This paper proposes an appearance-based approach to this problem by combining the sparse template matching and the particle filter. Although the combination of them has already been discussed for 2d tracker, it has not been applied for efficient 3d tracking. This paper discusses an appearance-based tracker when a surface model of the target 3d object and the initial pose are given. The fundamental framework of the particle filter is provided at first for implementing a pose tracker based on sparse 3d template matching. Then, the coarse-to-fine approach is introduced for efficient implementation. Although the fundamental particle filter often requires a lot of particles for sufficient tracking, the number of particles can be effectively reduced by the coarse-to-fine strategy. Experimental results for both the simulation data and real images show how the proposed method works in frame rate on 3GHz Core 2 Quad(single thread) without using GPU or other special hardware.

Original languageEnglish
Title of host publicationProceedings of the 5th International Conference on Image and Graphics, ICIG 2009
Pages390-397
Number of pages8
DOIs
Publication statusPublished - 2010
Event5th International Conference on Image and Graphics, ICIG 2009 - Xi'an, Shanxi, China
Duration: Sep 20 2009Sep 23 2009

Other

Other5th International Conference on Image and Graphics, ICIG 2009
CountryChina
CityXi'an, Shanxi
Period9/20/099/23/09

Fingerprint

Template matching
Computer vision
Hardware
Graphics processing unit

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition

Cite this

Oka, Y., Kuroda, T., Migita, T., & Shakunaga, T. (2010). Tracking 3d pose of rigid object by sparse template matching. In Proceedings of the 5th International Conference on Image and Graphics, ICIG 2009 (pp. 390-397). [5437886] https://doi.org/10.1109/ICIG.2009.138

Tracking 3d pose of rigid object by sparse template matching. / Oka, Yuki; Kuroda, Toshiyuki; Migita, Tsuyoshi; Shakunaga, Takeshi.

Proceedings of the 5th International Conference on Image and Graphics, ICIG 2009. 2010. p. 390-397 5437886.

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

Oka, Y, Kuroda, T, Migita, T & Shakunaga, T 2010, Tracking 3d pose of rigid object by sparse template matching. in Proceedings of the 5th International Conference on Image and Graphics, ICIG 2009., 5437886, pp. 390-397, 5th International Conference on Image and Graphics, ICIG 2009, Xi'an, Shanxi, China, 9/20/09. https://doi.org/10.1109/ICIG.2009.138
Oka Y, Kuroda T, Migita T, Shakunaga T. Tracking 3d pose of rigid object by sparse template matching. In Proceedings of the 5th International Conference on Image and Graphics, ICIG 2009. 2010. p. 390-397. 5437886 https://doi.org/10.1109/ICIG.2009.138
Oka, Yuki ; Kuroda, Toshiyuki ; Migita, Tsuyoshi ; Shakunaga, Takeshi. / Tracking 3d pose of rigid object by sparse template matching. Proceedings of the 5th International Conference on Image and Graphics, ICIG 2009. 2010. pp. 390-397
@inproceedings{bce9c1413b114cdc8c86404d55376cf1,
title = "Tracking 3d pose of rigid object by sparse template matching",
abstract = "Tracking 3d pose of a known object is one of the most important problems in computer vision. This paper proposes an appearance-based approach to this problem by combining the sparse template matching and the particle filter. Although the combination of them has already been discussed for 2d tracker, it has not been applied for efficient 3d tracking. This paper discusses an appearance-based tracker when a surface model of the target 3d object and the initial pose are given. The fundamental framework of the particle filter is provided at first for implementing a pose tracker based on sparse 3d template matching. Then, the coarse-to-fine approach is introduced for efficient implementation. Although the fundamental particle filter often requires a lot of particles for sufficient tracking, the number of particles can be effectively reduced by the coarse-to-fine strategy. Experimental results for both the simulation data and real images show how the proposed method works in frame rate on 3GHz Core 2 Quad(single thread) without using GPU or other special hardware.",
author = "Yuki Oka and Toshiyuki Kuroda and Tsuyoshi Migita and Takeshi Shakunaga",
year = "2010",
doi = "10.1109/ICIG.2009.138",
language = "English",
isbn = "9780769538839",
pages = "390--397",
booktitle = "Proceedings of the 5th International Conference on Image and Graphics, ICIG 2009",

}

TY - GEN

T1 - Tracking 3d pose of rigid object by sparse template matching

AU - Oka, Yuki

AU - Kuroda, Toshiyuki

AU - Migita, Tsuyoshi

AU - Shakunaga, Takeshi

PY - 2010

Y1 - 2010

N2 - Tracking 3d pose of a known object is one of the most important problems in computer vision. This paper proposes an appearance-based approach to this problem by combining the sparse template matching and the particle filter. Although the combination of them has already been discussed for 2d tracker, it has not been applied for efficient 3d tracking. This paper discusses an appearance-based tracker when a surface model of the target 3d object and the initial pose are given. The fundamental framework of the particle filter is provided at first for implementing a pose tracker based on sparse 3d template matching. Then, the coarse-to-fine approach is introduced for efficient implementation. Although the fundamental particle filter often requires a lot of particles for sufficient tracking, the number of particles can be effectively reduced by the coarse-to-fine strategy. Experimental results for both the simulation data and real images show how the proposed method works in frame rate on 3GHz Core 2 Quad(single thread) without using GPU or other special hardware.

AB - Tracking 3d pose of a known object is one of the most important problems in computer vision. This paper proposes an appearance-based approach to this problem by combining the sparse template matching and the particle filter. Although the combination of them has already been discussed for 2d tracker, it has not been applied for efficient 3d tracking. This paper discusses an appearance-based tracker when a surface model of the target 3d object and the initial pose are given. The fundamental framework of the particle filter is provided at first for implementing a pose tracker based on sparse 3d template matching. Then, the coarse-to-fine approach is introduced for efficient implementation. Although the fundamental particle filter often requires a lot of particles for sufficient tracking, the number of particles can be effectively reduced by the coarse-to-fine strategy. Experimental results for both the simulation data and real images show how the proposed method works in frame rate on 3GHz Core 2 Quad(single thread) without using GPU or other special hardware.

UR - http://www.scopus.com/inward/record.url?scp=77952279337&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77952279337&partnerID=8YFLogxK

U2 - 10.1109/ICIG.2009.138

DO - 10.1109/ICIG.2009.138

M3 - Conference contribution

AN - SCOPUS:77952279337

SN - 9780769538839

SP - 390

EP - 397

BT - Proceedings of the 5th International Conference on Image and Graphics, ICIG 2009

ER -