A visual tracking strategy using computer graphics and edge

Chuantao Zang; Koichi Hashimoto; Jungjae Moon

doi:10.1109/ROBIO.2011.6181415

A visual tracking strategy using computer graphics and edge

Chuantao Zang, Koichi Hashimoto, Jungjae Moon

INF - System Information Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Citations (Scopus)

Abstract

In this paper we have proposed a visual tracking strategy for 3D object recognition and tracking in robot vision applications. We adopt a Coarse-to-Fine combination strategy for 3D object tracking. In the coarse step, compared with those edge-based only methods, the convergence range of initial camera pose estimation has been enlarged in our system by a template-based matching between a series of template images rendered from Computer Graphics (CG) and a current image. In the fine step an edge-based object tracking method is used to realize a more accurate visual tracking application with the results from the previous coarse step. The implementation of this strategy is introduced in detail. The experiments results show that this combination strategy is effective for tracking real objects in robot vision applications.

Original language	English
Title of host publication	2011 IEEE International Conference on Robotics and Biomimetics, ROBIO 2011
Pages	981-986
Number of pages	6
DOIs	https://doi.org/10.1109/ROBIO.2011.6181415
Publication status	Published - 2011 Dec 1
Event	2011 IEEE International Conference on Robotics and Biomimetics, ROBIO 2011 - Phuket, Thailand Duration: 2011 Dec 7 → 2011 Dec 11

Publication series

Name	2011 IEEE International Conference on Robotics and Biomimetics, ROBIO 2011

Other

Other	2011 IEEE International Conference on Robotics and Biomimetics, ROBIO 2011
Country	Thailand
City	Phuket
Period	11/12/7 → 11/12/11

ASJC Scopus subject areas

Computer Vision and Pattern Recognition

Access to Document

10.1109/ROBIO.2011.6181415

Fingerprint Dive into the research topics of 'A visual tracking strategy using computer graphics and edge'. Together they form a unique fingerprint.

Cite this

A visual tracking strategy using computer graphics and edge. / Zang, Chuantao; Hashimoto, Koichi; Moon, Jungjae.

2011 IEEE International Conference on Robotics and Biomimetics, ROBIO 2011. 2011. p. 981-986 6181415 (2011 IEEE International Conference on Robotics and Biomimetics, ROBIO 2011).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Zang, C, Hashimoto, K & Moon, J 2011, A visual tracking strategy using computer graphics and edge. in 2011 IEEE International Conference on Robotics and Biomimetics, ROBIO 2011., 6181415, 2011 IEEE International Conference on Robotics and Biomimetics, ROBIO 2011, pp. 981-986, 2011 IEEE International Conference on Robotics and Biomimetics, ROBIO 2011, Phuket, Thailand, 11/12/7. https://doi.org/10.1109/ROBIO.2011.6181415

@inproceedings{2eb3247d4dfe4794908bfbda3f80a8c3,

title = "A visual tracking strategy using computer graphics and edge",

abstract = "In this paper we have proposed a visual tracking strategy for 3D object recognition and tracking in robot vision applications. We adopt a Coarse-to-Fine combination strategy for 3D object tracking. In the coarse step, compared with those edge-based only methods, the convergence range of initial camera pose estimation has been enlarged in our system by a template-based matching between a series of template images rendered from Computer Graphics (CG) and a current image. In the fine step an edge-based object tracking method is used to realize a more accurate visual tracking application with the results from the previous coarse step. The implementation of this strategy is introduced in detail. The experiments results show that this combination strategy is effective for tracking real objects in robot vision applications.",

author = "Chuantao Zang and Koichi Hashimoto and Jungjae Moon",

year = "2011",

month = dec,

day = "1",

doi = "10.1109/ROBIO.2011.6181415",

language = "English",

isbn = "9781457721373",

series = "2011 IEEE International Conference on Robotics and Biomimetics, ROBIO 2011",

pages = "981--986",

booktitle = "2011 IEEE International Conference on Robotics and Biomimetics, ROBIO 2011",

note = "2011 IEEE International Conference on Robotics and Biomimetics, ROBIO 2011 ; Conference date: 07-12-2011 Through 11-12-2011",

}

TY - GEN

T1 - A visual tracking strategy using computer graphics and edge

AU - Zang, Chuantao

AU - Hashimoto, Koichi

AU - Moon, Jungjae

PY - 2011/12/1

Y1 - 2011/12/1

N2 - In this paper we have proposed a visual tracking strategy for 3D object recognition and tracking in robot vision applications. We adopt a Coarse-to-Fine combination strategy for 3D object tracking. In the coarse step, compared with those edge-based only methods, the convergence range of initial camera pose estimation has been enlarged in our system by a template-based matching between a series of template images rendered from Computer Graphics (CG) and a current image. In the fine step an edge-based object tracking method is used to realize a more accurate visual tracking application with the results from the previous coarse step. The implementation of this strategy is introduced in detail. The experiments results show that this combination strategy is effective for tracking real objects in robot vision applications.

AB - In this paper we have proposed a visual tracking strategy for 3D object recognition and tracking in robot vision applications. We adopt a Coarse-to-Fine combination strategy for 3D object tracking. In the coarse step, compared with those edge-based only methods, the convergence range of initial camera pose estimation has been enlarged in our system by a template-based matching between a series of template images rendered from Computer Graphics (CG) and a current image. In the fine step an edge-based object tracking method is used to realize a more accurate visual tracking application with the results from the previous coarse step. The implementation of this strategy is introduced in detail. The experiments results show that this combination strategy is effective for tracking real objects in robot vision applications.

UR - http://www.scopus.com/inward/record.url?scp=84860749877&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84860749877&partnerID=8YFLogxK

U2 - 10.1109/ROBIO.2011.6181415

DO - 10.1109/ROBIO.2011.6181415

M3 - Conference contribution

AN - SCOPUS:84860749877

SN - 9781457721373

T3 - 2011 IEEE International Conference on Robotics and Biomimetics, ROBIO 2011

SP - 981

EP - 986

BT - 2011 IEEE International Conference on Robotics and Biomimetics, ROBIO 2011

T2 - 2011 IEEE International Conference on Robotics and Biomimetics, ROBIO 2011

Y2 - 7 December 2011 through 11 December 2011

ER -