A Benchmark Dataset for 6DoF Object Pose Tracking

Po Chen Wu, Yueh Ying Lee, Hung Yu Tseng, Hsuan I. Ho, Ming Hsuan Yang, Shao Yi Chien

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

4 Citations (Scopus)

Abstract

Accurately tracking the six degree-of-freedom pose of an object in real scenes is an important task in computer vision and augmented reality with numerous applications. Although a variety of algorithms for this task have been proposed, it remains difficult to evaluate existing methods in the literature as oftentimes different sequences are used and no large benchmark datasets close to realworld scenarios are available. In this paper, we present a large object pose tracking benchmark dataset consisting of RGB-D video sequences of 2D and 3D targets with ground-truth information. The videos are recorded under various lighting conditions, different motion patterns and speeds with the help of a programmable robotic arm. We present extensive quantitative evaluation results of the state-of-the-art methods on this benchmark dataset and discuss the potential research directions in this field. The proposed benchmark dataset is available online at media.ee.ntu.edu.tw/research/OPT.

Original languageEnglish
Title of host publicationAdjunct Proceedings of the 2017 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2017
EditorsWolfgang Broll, Holger Regenbrecht, J Edward Swan, Gerd Bruder, Myriam Servieres, Maki Sugimoto
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages186-191
Number of pages6
ISBN (Electronic)9780769563275
DOIs
Publication statusPublished - 2017 Oct 27
Event16th Adjunct IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2017 - Nantes, France
Duration: 2017 Oct 92017 Oct 13

Publication series

NameAdjunct Proceedings of the 2017 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2017

Conference

Conference16th Adjunct IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2017
CountryFrance
CityNantes
Period17/10/917/10/13

Fingerprint

Robotic arms
Augmented reality
Computer vision
Lighting

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Human-Computer Interaction
  • Media Technology

Cite this

Wu, P. C., Lee, Y. Y., Tseng, H. Y., Ho, H. I., Yang, M. H., & Chien, S. Y. (2017). A Benchmark Dataset for 6DoF Object Pose Tracking. In W. Broll, H. Regenbrecht, J. E. Swan, G. Bruder, M. Servieres, & M. Sugimoto (Eds.), Adjunct Proceedings of the 2017 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2017 (pp. 186-191). [8088479] (Adjunct Proceedings of the 2017 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2017). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISMAR-Adjunct.2017.62
Wu, Po Chen ; Lee, Yueh Ying ; Tseng, Hung Yu ; Ho, Hsuan I. ; Yang, Ming Hsuan ; Chien, Shao Yi. / A Benchmark Dataset for 6DoF Object Pose Tracking. Adjunct Proceedings of the 2017 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2017. editor / Wolfgang Broll ; Holger Regenbrecht ; J Edward Swan ; Gerd Bruder ; Myriam Servieres ; Maki Sugimoto. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 186-191 (Adjunct Proceedings of the 2017 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2017).
@inproceedings{6f61d17518624608b457aac030dc598a,
title = "A Benchmark Dataset for 6DoF Object Pose Tracking",
abstract = "Accurately tracking the six degree-of-freedom pose of an object in real scenes is an important task in computer vision and augmented reality with numerous applications. Although a variety of algorithms for this task have been proposed, it remains difficult to evaluate existing methods in the literature as oftentimes different sequences are used and no large benchmark datasets close to realworld scenarios are available. In this paper, we present a large object pose tracking benchmark dataset consisting of RGB-D video sequences of 2D and 3D targets with ground-truth information. The videos are recorded under various lighting conditions, different motion patterns and speeds with the help of a programmable robotic arm. We present extensive quantitative evaluation results of the state-of-the-art methods on this benchmark dataset and discuss the potential research directions in this field. The proposed benchmark dataset is available online at media.ee.ntu.edu.tw/research/OPT.",
author = "Wu, {Po Chen} and Lee, {Yueh Ying} and Tseng, {Hung Yu} and Ho, {Hsuan I.} and Yang, {Ming Hsuan} and Chien, {Shao Yi}",
year = "2017",
month = "10",
day = "27",
doi = "10.1109/ISMAR-Adjunct.2017.62",
language = "English",
series = "Adjunct Proceedings of the 2017 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "186--191",
editor = "Wolfgang Broll and Holger Regenbrecht and Swan, {J Edward} and Gerd Bruder and Myriam Servieres and Maki Sugimoto",
booktitle = "Adjunct Proceedings of the 2017 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2017",
address = "United States",

}

Wu, PC, Lee, YY, Tseng, HY, Ho, HI, Yang, MH & Chien, SY 2017, A Benchmark Dataset for 6DoF Object Pose Tracking. in W Broll, H Regenbrecht, JE Swan, G Bruder, M Servieres & M Sugimoto (eds), Adjunct Proceedings of the 2017 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2017., 8088479, Adjunct Proceedings of the 2017 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2017, Institute of Electrical and Electronics Engineers Inc., pp. 186-191, 16th Adjunct IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2017, Nantes, France, 17/10/9. https://doi.org/10.1109/ISMAR-Adjunct.2017.62

A Benchmark Dataset for 6DoF Object Pose Tracking. / Wu, Po Chen; Lee, Yueh Ying; Tseng, Hung Yu; Ho, Hsuan I.; Yang, Ming Hsuan; Chien, Shao Yi.

Adjunct Proceedings of the 2017 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2017. ed. / Wolfgang Broll; Holger Regenbrecht; J Edward Swan; Gerd Bruder; Myriam Servieres; Maki Sugimoto. Institute of Electrical and Electronics Engineers Inc., 2017. p. 186-191 8088479 (Adjunct Proceedings of the 2017 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2017).

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

TY - GEN

T1 - A Benchmark Dataset for 6DoF Object Pose Tracking

AU - Wu, Po Chen

AU - Lee, Yueh Ying

AU - Tseng, Hung Yu

AU - Ho, Hsuan I.

AU - Yang, Ming Hsuan

AU - Chien, Shao Yi

PY - 2017/10/27

Y1 - 2017/10/27

N2 - Accurately tracking the six degree-of-freedom pose of an object in real scenes is an important task in computer vision and augmented reality with numerous applications. Although a variety of algorithms for this task have been proposed, it remains difficult to evaluate existing methods in the literature as oftentimes different sequences are used and no large benchmark datasets close to realworld scenarios are available. In this paper, we present a large object pose tracking benchmark dataset consisting of RGB-D video sequences of 2D and 3D targets with ground-truth information. The videos are recorded under various lighting conditions, different motion patterns and speeds with the help of a programmable robotic arm. We present extensive quantitative evaluation results of the state-of-the-art methods on this benchmark dataset and discuss the potential research directions in this field. The proposed benchmark dataset is available online at media.ee.ntu.edu.tw/research/OPT.

AB - Accurately tracking the six degree-of-freedom pose of an object in real scenes is an important task in computer vision and augmented reality with numerous applications. Although a variety of algorithms for this task have been proposed, it remains difficult to evaluate existing methods in the literature as oftentimes different sequences are used and no large benchmark datasets close to realworld scenarios are available. In this paper, we present a large object pose tracking benchmark dataset consisting of RGB-D video sequences of 2D and 3D targets with ground-truth information. The videos are recorded under various lighting conditions, different motion patterns and speeds with the help of a programmable robotic arm. We present extensive quantitative evaluation results of the state-of-the-art methods on this benchmark dataset and discuss the potential research directions in this field. The proposed benchmark dataset is available online at media.ee.ntu.edu.tw/research/OPT.

UR - http://www.scopus.com/inward/record.url?scp=85040222900&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040222900&partnerID=8YFLogxK

U2 - 10.1109/ISMAR-Adjunct.2017.62

DO - 10.1109/ISMAR-Adjunct.2017.62

M3 - Conference contribution

AN - SCOPUS:85040222900

T3 - Adjunct Proceedings of the 2017 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2017

SP - 186

EP - 191

BT - Adjunct Proceedings of the 2017 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2017

A2 - Broll, Wolfgang

A2 - Regenbrecht, Holger

A2 - Swan, J Edward

A2 - Bruder, Gerd

A2 - Servieres, Myriam

A2 - Sugimoto, Maki

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Wu PC, Lee YY, Tseng HY, Ho HI, Yang MH, Chien SY. A Benchmark Dataset for 6DoF Object Pose Tracking. In Broll W, Regenbrecht H, Swan JE, Bruder G, Servieres M, Sugimoto M, editors, Adjunct Proceedings of the 2017 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 186-191. 8088479. (Adjunct Proceedings of the 2017 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2017). https://doi.org/10.1109/ISMAR-Adjunct.2017.62