Robust plane-based calibration of multiple non-overlapping cameras

Chen Zhu, Zihan Zhou, Ziran Xing, Yanbing Dong, Yi Ma, Jingyi Yu

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

4 Citations (Scopus)

Abstract

The availability of commodity multi-camera systems such as Google Jump, Jaunt, and Lytro Immerge have brought new demand for reliable and efficient extrinsic camera calibration. State-of-the-art solutions generally require that adjacent, if not all, cameras observe a common area or employ known scene structures. In this paper, we present a novel multi-camera calibration technique that eliminates such requirements. Our approach extends the single-pair hand-eye calibration used in robotics to multi-camera systems. Specifically, we make use of (possibly unknown) planar structures in the scene and combine plane-based structure from motion, camera pose estimation, and task-specific bundle adjustment for extrinsic calibration. Experiments on several multi-camera setups demonstrate that our scheme is highly accurate, robust, and efficient.

Original languageEnglish (US)
Title of host publicationProceedings - 2016 4th International Conference on 3D Vision, 3DV 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages658-666
Number of pages9
ISBN (Electronic)9781509054077
DOIs
StatePublished - Dec 15 2016
Event4th International Conference on 3D Vision, 3DV 2016 - Stanford, United States
Duration: Oct 25 2016Oct 28 2016

Publication series

NameProceedings - 2016 4th International Conference on 3D Vision, 3DV 2016

Conference

Conference4th International Conference on 3D Vision, 3DV 2016
CountryUnited States
CityStanford
Period10/25/1610/28/16

Fingerprint

Cameras
Calibration
End effectors
Robotics
Availability
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Zhu, C., Zhou, Z., Xing, Z., Dong, Y., Ma, Y., & Yu, J. (2016). Robust plane-based calibration of multiple non-overlapping cameras. In Proceedings - 2016 4th International Conference on 3D Vision, 3DV 2016 (pp. 658-666). [7785142] (Proceedings - 2016 4th International Conference on 3D Vision, 3DV 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/3DV.2016.73
Zhu, Chen ; Zhou, Zihan ; Xing, Ziran ; Dong, Yanbing ; Ma, Yi ; Yu, Jingyi. / Robust plane-based calibration of multiple non-overlapping cameras. Proceedings - 2016 4th International Conference on 3D Vision, 3DV 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 658-666 (Proceedings - 2016 4th International Conference on 3D Vision, 3DV 2016).
@inproceedings{edb36900590a4e86920a45a60ac0dea5,
title = "Robust plane-based calibration of multiple non-overlapping cameras",
abstract = "The availability of commodity multi-camera systems such as Google Jump, Jaunt, and Lytro Immerge have brought new demand for reliable and efficient extrinsic camera calibration. State-of-the-art solutions generally require that adjacent, if not all, cameras observe a common area or employ known scene structures. In this paper, we present a novel multi-camera calibration technique that eliminates such requirements. Our approach extends the single-pair hand-eye calibration used in robotics to multi-camera systems. Specifically, we make use of (possibly unknown) planar structures in the scene and combine plane-based structure from motion, camera pose estimation, and task-specific bundle adjustment for extrinsic calibration. Experiments on several multi-camera setups demonstrate that our scheme is highly accurate, robust, and efficient.",
author = "Chen Zhu and Zihan Zhou and Ziran Xing and Yanbing Dong and Yi Ma and Jingyi Yu",
year = "2016",
month = "12",
day = "15",
doi = "10.1109/3DV.2016.73",
language = "English (US)",
series = "Proceedings - 2016 4th International Conference on 3D Vision, 3DV 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "658--666",
booktitle = "Proceedings - 2016 4th International Conference on 3D Vision, 3DV 2016",
address = "United States",

}

Zhu, C, Zhou, Z, Xing, Z, Dong, Y, Ma, Y & Yu, J 2016, Robust plane-based calibration of multiple non-overlapping cameras. in Proceedings - 2016 4th International Conference on 3D Vision, 3DV 2016., 7785142, Proceedings - 2016 4th International Conference on 3D Vision, 3DV 2016, Institute of Electrical and Electronics Engineers Inc., pp. 658-666, 4th International Conference on 3D Vision, 3DV 2016, Stanford, United States, 10/25/16. https://doi.org/10.1109/3DV.2016.73

Robust plane-based calibration of multiple non-overlapping cameras. / Zhu, Chen; Zhou, Zihan; Xing, Ziran; Dong, Yanbing; Ma, Yi; Yu, Jingyi.

Proceedings - 2016 4th International Conference on 3D Vision, 3DV 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 658-666 7785142 (Proceedings - 2016 4th International Conference on 3D Vision, 3DV 2016).

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

TY - GEN

T1 - Robust plane-based calibration of multiple non-overlapping cameras

AU - Zhu, Chen

AU - Zhou, Zihan

AU - Xing, Ziran

AU - Dong, Yanbing

AU - Ma, Yi

AU - Yu, Jingyi

PY - 2016/12/15

Y1 - 2016/12/15

N2 - The availability of commodity multi-camera systems such as Google Jump, Jaunt, and Lytro Immerge have brought new demand for reliable and efficient extrinsic camera calibration. State-of-the-art solutions generally require that adjacent, if not all, cameras observe a common area or employ known scene structures. In this paper, we present a novel multi-camera calibration technique that eliminates such requirements. Our approach extends the single-pair hand-eye calibration used in robotics to multi-camera systems. Specifically, we make use of (possibly unknown) planar structures in the scene and combine plane-based structure from motion, camera pose estimation, and task-specific bundle adjustment for extrinsic calibration. Experiments on several multi-camera setups demonstrate that our scheme is highly accurate, robust, and efficient.

AB - The availability of commodity multi-camera systems such as Google Jump, Jaunt, and Lytro Immerge have brought new demand for reliable and efficient extrinsic camera calibration. State-of-the-art solutions generally require that adjacent, if not all, cameras observe a common area or employ known scene structures. In this paper, we present a novel multi-camera calibration technique that eliminates such requirements. Our approach extends the single-pair hand-eye calibration used in robotics to multi-camera systems. Specifically, we make use of (possibly unknown) planar structures in the scene and combine plane-based structure from motion, camera pose estimation, and task-specific bundle adjustment for extrinsic calibration. Experiments on several multi-camera setups demonstrate that our scheme is highly accurate, robust, and efficient.

UR - http://www.scopus.com/inward/record.url?scp=85011271376&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85011271376&partnerID=8YFLogxK

U2 - 10.1109/3DV.2016.73

DO - 10.1109/3DV.2016.73

M3 - Conference contribution

AN - SCOPUS:85011271376

T3 - Proceedings - 2016 4th International Conference on 3D Vision, 3DV 2016

SP - 658

EP - 666

BT - Proceedings - 2016 4th International Conference on 3D Vision, 3DV 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Zhu C, Zhou Z, Xing Z, Dong Y, Ma Y, Yu J. Robust plane-based calibration of multiple non-overlapping cameras. In Proceedings - 2016 4th International Conference on 3D Vision, 3DV 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 658-666. 7785142. (Proceedings - 2016 4th International Conference on 3D Vision, 3DV 2016). https://doi.org/10.1109/3DV.2016.73