Combining Kinect and PnP for camera pose estimation

Shu Zhang; Hui Yu; Junyu Dong; Ting Wang; Lin Qi; Honghai Liu

doi:10.1109/HSI.2015.7170693

Combining Kinect and PnP for camera pose estimation

Shu Zhang, Hui Yu, Junyu Dong, Ting Wang, Lin Qi, Honghai Liu

School of Computing

Ocean University of China

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

930 Downloads (Pure)

Abstract

This paper presents a novel method to conduct
camera pose estimation though combining Kinect and Perspectiven-points
algorithms. Most existing camera pose estimation
methods suffer from the errors caused by inevitable outliers
between 2D-3D correspondences. To this end, we propose to use a
random down sampling process to deal with outliers in this paper.
The proposed method is divided into two main steps, which are
2D-3D correspondences generation and pose estimation. The
method has been tested in a real project, and the experiment has
shown encouraging results compared to the ground truth.

Original language	English
Title of host publication	2015 8th International Conference on Human System Interactions (HSI)
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	357 - 361
Number of pages	5
ISBN (Print)	978-1467369374
DOIs	https://doi.org/10.1109/HSI.2015.7170693
Publication status	Published - Jun 2015

Access to Document

10.1109/HSI.2015.7170693

Combining_Kinect_and_PnP
© 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript (Post-print), 19.4 MB

Cite this

@inproceedings{2bd0a560e2ff40388636708610ab490a,

title = "Combining Kinect and PnP for camera pose estimation",

abstract = "This paper presents a novel method to conductcamera pose estimation though combining Kinect and Perspectiven-pointsalgorithms. Most existing camera pose estimationmethods suffer from the errors caused by inevitable outliersbetween 2D-3D correspondences. To this end, we propose to use arandom down sampling process to deal with outliers in this paper.The proposed method is divided into two main steps, which are2D-3D correspondences generation and pose estimation. Themethod has been tested in a real project, and the experiment hasshown encouraging results compared to the ground truth. ",

author = "Shu Zhang and Hui Yu and Junyu Dong and Ting Wang and Lin Qi and Honghai Liu",

year = "2015",

month = jun,

doi = "10.1109/HSI.2015.7170693",

language = "English",

isbn = "978-1467369374",

pages = "357 -- 361",

booktitle = "2015 8th International Conference on Human System Interactions (HSI)",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

}

TY - GEN

T1 - Combining Kinect and PnP for camera pose estimation

AU - Zhang, Shu

AU - Yu, Hui

AU - Dong, Junyu

AU - Wang, Ting

AU - Qi, Lin

AU - Liu, Honghai

PY - 2015/6

Y1 - 2015/6

N2 - This paper presents a novel method to conductcamera pose estimation though combining Kinect and Perspectiven-pointsalgorithms. Most existing camera pose estimationmethods suffer from the errors caused by inevitable outliersbetween 2D-3D correspondences. To this end, we propose to use arandom down sampling process to deal with outliers in this paper.The proposed method is divided into two main steps, which are2D-3D correspondences generation and pose estimation. Themethod has been tested in a real project, and the experiment hasshown encouraging results compared to the ground truth.

AB - This paper presents a novel method to conductcamera pose estimation though combining Kinect and Perspectiven-pointsalgorithms. Most existing camera pose estimationmethods suffer from the errors caused by inevitable outliersbetween 2D-3D correspondences. To this end, we propose to use arandom down sampling process to deal with outliers in this paper.The proposed method is divided into two main steps, which are2D-3D correspondences generation and pose estimation. Themethod has been tested in a real project, and the experiment hasshown encouraging results compared to the ground truth.

U2 - 10.1109/HSI.2015.7170693

DO - 10.1109/HSI.2015.7170693

M3 - Conference contribution

SN - 978-1467369374

SP - 357

EP - 361

BT - 2015 8th International Conference on Human System Interactions (HSI)

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Combining Kinect and PnP for camera pose estimation

Abstract

Access to Document

Fingerprint

Cite this