A Fast and Robust Extrinsic Calibration for RGB-D Camera Networks
From object tracking to 3D reconstruction, RGB-Depth (RGB-D) camera networks play an increasingly important role in many vision and graphics applications. Practical applications often use sparsely-placed cameras to maximize visibility, while using as few cameras as possible to minimize cost. In gene...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/18/1/235 |
| _version_ | 1811300410508443648 |
|---|---|
| author | Po-Chang Su Ju Shen Wanxin Xu Sen-Ching S. Cheung Ying Luo |
| author_facet | Po-Chang Su Ju Shen Wanxin Xu Sen-Ching S. Cheung Ying Luo |
| author_sort | Po-Chang Su |
| collection | DOAJ |
| description | From object tracking to 3D reconstruction, RGB-Depth (RGB-D) camera networks play an increasingly important role in many vision and graphics applications. Practical applications often use sparsely-placed cameras to maximize visibility, while using as few cameras as possible to minimize cost. In general, it is challenging to calibrate sparse camera networks due to the lack of shared scene features across different camera views. In this paper, we propose a novel algorithm that can accurately and rapidly calibrate the geometric relationships across an arbitrary number of RGB-D cameras on a network. Our work has a number of novel features. First, to cope with the wide separation between different cameras, we establish view correspondences by using a spherical calibration object. We show that this approach outperforms other techniques based on planar calibration objects. Second, instead of modeling camera extrinsic calibration using rigid transformation, which is optimal only for pinhole cameras, we systematically test different view transformation functions including rigid transformation, polynomial transformation and manifold regression to determine the most robust mapping that generalizes well to unseen data. Third, we reformulate the celebrated bundle adjustment procedure to minimize the global 3D reprojection error so as to fine-tune the initial estimates. Finally, our scalable client-server architecture is computationally efficient: the calibration of a five-camera system, including data capture, can be done in minutes using only commodity PCs. Our proposed framework is compared with other state-of-the-arts systems using both quantitative measurements and visual alignment results of the merged point clouds. |
| first_indexed | 2024-04-13T06:50:47Z |
| format | Article |
| id | doaj.art-e121b8becbbc449690f27fef424a9537 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-13T06:50:47Z |
| publishDate | 2018-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-e121b8becbbc449690f27fef424a95372022-12-22T02:57:25ZengMDPI AGSensors1424-82202018-01-0118123510.3390/s18010235s18010235A Fast and Robust Extrinsic Calibration for RGB-D Camera NetworksPo-Chang Su0Ju Shen1Wanxin Xu2Sen-Ching S. Cheung3Ying Luo4Center for Visualization and Virtual Environments, University of Kentucky, Lexington, KY 40506, USAInteractive Visual Media (IVDIA) Lab, University of Dayton, Dayton, OH 45469, USACenter for Visualization and Virtual Environments, University of Kentucky, Lexington, KY 40506, USACenter for Visualization and Virtual Environments, University of Kentucky, Lexington, KY 40506, USADepartment of Computer Information Technology and Graphics, Purdue University Northwest, Hammond, IN 46323, USAFrom object tracking to 3D reconstruction, RGB-Depth (RGB-D) camera networks play an increasingly important role in many vision and graphics applications. Practical applications often use sparsely-placed cameras to maximize visibility, while using as few cameras as possible to minimize cost. In general, it is challenging to calibrate sparse camera networks due to the lack of shared scene features across different camera views. In this paper, we propose a novel algorithm that can accurately and rapidly calibrate the geometric relationships across an arbitrary number of RGB-D cameras on a network. Our work has a number of novel features. First, to cope with the wide separation between different cameras, we establish view correspondences by using a spherical calibration object. We show that this approach outperforms other techniques based on planar calibration objects. Second, instead of modeling camera extrinsic calibration using rigid transformation, which is optimal only for pinhole cameras, we systematically test different view transformation functions including rigid transformation, polynomial transformation and manifold regression to determine the most robust mapping that generalizes well to unseen data. Third, we reformulate the celebrated bundle adjustment procedure to minimize the global 3D reprojection error so as to fine-tune the initial estimates. Finally, our scalable client-server architecture is computationally efficient: the calibration of a five-camera system, including data capture, can be done in minutes using only commodity PCs. Our proposed framework is compared with other state-of-the-arts systems using both quantitative measurements and visual alignment results of the merged point clouds.http://www.mdpi.com/1424-8220/18/1/235RGB-D cameraspherical objectcamera network calibration3D reconstruction |
| spellingShingle | Po-Chang Su Ju Shen Wanxin Xu Sen-Ching S. Cheung Ying Luo A Fast and Robust Extrinsic Calibration for RGB-D Camera Networks Sensors RGB-D camera spherical object camera network calibration 3D reconstruction |
| title | A Fast and Robust Extrinsic Calibration for RGB-D Camera Networks |
| title_full | A Fast and Robust Extrinsic Calibration for RGB-D Camera Networks |
| title_fullStr | A Fast and Robust Extrinsic Calibration for RGB-D Camera Networks |
| title_full_unstemmed | A Fast and Robust Extrinsic Calibration for RGB-D Camera Networks |
| title_short | A Fast and Robust Extrinsic Calibration for RGB-D Camera Networks |
| title_sort | fast and robust extrinsic calibration for rgb d camera networks |
| topic | RGB-D camera spherical object camera network calibration 3D reconstruction |
| url | http://www.mdpi.com/1424-8220/18/1/235 |
| work_keys_str_mv | AT pochangsu afastandrobustextrinsiccalibrationforrgbdcameranetworks AT jushen afastandrobustextrinsiccalibrationforrgbdcameranetworks AT wanxinxu afastandrobustextrinsiccalibrationforrgbdcameranetworks AT senchingscheung afastandrobustextrinsiccalibrationforrgbdcameranetworks AT yingluo afastandrobustextrinsiccalibrationforrgbdcameranetworks AT pochangsu fastandrobustextrinsiccalibrationforrgbdcameranetworks AT jushen fastandrobustextrinsiccalibrationforrgbdcameranetworks AT wanxinxu fastandrobustextrinsiccalibrationforrgbdcameranetworks AT senchingscheung fastandrobustextrinsiccalibrationforrgbdcameranetworks AT yingluo fastandrobustextrinsiccalibrationforrgbdcameranetworks |