Computer Graphics Laboratory ETH Zurich

ETH

MasterCam FVV: Robust registration of multiview sports video to a static high-resolution master camera for free viewpoint video

F. Angehrn, O. Wang, Y. Aksoy, M. Gross, A. Smolic

Image Processing (ICIP), 2014 IEEE International Conference on, , vol. , no. , 2014, pp. 3474-3478
[Abstract] [BibTeX] [PDF]

Abstract

Free viewpoint video enables interactive viewpoint selection in real world scenes, which is attractive for many applications such as sports visualization. Multi-camera registration is one of the difficult tasks in such systems. We introduce the concept of a static high resolution master camera for improved long-term multiview alignment. All broadcast cameras are aligned to a common reference. Our approach builds on frame-to-frame alignment, extended into a recursive long-term estimation process, which is shown to be accurate, robust and stable over long sequences.

@INPROCEEDINGS{7025705,
author={Angehrn, F. and Wang, O. and Aksoy, Y. and Gross, M. and Smolic, A.},
booktitle={Image Processing (ICIP), 2014 IEEE International Conference on},
title={MasterCam FVV: Robust registration of multiview sports video to a static high-resolution master camera for free viewpoint video},
year={2014},
month={Oct},
pages={3474-3478},
keywords={cameras;data visualisation;image registration;image resolution;MasterCam FVV;frame-to-frame alignment;free viewpoint video;interactive viewpoint selection;long-term estimation process;multicamera registration;sports visualization;static high-resolution master camera;Calibration;Cameras;Estimation;Image edge detection;Production;Robustness;Three-dimensional displays;Free viewpoint video;alignment;camera registration;multiview video;sports visualization},
doi={10.1109/ICIP.2014.7025705},
}
[Download BibTeX]

Downloads

Download Paper
[PDF]