Robust Global Motion Compensation in Presence of Predominant Foreground
Seyed Morteza Safdarnejad, Xiaoming Liu and Lalita Udpa
Abstract
Global motion compensation (GMC) removes intentional and unwanted camera motion. GMC is widely applicable for video stitching and, as a pre-processing module, for motion-based video analysis. While state-of-the-art GMC algorithms generally estimate homography satisfactorily between consecutive frames, their performances deteriorate on real-world unconstrained videos, for instance, videos with predominant foreground, e.g., moving objects or human, or uniform background. Since GMC transformation of frames to the global motion-compensated coordinate is done by cascading homographies, failure in GMC of a single frame drastically harms the final result. Thus, we propose a robust GMC, termed RGMC, based on homography estimation using keypoint matches. RGMC first suppresses the foreground impact by clustering the keypoint matches and removing those pertaining to the foreground, as well as erroneous matches. For homography verification, we propose a probabilistic model that combines keypoint matching error, consistency of edges after homograhy transformation, the motion history, and prior camera motion information. Experimental results on the Sports Videos in the Wild, Holleywood2, and HMDB51 datasets demonstrate the superiority of RGMC.
Session
Poster 1
Files
Extended Abstract (PDF, 250K)
Paper (PDF, 7M)
DOI
10.5244/C.29.21
https://dx.doi.org/10.5244/C.29.21
Citation
Seyed Morteza Safdarnejad, Xiaoming Liu and Lalita Udpa. Robust Global Motion Compensation in Presence of Predominant Foreground. In Xianghua Xie, Mark W. Jones, and Gary K. L. Tam, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 21.1-21.11. BMVA Press, September 2015.
Bibtex
@inproceedings{BMVC2015_21,
title={Robust Global Motion Compensation in Presence of Predominant Foreground},
author={Seyed Morteza Safdarnejad and Xiaoming Liu and Lalita Udpa},
year={2015},
month={September},
pages={21.1-21.11},
articleno={21},
numpages={11},
booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
publisher={BMVA Press},
editor={Xianghua Xie, Mark W. Jones, and Gary K. L. Tam},
doi={10.5244/C.29.21},
isbn={1-901725-53-7},
url={https://dx.doi.org/10.5244/C.29.21}
}