Research on Evaluation Method of Video Stabilization

DOI

10.2991/amsee-16.2016.67How to use a DOI?

Keywords

video stabilization; evaluation method; global motion vector; VIA

Abstract

In order to accomplish the task of evaluating video stabilization, we divided videos into four classes according to the state of the cameras and moving targets in the monitoring areas. It also analyzed the difficulties of evaluating video stabilization in each condition. As PSNR(peak signal to noise ratio) becomes disabled with moving cameras, we proposed a novel evaluation method based on the VIA(variation of intersection angles) between global motion vectors. In order to decrease the influences to PSNR caused by moving objects in FOV(field of view), we computed PSNR of the overlapping background instead of the whole image achieved by fixed camera. As moving objects also affect VIA, we deleted the motion vectors on them and removed the related interference. As the experiments show, the evaluating architecture proposed in this paper can remove the disturbance caused by moving objects in every class of video and evaluate video stabilization correctly.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Bin Chen
AU  - Jianjun Zhao
AU  - Yi Wang
PY  - 2016/04
DA  - 2016/04
TI  - Research on Evaluation Method of Video Stabilization
BT  - Proceedings of the 2016 International Conference on Advanced Materials Science and Environmental Engineering
PB  - Atlantis Press
SP  - 251
EP  - 256
SN  - 2352-5401
UR  - https://doi.org/10.2991/amsee-16.2016.67
DO  - 10.2991/amsee-16.2016.67
ID  - Chen2016/04
ER  -