Shaking Video Synthesis for Video Stabilization Performance Assessment

Hui Qu
Li Song
Gengjian Xue

Shanghai Jiao Tong University


Abstract

The goal of video stabilization is to remove the unwanted camera motion and obtain stable versions. Theoretically, a good stabilization algorithm should remove the unwanted motion without the loss of image qualities. However, due to the lack of ground-truth video frames, the accurate performance evaluation of different algorithms is hard. Most existing evaluation techniques usually synthesize stable videos from shaking ones, but they are not effective enough. Different from previous methods, in this paper we propose a novel method which synthesize shaking videos from stable frames. Based on the synthetic shaking videos, we perform preliminary video stabilization performance assessment on three stabilization algorithms. Our shaking video synthesis method can not only give a benchmark for full-reference video stabilization performance assessment, but also provide a basis for exploring the theoretical bound of video stabilization which may help to improve existing stabilization algorithms.

Results

"bank": synthetic shaking videos

"bank": stabilized videos by three algorithms



comparison between synthetic(adding Jitter1)

and real shaking videos

comparison between synthetic(adding Jitter2)

and real shaking videos


More results are available on the website http://www.youku.com/playlist_show/id_19274439.html

Downloads


Shaking Video Synthesis for Video Stabilization Performance Assessment

Hui Qu, Li Song, Gengjian Xue

Visual Communications and Image Processing (VCIP), 2013.


Paper (pdf,3.42MB)



Presentation Sildes (pptx, 98.1MB)



Dataset (compressed, 16384kbps, 309MB)



Executable Program (two compressed test videos included, 41.9MB)


Citation

@inproceedings{qu2013shaking,
title={Shaking video synthesis for video stabilization performance assessment},
author={Qu, Hui and Song, Li and Xue, Gengjian},
booktitle={Visual Communications and Image Processing (VCIP), 2013},
pages={1--6},
year={2013},
organization={IEEE}
}