A Non-Linear Filter for Gyroscope-Based Video Stabilization

Abstract

We present a method for video stabilization and rolling-shutter correction for videos captured on mobile devices. The method uses the data from an on-board gyroscope to track the camera’s angular velocity, and can run in real time within the camera capture pipeline. We remove small motions and rolling-shutter distortions due to hand shake, creating the impression of a video shot on a tripod. For larger motions, we filter the camera’s angular velocity to produce a smooth output. To meet the latency constraints of a real-time camera capture pipeline, our filter operates on a small temporal window of three to five frames. Our algorithm performs better than the previous work that uses a gyroscope to stabilize a video stream, and at a similar level with respect to current feature-based methods.

Cite

Text

Bell et al. "A Non-Linear Filter for Gyroscope-Based Video Stabilization." European Conference on Computer Vision, 2014. doi:10.1007/978-3-319-10593-2_20

Markdown

[Bell et al. "A Non-Linear Filter for Gyroscope-Based Video Stabilization." European Conference on Computer Vision, 2014.](https://mlanthology.org/eccv/2014/bell2014eccv-non/) doi:10.1007/978-3-319-10593-2_20

BibTeX

@inproceedings{bell2014eccv-non,
  title     = {{A Non-Linear Filter for Gyroscope-Based Video Stabilization}},
  author    = {Bell, Steven and Troccoli, Alejandro J. and Pulli, Kari},
  booktitle = {European Conference on Computer Vision},
  year      = {2014},
  pages     = {294-308},
  doi       = {10.1007/978-3-319-10593-2_20},
  url       = {https://mlanthology.org/eccv/2014/bell2014eccv-non/}
}