Rectifying Rolling Shutter Video from Hand-Held Devices
Abstract
This paper presents a method for rectifying video sequences from rolling shutter (RS) cameras. In contrast to previous RS rectification attempts we model distortions as being caused by the 3D motion of the camera. The camera motion is parametrised as a continuous curve, with knots at the last row of each frame. Curve parameters are solved for using non-linear least squares over inter-frame correspondences obtained from a KLT tracker. We have generated synthetic RS sequences with associated ground-truth to allow controlled evaluation. Using these sequences, we demonstrate that our algorithm improves over to two previously published methods. The RS dataset is available on the web to allow comparison with other methods.
Cite
Text
Forssén and Ringaby. "Rectifying Rolling Shutter Video from Hand-Held Devices." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010. doi:10.1109/CVPR.2010.5540173Markdown
[Forssén and Ringaby. "Rectifying Rolling Shutter Video from Hand-Held Devices." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2010.](https://mlanthology.org/cvpr/2010/forssen2010cvpr-rectifying/) doi:10.1109/CVPR.2010.5540173BibTeX
@inproceedings{forssen2010cvpr-rectifying,
title = {{Rectifying Rolling Shutter Video from Hand-Held Devices}},
author = {Forssén, Per-Erik and Ringaby, Erik},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2010},
pages = {507-514},
doi = {10.1109/CVPR.2010.5540173},
url = {https://mlanthology.org/cvpr/2010/forssen2010cvpr-rectifying/}
}