Rectifying rolling shutter video from hand-held devices
Erik Ringaby, Per-Erik ForssénSSBA11
Proceedings SSBA'11 Symposium on Image Analysis
March 2011
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 two previously published methods. The RS dataset is available on the web to allow comparison with other methods.
Full Paper
This work was originally presented at the CVPR10 conference.
Bibtex entry
@InProceedings{ringaby11a, author = {Erik Ringaby and Per-Erik Forss\'en}, title = {Rectifying rolling shutter video from hand-held devices}, booktitle = {Proceedings {SSBA'11} Symposium on Image Analysis}, year = {2011}, month = {March}, note = {Non-reviewed workshop}, OPTpages = {} }
Per-Erik Forssén
Contact:
Computer Vision Laboratory
Department of Electrical Engineering
Building B
Room 2D:521
SE-581 83 Linköping, Sweden
+46(0)13 285654
< >
My pages:
Informationsansvarig: Per-Erik Forssén
Senast uppdaterad: 2024-09-28