Visual Tracking in the Presence of Motion Blur
Abstract
We consider the problem of visual tracking of regions of interest in a sequence of motion blurred images. Traditional methods couple tracking with deblurring in order to correctly account for the effects of motion blur. Such coupling is usually appropriate, but computationally wasteful when visual tracking is the lone objective. Instead of deblurring images, we propose to match regions by blurring them. The matching score for two image regions is governed by a cost function that only involves the region deformation parameters and two motion blur vectors. We present an efficient algorithm to minimize the proposed cost function and demonstrate it on sequences of real blurred images.
Cite
Text
Jin et al. "Visual Tracking in the Presence of Motion Blur." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005. doi:10.1109/CVPR.2005.372Markdown
[Jin et al. "Visual Tracking in the Presence of Motion Blur." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2005.](https://mlanthology.org/cvpr/2005/jin2005cvpr-visual/) doi:10.1109/CVPR.2005.372BibTeX
@inproceedings{jin2005cvpr-visual,
title = {{Visual Tracking in the Presence of Motion Blur}},
author = {Jin, Hailin and Favaro, Paolo and Cipolla, Roberto},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2005},
pages = {18-25},
doi = {10.1109/CVPR.2005.372},
url = {https://mlanthology.org/cvpr/2005/jin2005cvpr-visual/}
}