Learning Features for Tracking
Abstract
We treat tracking as a matching problem of detected key-points between successive frames. The novelty of this paper is to learn classifier-based keypoint descriptions allowing to incorporate background information. Contrary to existing approaches, we are able to start tracking of the object from scratch requiring no off-line training phase before tracking. The tracker is initialized by a region of interest in the first frame. Afterwards an on-line boosting technique is used for learning descriptions of detected keypoints lying within the region of interest. New frames provide new samples for updating the classifiers which increases their stability. A simple mechanism incorporates temporal information for selecting stable features. In order to ensure correct updates a verification step based on estimating homographies using RANSAC is performed. The approach can be used for real-time applications since on-line updating and evaluating classifiers can be done efficiently.
Cite
Text
Grabner et al. "Learning Features for Tracking." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2007. doi:10.1109/CVPR.2007.382995Markdown
[Grabner et al. "Learning Features for Tracking." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2007.](https://mlanthology.org/cvpr/2007/grabner2007cvpr-learning/) doi:10.1109/CVPR.2007.382995BibTeX
@inproceedings{grabner2007cvpr-learning,
title = {{Learning Features for Tracking}},
author = {Grabner, Michael and Grabner, Helmut and Bischof, Horst},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2007},
doi = {10.1109/CVPR.2007.382995},
url = {https://mlanthology.org/cvpr/2007/grabner2007cvpr-learning/}
}