Efficient Non-Consecutive Feature Tracking for Structure-from-Motion
Abstract
Structure-from-motion (SfM) is an important computer vision problem and largely relies on the quality of feature tracking. In image sequences, if disjointed tracks caused by objects moving in and out of the view, occasional occlusion, or image noise, are not handled well, the corresponding SfM could be significantly affected. In this paper, we address the non-consecutive feature point tracking problem and propose an effective method to match interrupted tracks. Our framework consists of steps of solving the feature ‘dropout’ problem when indistinctive structures, noise or even large image distortion exist, and of rapidly recognizing and joining common features located in different subsequences. Experimental results on several challenging and large-scale video sets show that our method notably improves SfM.
Cite
Text
Zhang et al. "Efficient Non-Consecutive Feature Tracking for Structure-from-Motion." European Conference on Computer Vision, 2010. doi:10.1007/978-3-642-15555-0_31Markdown
[Zhang et al. "Efficient Non-Consecutive Feature Tracking for Structure-from-Motion." European Conference on Computer Vision, 2010.](https://mlanthology.org/eccv/2010/zhang2010eccv-efficient/) doi:10.1007/978-3-642-15555-0_31BibTeX
@inproceedings{zhang2010eccv-efficient,
title = {{Efficient Non-Consecutive Feature Tracking for Structure-from-Motion}},
author = {Zhang, Guofeng and Dong, Zilong and Jia, Jiaya and Wong, Tien-Tsin and Bao, Hujun},
booktitle = {European Conference on Computer Vision},
year = {2010},
pages = {422-435},
doi = {10.1007/978-3-642-15555-0_31},
url = {https://mlanthology.org/eccv/2010/zhang2010eccv-efficient/}
}