Experiments on Visual Loop Closing Using Vocabulary Trees
Abstract
In this paper we study the problem of visual loop closing for long trajectories in an urban environment. We use GPS positioning only to narrow down the search area and use pre-built vocabulary trees to find the best matching image in this search area. Geometric consistency is then used to prune out the bad matches. We compare several vocabulary trees on a sequence of 6.5 kilometers. We experiment with hierarchical k-means based trees as well as extremely randomized trees and compare results obtained using five different trees. We obtain the best results using extremely randomized trees. After enforcing geometric consistency the matched images look promising for structure from motion applications.
Cite
Text
Kumar et al. "Experiments on Visual Loop Closing Using Vocabulary Trees." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2008. doi:10.1109/CVPRW.2008.4563140Markdown
[Kumar et al. "Experiments on Visual Loop Closing Using Vocabulary Trees." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2008.](https://mlanthology.org/cvprw/2008/kumar2008cvprw-experiments/) doi:10.1109/CVPRW.2008.4563140BibTeX
@inproceedings{kumar2008cvprw-experiments,
title = {{Experiments on Visual Loop Closing Using Vocabulary Trees}},
author = {Kumar, Ankita and Tardif, Jean-Philippe and Anati, Roy and Daniilidis, Kostas},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2008},
pages = {1-8},
doi = {10.1109/CVPRW.2008.4563140},
url = {https://mlanthology.org/cvprw/2008/kumar2008cvprw-experiments/}
}