Automatic vocabulary and graph verification for accurate loop closure detection

Page view(s)
13
Checked on Sep 10, 2023
Automatic vocabulary and graph verification for accurate loop closure detection
Title:
Automatic vocabulary and graph verification for accurate loop closure detection
Journal Title:
Journal of Field Robotics
Publication Date:
10 June 2022
Citation:
Yue, H., Miao, J., Chen, W., Wang, W., Guo, F., & Li, Z. (2022). Automatic vocabulary and graph verification for accurate loop closure detection. Journal of Field Robotics, 39(7), 1071–1086. Portico. https://doi.org/10.1002/rob.22088
Abstract:
Localizing previously visited places during long-term localization and mapping, i.e., loop closure detection (LCD), is a crucial technique to correct accumulated inconsistencies. In common bag-of-words (BoW) model, a visual vocabulary is built to associate features for detecting loops. Currently, methods that build vocabularies off-line determine scales of the vocabulary by trial-and-error, which results in unreasonable feature association. Moreover, the detection precision of the algorithm declines due to perceptual aliasing given that the BoW-based method ignores the positions of visual features. To build the optimal vocabulary automatically and eliminate human heuristics, we propose a natural convergence criterion based on the comparison between the radii of nodes and the drifts of feature descriptors in vocabulary construction. Furthermore, a novel topological graph verification method is proposed for validating loop candidates, which can effectively distinguish visual ambiguities by involving geometrical position of features and thus improve the precision of LCD. Experiments on various public datasets verify the effectiveness of our proposed approach.
License type:
Publisher Copyright
Funding Info:
This research was funded by National Natural Science Foundation of China (No.61603020, No.61620106012), the Fundamental Research Funds for the Central Universities (No.YWF21-BJ-J-923), and the Foundation of Strengthening Program Technology Fund Projects (No. 2019-JCJQ-JJ-268).
Description:
This is the peer reviewed version of the following article: Yue, H., Miao, J., Chen, W., Wang, W., Guo, F., & Li, Z. (2022). Automatic vocabulary and graph verification for accurate loop closure detection. Journal of Field Robotics, 39(7), 1071–1086. Portico. https://doi.org/10.1002/rob.22088, which has been published in final form at doi.org/10.1002/rob.22088. This article may be used for non-commercial purposes in accordance with Wiley Terms and Conditions for Use of Self-Archived Versions. This article may not be enhanced, enriched or otherwise transformed into a derivative work, without express permission from Wiley or by statutory rights under applicable legislation. Copyright notices must not be removed, obscured or modified. The article must be linked to Wiley’s version of record on Wiley Online Library and any embedding, framing or otherwise making available the article or pages thereof by third parties from platforms, services and websites other than Wiley Online Library must be prohibited
ISSN:
1556-4959
1556-4967
Files uploaded:

File Size Format Action
jfr22.pdf 1.84 MB PDF Open