A Low-Texture Robust Hybrid Feature Based Visual Odometry

Page view(s)
12
Checked on Nov 27, 2024
A Low-Texture Robust Hybrid Feature Based Visual Odometry
Title:
A Low-Texture Robust Hybrid Feature Based Visual Odometry
Journal Title:
IROS
DOI:
Publication URL:
Keywords:
Publication Date:
19 October 2024
Citation:
He Wang, Qi Zhang, Zhiwen Zheng, Xiaoli Li, Ru Li, "A Low-Texture Robust Hybrid Feature Based Visual Odometry", IROS 2024
Abstract:
In low-texture scenes, Visual Odometry (VO) algorithms often encounter challenges stemming from sparse feature sets and reduced accuracy in feature matching. To overcome this, integrating plane features and vanishing point characteristics can provide additional constraints for refining camera poses. Optical flow-based tracking methods may also offer improved matching precision compared to traditional featurebased approaches. Motivated by these challenges, we present a robust Visual Odometry system tailored for low-texture environments. Our system combines a vanishing point-based approach for camera pose optimization with a Manhattan-aided algorithm for matching line segments using optical flow. By incorporating planes and vanishing points as supplementary features for pose estimation, we enhance overall accuracy without significant time overhead.We utilize detected line features to compute vanishing points, improving accuracy without compromising efficiency. In addition, our Manhattan-aided optical flow technique supplements and refines the results of line feature matching, further enhancing the accuracy of vanishing points. Evaluation on various public datasets demonstrates the superior accuracy and robustness of our system compared to state-ofthe- art Simultaneous Localization And Mapping (SLAM) and VO methods. Notably, our method effectively addresses issues of failure in low-texture scenes and improves the accuracy of line feature matching compared to baseline methods. We will release our source code upon paper acceptance.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the Science and Technology Cooperation and Exchange Special Project of ShanXi Province under Grant 202204041101016, in part by the 1331 Engineering Project of Shanxi Province - NA
Grant Reference no. : 215541015
Description:
© 2024 IEEE.  Personal use of this material is permitted.  Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISBN:
NIL
Files uploaded:

File Size Format Action
iros24-1632-fi.pdf 5.55 MB PDF Request a copy