Sliding Windowed Optimization Algorithm for Fusion of Redundant Stereo Visual Odometries
- 18 October 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 300-305
Abstract
We propose a sliding windowed graph-optimization based approach for the fusion of two stereo visual odometries with 6 degrees of freedom poses. Stereo odometries are calculated independently, using pairs of stereo images that are captured by stereo cameras mounted on the top of a moving platform. We implemented our sliding windowed approach using the public library LIBVISO2. Our results are compared against the two recognized SLAM frameworks ORB-SLAM2 and UCOSLAM. The relative pose error of the fused poses decreases by up to 94% in relation to the error of single stereo odometry and by up to 91% compared with the results of UCOSLAM.Keywords
Funding Information
- CNPq
- CAPES (001)
This publication has 18 references indexed in Scilit:
- ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D CamerasIEEE Transactions on Robotics, 2017
- Visual-Inertial Monocular SLAM With Map ReuseIEEE Robotics and Automation Letters, 2017
- Pose fusion with chain pose graphs for automated driving2016
- Keyframe-based visual–inertial odometry using nonlinear optimizationThe International Journal of Robotics Research, 2014
- A Fast Visual Odometry and Mapping System for RGB-D Cameras2014
- 3D Probabilistic Occupancy Grid to Robotic Mapping with Stereo Vision2012
- Visual Odometry [Tutorial]IEEE Robotics & Automation Magazine, 2011
- G2o: A general framework for graph optimization2011
- Bundle Adjustment — A Modern Synthesis2000
- Introduction to Lie Algebras and Representation Theory1972