.png){kind=icon}
返回
A Parallel Nonlinear Factor Recovery Method for VIO Based on a Factor Graph
.png){kind=icon}
PRE
AI
DOI：10.1109/TIM.2023.3320757.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Under factor graph-based visual-inertial odometry (VIO), is usually used to limit the continuously increasing numbers of nodes (states) and edges (observations). However, this approach will destroy the original sparse structure of graph optimization. To solve this problem, we propose a paralleled online sparsification method in the fixed-lag smoothing VIO by minimizing Kullback-Leibler divergence (KLD) to recover nonlinear and sparse factors that optimally approximate the original dense prior induced by marginalization. In addition, we propose a new graph formulation capable of simplifying partial VIO into visual odometry (VO) with a gravity-aligned pose prior. In addition, a novel method is presented in the loop-closure phase and mapping, in which the recovered factors and the observation of landmarks can be reused for more consistent back-end optimization. The proposed method is validated based on real datasets and compared with other state-of-the-art methods to verify its efficiency and accuracy. The experimental results demonstrate that the proposed sparse method effectively reduces computational complexity when compared to the traditional tightly coupled VINS system. Furthermore, the proposed method offers a novel perspective for achieving global consistent mapping, making it an innovative addition to existing advanced systems employing sparse steps.
Keyword:
Optimization
Cameras
Odometry
Visualization
Smoothing methods
Markov processes
Gravity
Factor graph sparsification
kullback-leibler divergence (KLD)
marginalization
visual-inertial odometry (VIO)
期刊
IF:
5.9
论文数:
2.0W
被引数:
5.8W
机构
引用论文
分享收藏
分享收藏Risk of Type 2 Diabetes in Patients With Nonapnea Sleep Disorders in Using Different Types of Hypnotics.png)
Medicine
OAAI
MedicineIF0
OAAI分享收藏分享收藏
查看更多内容