Ct-LVI: A Framework Towards Continuous-time Laser-Visual-Inertial Odometry and Mapping

Zhong Wang1, Lin Zhang1, Shengjie Zhao1, and Yicong Zhou2

1School of Software Engineering, Tongji University, Shanghai, China

2Department of Computer and Information Science, University of Macau, China

Introduction

This is the website for our paper "Ct-LVI: A Framework Towards Continuous-time Laser-Visual-Inertial Odometry and Mapping".

Framework

Figure 1. (a) Self-developed handheld device. (b) The framework of Ct-LVI: “Preprocessing” produces synchronized and de-skewed point clouds, roughly fitted trajectory, and tracked visual features; “Front-end” conducts continuous-time laser-visual-inertial odometry; and “Backend” eliminates drifts via laser-visual fused loop detection and constraint construction, as well as global pose graph adjustment.

Source Codes

Ct-LVI Codes

Demo Video

The following demo video shows the functionality and demonstrates the performance of our Ct-LVI.