CVIDS: A Collaborative Localization and Dense Mapping Framework for Multi-agent Based Visual-inertial SLAM

Tianjun Zhang1, Lin Zhang1, Yang Chen1, Yicong Zhou2

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

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

Introduction

This is the website for our paper "CVIDS: A Collaborative Localization and Dense Mapping Framework for Multi-agent Based Visual-inertial SLAM. "

 

Source Codes

Get the code

Use git to clone the repository:

    git clone git@github.com:z619850002/CVIDS.git

Tested data Extraction Code: ear2

Dependencies

Note: all these codes are implemented in C++ 11. We have tested the library in Ubuntu 16, but it should be feasible to compile in other platforms.

1. ROS-Kinetic

CVIDS is implemented based on ROS-Kinetic.

 

2. OpenCV

We use OpenCV to manipulate images and features. Dowload and install instructions can be found at: http://opencv.org. We use 3.4.1, but it should also work for other version at least 3.0.

 

3. Eigen3

Download and install instructions can be found at: http://eigen.tuxfamily.org.

 

4. ceres

This is an optimziation library. We use ceres library to perform non-linear optimizations. More details can be found in http://www.ceres-solver.org/.

 

5. Sophus

Sophus is a Lie algebra library. More details can be found in https://github.com/strasdat/Sophus.

Demo Videos

The following is the demo video demonstrating the performance of our CVIDS framework for collaborative localization.

The following is the demo video demonstrating the performance of our CVIDS framework for collaborative dense mapping.

Last update: Mar. 8, 2022