VINS-Mono

Introduction

VINS-MONO is a robust and versatile monocular visual-inertial state estimator. It begins with a sturdy initialization process for the estimates and employs a tightly-coupled, nonlinear optimization approach that integrates pre-integrated IMU measurements with feature observations to achieve high-precision visual-inertial odometry. The loop closure detection module, combined with the tightly-coupled formulation, enables efficient relocalization with minimal computation and implements 4DOF pose graph optimization to ensure global consistency. Moreover, the system is capable of reusing maps by effectively saving and loading them. The current map can be merged with previous ones through global pose graph optimization. Furthermore, this algorithm has been deployed in an airborne closed-loop autonomous flight on a micro-aerial vehicle platform, as well as in an iOS-based demonstration. This work presents a reliable, comprehensive, and multifunctional system suitable for various applications requiring high-precision localization.
Here are some reference links: code link. paper link. vedio link.

Image description — Fig. 1. Workflow diagram of VINS-MONO

2 Compilation Process

2.1 Requirement

This package requires ubuntu20.04 、ros-noetic、cmake、gcc、g++、 Pangolin_v0.5、opencv-3.3.1、cv-bridge、eigen-3.3.3、ceres-solver-1.14.0、vins-mono code、bag
During the installation of third-party libraries, there may be many version mismatch issues.
Below are just examples of installation.
Please make sure to match the versions, otherwise compilation will have significant problems.
If there are any issues during the appeal process, please search online to resolve them.

install dependence


            sudo apt-get update 

            sudo apt-get install git gcc g++ vim make cmake

install Pangolin


            sudo apt-get install libglew-dev libboost-dev libboost-thread-dev libboost-filesystem-dev 

            sudo apt-get install ffmpeg libavcodec-dev libavutil-dev libavformat-dev libswscale-dev libpng-dev 

            download Pangolin 

            cd Pangolin 

            mkdir build && cd build

            cmake -DCPP11_NO_BOOST=1 .. 

            make 

            sudo make install

install OpenCV


            sudo apt-get install build-essential libgtk2.0-dev libavcodec-dev  

            sudo apt-get install libavformat-dev libjpeg.dev libtiff5.dev  

            sudo apt-get install libswscale-dev libjasper-dev  

            sudo apt-get install libcanberra-gtk-module libcanberra-gtk3-module  

            download opencv 

            cd opencv 

            mkdir build && cd build 

            cmake -D CMAKE_BUILD_TYPE=Release -D CMAKE_INSTALL_PREFIX=/usr/local ..

            make 

            sudo make install

install Eigen3


            download Eigen3 

            cd eigen3

            mkdir build && cd build

            cmake ..

            make

            sudo make install

install Ceres


            sudo apt-get install libgoogle-glog-dev libgflags-dev

            sudo apt-get install libatlas-base-dev

            download Ceres 

            mkdir ceres-bin 

            cd ceres-bin 

            cmake ../ceres-solver-1.14.0 

            make  

            sudo make install

2.2 Build VINS-MONO

Clone the repository and catkin_make:


            cd ~/catkin_ws/src

            git clone https://github.com/HKUST-Aerial-Robotics/VINS-Mono.git  

            cd ../

            catkin_make

            source ~/catkin_ws/devel/setup.bash

2.3 Run VINS-MONO


            roslaunch vins_estimator xxxxx.launch #修改配置文件，包括里面的yaml文件。

            roslaunch vins_estimator vins_rviz.launch  #启动rviz可视化  

            rosbag play xxx.bag  #播放你的bag，修改目录即可 

            ./run.sh   //也可以运行sh文件来一键启动，不过需要自己写

Evaluation

Platforms	Sequences	Length(m)	ATE
A Handheld Device	Escalator	77.460	0.858
	MCR normal dark	76.499	0.390
	MCR aggressive 6dof light	100.871	X
	Parkway loop night	461.049	22.851
	Forest	130.937	0.587
A UGV	Elevator	39.336	X
	Indoor loop	270.674	0.704
	MCR hdr	193.918	4.551
	Street day	2064.475	16.690
	Parkway loop night	461.051	25.503
A QR	Underground	98.312	0.858
	MCR hdr	85.08	0.527
	Forest	108.037	0.176
A UAV	MCR loop light	104.989	0.231
A Car	Urban night loop	1807.884	30.828