Ubuntu18.04运行Vins-Fusion

目录

一. 安装ros

1. Installation

2. Environment setup

3. Dependencies for building packages

4. 安装ros与opencv的桥接工具包

5.验证ros是否安装成功

二.  安装eigen

三. 安装opencv

1. 进入下载opencv的根目录

四. 安装ceres

1. 安装ceres依赖项

2. 进入Ceres的主目录，编译Ceres

五. 编译Vins-Fusion

1. 创建ros工作空间

2. 编译VINS-Fusion

3. 至此VINS-Fusion编译完成，后面需要打开四个shell窗口分别运行ros命令，为了避免每次打开新的shell都需要source，我们将其添加到bash配置文件中

4. 下载EuRoc数据集

5. 运行VINS-Fusion

Monocualr camera + IMU

Stereo cameras + IMU

Stereo cameras

六. 运行效果

---

---

一. 安装ros

不同的ubuntu版本对应不同版本的ros，具体可查询ros官网

http://wiki.ros.org/ROS/Installation

ubuntu16.04以及更老的版本对应ROS Kinetic Kame

ubuntu18.04对应ROS Melodic Morenia

ubuntu20.04对应ROS Noetic Ninjemys

下面开始安装ROS Melodic，详细安装教程可以参考下面的官网连接：

http://wiki.ros.org/melodic/Installation/Ubuntu

1. Installation

sudo sh -c 'echo "deb http://packages.ros.org/ros/ubuntu $(lsb_release -sc) main" > /etc/apt/sources.list.d/ros-latest.list' 
sudo apt-key adv --keyserver 'hkp://keyserver.ubuntu.com:80' --recv-key C1CF6E31E6BADE8868B172B4F42ED6FBAB17C654 
sudo apt update 
sudo apt install ros-melodic-desktop-full 

 

2. Environment setup

  If you have more than one ROS distribution installed, ~/.bashrc must only source the setup.bash for the version you are currently using.

echo "source /opt/ros/melodic/setup.bash" >> ~/.bashrc 
source ~/.bashrc

3. Dependencies for building packages

sudo apt install python-rosdep python-rosinstall python-rosinstall-generator python-wstool build-essential
sudo apt install python-rosdep
sudo rosdep init
rosdep update

4. 安装ros与opencv的桥接工具包

sudo apt-get install ros-melodic-cv-bridge ros-melodic-tf ros-melodic-message-filters ros-melodic-image-transport

5.验证ros是否安装成功

roscore

二.  安装eigen

sudo apt-get install libeigen3-dev

三. 安装opencv

下载opencv源码：

https://github.com/opencv/opencv

如果没有安装cmake，需要先安装cmake

sudo apt-get install cmake
sudo apt-get install build-essential libgtk2.0-dev libavcodec-dev libavformat-dev libjpeg.dev libtiff4.dev libswscale-dev libjasper-dev

1. 进入下载opencv的根目录

mkdir build 
cd build
cmake -D CMAKE_BUILD_TYPE=Release -D CMAKE_INSTALL_PREFIX=/usr/local ..
sudo make install

四. 安装ceres

下载ceres源码：

https://github.com/ceres-solver/ceres-solver

1. 安装ceres依赖项

sudo apt-get install liblapack-dev 
sudo apt-get install libsuitesparse-dev 
sudo apt-get install libcxsparse3.1.2 
sudo apt-get install libgflags-dev 
sudo apt-get install libgoogle-glog-dev libgtest-dev

安装libcxsparse3.1.2有可能找不到安装源，可参考如下解决：

sudo vi /etc/apt/sources.list
文件最后一行添加镜像源：deb http://archive.ubuntu.com/ubuntu/ trusty main universe restricted multiverse
sudo apt-get update

2. 进入Ceres的主目录，编译Ceres

mkdir build
cd build
cmake ..
sudo make install

五. 编译Vins-Fusion

1. 创建ros工作空间

mkdir -p ~/catkin_ws/src              
cd ~/catkin_ws/src
catkin_init_workspace

2. 编译VINS-Fusion

cd ~/catkin_ws/src
git clone https://github.com/HKUST-Aerial-Robotics/VINS-Fusion.git
cd ../
catkin_make
source ~/catkin_ws/devel/setup.bash

3. 至此VINS-Fusion编译完成，后面需要打开四个shell窗口分别运行ros命令，为了避免每次打开新的shell都需要source，我们将其添加到bash配置文件中

sudo  vi ~/.bashrc
最后一行添加：source ~/catkin_ws/devel/setup.bash
保存，退出

4. 下载EuRoc数据集

https://projects.asl.ethz.ch/datasets/doku.php?id=kmavvisualinertialdatasets#the_euroc_mav_dataset

我们以MH_04_difficult.bag为例，将其下载并保存在目录~/SLAM/test_data/

5. 运行VINS-Fusion

以单相机+IMU为例，分别打开四个shell窗口，运行命令

   窗口1：

roslaunch vins vins_rviz.launch

   窗口2：

rosrun vins vins_node ~/catkin_ws/src/VINS-Fusion/config/euroc/euroc_mono_imu_config.yaml

   窗口3(可选择运行，执行回环检测)：

(optional) rosrun loop_fusion loop_fusion_node ~/catkin_ws/src/VINS-Fusion/config/euroc/euroc_mono_imu_config.yaml 

   窗口4：

rosbag play ~/SLAM/test_data/MH_04_difficult.bag

Monocualr camera + IMU

roslaunch vins vins_rviz.launch
rosrun vins vins_node ~/catkin_ws/src/VINS-Fusion/config/euroc/euroc_mono_imu_config.yaml 
(optional) rosrun loop_fusion loop_fusion_node ~/catkin_ws/src/VINS-Fusion/config/euroc/euroc_mono_imu_config.yaml 
rosbag play ~/SLAM/test_data/MH_04_difficult.bag

Stereo cameras + IMU

roslaunch vins vins_rviz.launch
rosrun vins vins_node ~/catkin_ws/src/VINS-Fusion/config/euroc/euroc_stereo_imu_config.yaml 
(optional) rosrun loop_fusion loop_fusion_node ~/catkin_ws/src/VINS-Fusion/config/euroc/euroc_stereo_imu_config.yaml 
rosbag play ~/SLAM/test_data/MH_04_difficult.bag

Stereo cameras

roslaunch vins vins_rviz.launch
rosrun vins vins_node ~/catkin_ws/src/VINS-Fusion/config/euroc/euroc_stereo_config.yaml 
(optional) rosrun loop_fusion loop_fusion_node ~/catkin_ws/src/VINS-Fusion/config/euroc/euroc_stereo_config.yaml 
rosbag play ~/SLAM/test_data/MH_04_difficult.bag

六. 运行效果