ORB-SLAM2 安装

参考

• 修改源文件即可避免兼容问题
• 实验环境
  Ubuntu 20.04
  ROS noetic

• https://zhuanlan.zhihu.com/p/640795165
• https://blog.csdn.net/qq_46107892/article/details/128922813
• https://blog.csdn.net/MRZHUGH/article/details/131658528

安装相关依赖

• 通用依赖

  sudo apt install -y libboost-all-dev libglew-dev libgtk2.0-dev \
  libavcodec-dev libavformat-dev libswscale-dev libjpeg-dev libpng-dev \
  libtiff-dev libopenexr-dev libxi-dev libxrandr-dev libx11-dev \
  libglu1-mesa-dev libgl1-mesa-dev libusb-1.0-0-dev libudev-dev doxygen \
  doxygen-doc libxkbcommon-dev wayland-protocols
  

• 安装 eigen3, Ubuntu 一般默认已经安装

  sudo apt install libeigen3-dev
  

• 安装 Pangolin,源码编译

  • 需要先安装 libxkbcommon-dev, wayland-protocols, libglew-dev
  • 选择版本 0.6

  # 安装依赖库, 前面装了就不用再重复了
  sudo apt-get update
  sudo apt-get install libxkbcommon-dev
  sudo apt-get install wayland-protocols
  sudo apt install libglew-dev
  # 进入到Pangolin下载文件夹目录，新开终端，这里以0.6版本为例
  unzip Pangolin-0.6.zip
  cd Pangolin-0.6/
  mkdir build
  cd build
  # cmake
  cmake ..
  # make
  make -j4
  # install
  sudo make install
  

• 安装 opencv

  • 源码编译时间较长, 且麻烦. 使用apt进行安装
  • 安装时默认 4.x

  sudo apt install libopencv-dev libopencv-highgui-dev libopencv-contrib-dev	
  

• 安装 ORB_SLAM2
  1. 下载 git clone https://github.com/raulmur/ORB_SLAM2.git
  2. 修改源文件, 很重要, 适配 opencv4.X

  a、ORB_SLAM2/CmakeLists.txt 和 ORB_SLAM2/Thirdparty/DBoW2/CmakeLists.txt 2处
  # 修改opencv版本
  -find_package(OpenCV 3.0 QUIET)
  +find_package(OpenCV 4.2 QUIET)
  b、include/LoopClosing.h
  // 解决类别定义问题
  -Eigen::aligned_allocator<std::pair<const KeyFrame*, g2o::Sim3> > > KeyFrameAndPose; 
  +Eigen::aligned_allocator<std::pair<KeyFrame* const, g2o::Sim3> > > KeyFrameAndPose; 
  c、include/ORBextractor.h
  // 解决opencv头文件引用问题
  -#include <opencv/cv.h>
  +#include <opencv2/imgproc/imgproc_c.h>
  +#include <opencv2/highgui/highgui_c.h>
  d、include/System.h
  +#include<opencv2/imgcodecs/legacy/constants_c.h> // 解决找不到CV_LOAD_IMAGE_UNCHANGED问题
  +#include<unistd.h> // 解决usleep函数不存在问题
  

  3. 编译

   cd ORB_SLAM2
  ./build.sh
  

测试数据集

https://cvg.cit.tum.de/data/datasets/rgbd-dataset/download
Tips:下载的数据需要解压成文件夹,作为参数.