視覺SLAM筆記--第2篇: ORB_SLAM2編譯運行

1. ORB-SLAM2編譯運行

1.1 安裝依賴庫

編譯ORBSLAM2需要的第三方依賴庫包括:

• OpenCV ( 版本 >2.4.3)
• Eigen3 (版本 > 3.1.0)
• Pangolin
• DBoW2和g2o(包含在工程中,不需要單獨安裝)
• ROS
  前三個依賴庫安裝教程:安裝教程;
  ROS安裝教程:ROS-Kinetic安裝;

1.2 編譯

根據官方說明,可按照以下步驟進行, 編譯過程會出現兩個問題,具體解決方案請看第2節:

# 將ORB_SLAM2克隆到本地文件目錄下
git clone https://github.com/raulmur/ORB_SLAM2.git ORB_SLAM2
# 打開.bashrc文件
gedit ~/.bashrc
# 將下面一行添加到.bashrc文件的最後一行,其中PATH需要改爲ORB_SLAM2所在的目錄路徑
export ROS_PACKAGE_PATH=${ROS_PACKAGE_PATH}:PATH/ORB_SLAM2/Examples/ROS
# source確保生效
source ~/.bashrc

# 1.編譯非ROS版本
cd ORB_SLAM2
sudo chmod +x build.sh
./build.sh

# 2.編譯ROS版本
cd ORB_SLAM2
sudo chmod +x build_ros.sh
./build_ros.sh

1.3 運行測試

數據集: EuRoC(筆者測試), KITTI, TUM.

1. 非ROS版運行測試
#  EuRoC單目, 按要求需要修改數據集路徑, 相機內參
./Examples/Monocular/mono_euroc Vocabulary/ORBvoc.txt Examples/Monocular/EuRoC.yaml /home/guofeng/桌面/Database/Euroc/mav0/cam0/data Examples/Monocular/EuRoC_TimeStamps/MH03.txt
# Euroc數據集雙目--MH03序列參數
./Examples/Stereo/stereo_euroc Vocabulary/ORBvoc.txt Examples/Stereo/EuRoC.yaml /home/guofeng/桌面/Database/Euroc/mav0/cam0/data /home/guofeng/桌面/Database/Euroc/mav0/cam1/data Examples/Stereo/EuRoC_TimeStamps/MH03.txt

#TUM數據集單目--TUM1相機參數
./Examples/Monocular/mono_tum Vocabulary/ORBvoc.txt Examples/Monocular/TUM1.yaml /home/guofeng/桌面/Database/TUM/data
#TUM數據集RGB-D深度相機--TUM1相機參數  
#注意要先使用下面命令轉換
python associate.py PATH_TO_SEQUENCE/rgb.txt PATH_TO_SEQUENCE/depth.txt > associations.txt
./Examples/RGB-D/rgbd_tum Vocabulary/ORBvoc.txt Examples/RGB-D/TUM1.yaml /home/guofeng/桌面/Database/TUM/data /home/guofeng/桌面/Database/TUM/associations.txt

#Kitti數據集單目--KITTI00-02相機內參，02序列圖像
./Examples/Monocular/mono_kitti Vocabulary/ORBvoc.txt Examples/Monocular/KITTI00-02.yaml /home/guofeng/桌面/Database/KITTI/dataset/sequences/02
#Kitti數據集雙目--KITTI00-02相機內參，02序列圖像
./Examples/Stereo/stereo_kitti Vocabulary/ORBvoc.txt Examples/Stereo/KITTIX.yaml /home/guofeng/桌面/Database/KITTI/dataset/sequences/02

2. ROS版本運行測試
roscore
#  EuRoC單目, 運行EuRoc單目目ROS數據包,發送圖像信息
rosbag play --pause V1_01_easy.bag /cam0/image_raw:=/camera/image_raw
rosrun ORB_SLAM2 Mono Vocabulary/ORBvoc.txt Examples/Monocular/EuRoC.yaml
#  EuRoC雙目, 運行EuRoc雙目ROS數據包,發送圖像信息
rosbag play --pause V1_01_easy.bag /cam0/image_raw:=/camera/left/image_raw /cam1/image_raw:=/camera/right/image_raw
rosrun ORB_SLAM2 Stereo Vocabulary/ORBvoc.txt Examples/Stereo/EuRoC.yaml true

1.4 測試結果

• 單目EuRoc (非ROS版本)
  
• 單目EuRoc (ROS版本)
  

2. 出現的問題及解決方案

2.1 cv_bridge問題

• 問題描述

[rospack] Error: package 'ORB_SLAM2' depends on non-existent package 'cv_bridge' and rosdep claims that it is not a system dependency. Check the ROS_PACKAGE_PATH or try calling 'rosdep update'

• 解決方案

# ROS缺少依賴包cv_bridge,作用是ROS發佈的圖像消息和opencv的圖像Mat矩陣形式的轉換橋樑;
$sudo apt-get install ros-kinetic-cv-bridge

2.2 鏈接庫問題

• 問題描述

/usr/bin/ld: CMakeFiles/RGBD.dir/src/ros_rgbd.cc.o: undefined reference to symbol '_ZN5boost6system15system_categoryEv'
/usr/lib/x86_64-linux-gnu/libboost_system.so: error adding symbols: DSO missing from command line
collect2: error: ld returned 1 exit status
CMakeFiles/RGBD.dir/build.make:217: recipe for target '../RGBD' failed
make[2]: *** [../RGBD] Error 1
CMakeFiles/Makefile2:67: recipe for target 'CMakeFiles/RGBD.dir/all' failed
make[1]: *** [CMakeFiles/RGBD.dir/all] Error 2
make[1]: *** 正在等待未完成的任務....
/usr/bin/ld: CMakeFiles/Stereo.dir/src/ros_stereo.cc.o: undefined reference to symbol '_ZN5boost6system15system_categoryEv'
/usr/lib/x86_64-linux-gnu/libboost_system.so: error adding symbols: DSO missing from command line
collect2: error: ld returned 1 exit status
CMakeFiles/Stereo.dir/build.make:217: recipe for target '../Stereo' failed
make[2]: *** [../Stereo] Error 1
CMakeFiles/Makefile2:104: recipe for target 'CMakeFiles/Stereo.dir/all' failed
make[1]: *** [CMakeFiles/Stereo.dir/all] Error 2
Makefile:127: recipe for target 'all' failed
make: *** [all] Error 2

• 解決方案

# 打開ORB_SLAM2/Examples/ROS/ORB_SLAM2目錄下的CMakeLists.txt文件.在set中增加 -lboost_system, 具體修改如下:
set(LIBS
${OpenCV_LIBS}
${EIGEN3_LIBS}
${Pangolin_LIBRARIES}
${PROJECT_SOURCE_DIR}/../../../Thirdparty/DBoW2/lib/libDBoW2.so
${PROJECT_SOURCE_DIR}/../../../Thirdparty/g2o/lib/libg2o.so
${PROJECT_SOURCE_DIR}/../../../lib/libORB_SLAM2.so
-lboost_system
)

3. 後續計劃

後續將開始閱讀視覺位置識別方向的文獻,主要是從圖像和點雲兩方面進行拓展研究,包括但不限於圖像檢索,點雲檢索,閉環檢測驗證,關鍵點匹配等.