ORB |
您所在的位置：网站首页 › 高速路限速不能超过多少码 › ORB |
ORB
|
前言
学习ORB_SLAM2，从编译源码开始 ORB_SLAM2的github地址: https://github.com/raulmur/ORB_SLAM2 一、准备工作: 1.安装依赖库: sudo apt install cmake sudo apt install libgl1-mesa-dev sudo apt install libeigen3-dev sudo apt install libglew-dev freeglut3-dev 2.安装Pangolin: git clone https://github.com/stevenlovegrove/Pangolin.git cd Pangolin/ mkdir build cmake .. make -j4 sudo make install # 默认安装在/usr/local/bin/Plotter 3.编译ORB_SLAM2: git clone https://github.com/raulmur/ORB_SLAM2.git cd ORB_SLAM2 chmod +x build.sh ./build.sh # 如果编译过程中死机，将build.sh中的make -j改为make -j4如果编译的过程中, 发现有usleep()函数的报错, 可以把报错的文件中添加头文件: #include # 一个小技巧, 搜索所有包含"usleep"字符串的文件 grep -r -e "usleep" ./Examples/ grep -r -e "usleep" ./src/ # 然后手动为这些文件添加: #include我编译过程中遇到的其他问题： error: static assertion failed: std::map must have the same value_type as its allocator 解决方法：https://blog.csdn.net/lixujie666/article/details/90023059 打开LoopClosing.h，将 typedef map KeyFrameAndPose; 改为 typedef map KeyFrameAndPose; 二、运行例程:下载测试数据: https://vision.in.tum.de/rgbd/dataset/freiburg1/rgbd_dataset_freiburg1_desk.tgz 然后执行: cd ORB_SLAM2/ mkdir sequence # 然后把文件解压到sequence文件夹下 # 运行例程 ./Examples/Monocular/mono_tum Vocabulary/ORBvoc.txt Examples/Monocular/TUM1.yaml sequence/rgbd_dataset_freiburg1_desk可以看到演示:
如果报错： [100%] Linking CXX executable ../MonoAR /usr/bin/ld: warning: libopencv_imgproc.so.4.2, needed by /opt/ros/noetic/lib/libcv_bridge.so, may conflict with libopencv_imgproc.so.3.4 /usr/bin/ld: CMakeFiles/MonoAR.dir/src/AR/ViewerAR.cc.o: undefined reference to symbol '_ZN2cv7putTextERKNS_17_InputOutputArrayERKNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEENS_6Point_IiEEidNS_7Scalar_IdEEiib' /usr/bin/ld: /usr/lib/x86_64-linux-gnu/libopencv_imgproc.so.4.2.0: error adding symbols: DSO missing from command line collect2: error: ld returned 1 exit status make[2]: *** [CMakeFiles/MonoAR.dir/build.make:248：../MonoAR] 错误 1 make[1]: *** [CMakeFiles/Makefile2:487：CMakeFiles/MonoAR.dir/all] 错误 2 make: *** [Makefile:130：all] 错误 2 需要安装opencv4.2，之后再重新运行./build.sh 下载解压opencv4.2：https://github.com/opencv/opencv/archive/4.2.0.zip cd opencv-4.2.0 mkdir build cd build cmake .. make -j8 sudo make install 3.编译调用笔记本自带摄像头的代码：参考：https://www.cnblogs.com/feifanrensheng/p/8995836.html mkdir -p ~/catkin_ws/src cd ~/catkin_ws/src catkin_init_workspace cd ~/catkin_ws/ catkin_make source devel/setup.bash cd ~/catkin_ws/src git clone https://github.com/bosch-ros-pkg/usb_cam.git cd .. catkin_make source ~/catkin_ws/devel/setup.bash roscd usb_cam # 没报错算成功 4.ros调用AR：用笔记本自带的摄像头，需要把ros_mono_ar.cc中的：ros::Subscriber sub = nodeHandler.subscribe("/camera/image_raw", 1, &ImageGrabber::GrabImage,&igb); 改为：ros::Subscriber sub = nodeHandler.subscribe("/usb_cam/image_raw", 1, &ImageGrabber::GrabImage,&igb);，再重新编译。 开启一个终端，运行： roscore再开启一个终端，运行： source ~/catkin_ws/devel/setup.bash cd ~/catkin_ws/src/usb_cam/launch/ roslaunch usb_cam usb_cam-test.launch # 可以看到笔记本摄像头的画面在ORB_SLAM2目录下开启第三个终端，运行： rosrun ORB_SLAM2 Mono Vocabulary/ORBvoc.txt Examples/Monocular/TUM1.yaml
|
【本文地址】