ROS与VSLAM入门教程-LSD-SLAM安装

ROS与VSLAM入门教程-LSD-SLAM安装

说明：

• 介绍如何安装LSD-SLAM

环境：

• ubuntu14.04 + indigo

步骤：

• 需使用rosbuild构建

sudo apt-get install python-rosinstall  
mkdir ~/rosbuild_ws  
cd ~/rosbuild_ws  
rosws init . /opt/ros/indigo  
mkdir package_dir  
rosws set ~/rosbuild_ws/package_dir -t .  
echo "source ~/rosbuild_ws/setup.bash" >> ~/.bashrc  
bash  
cd package_dir  

• 安装系统依赖：

sudo apt-get install ros-indigo-libg2o ros-indigo-cv-bridge liblapack-dev libblas-dev freeglut3-dev libqglviewer-dev libsuitesparse-dev libx11-dev

• 克隆代码库

cd ~/rosbuild_ws
git clone https://github.com/tum-vision/lsd_slam.git lsd_slam

• 安装openFabMap（可选）
• 修改lsd_slam_core/CMakeLists.txt

#add_subdirectory(${PROJECT_SOURCE_DIR}/thirdparty/openFabMap)
#include_directories(${PROJECT_SOURCE_DIR}/thirdparty/openFabMap/include)
#add_definitions("-DHAVE_FABMAP")
#set(FABMAP_LIB openFABMAP )

• 去掉注释
• 注意openFabMap需要OpenCv nonfree模块支持，OpenCV3.0以上已经不包含，作者推荐2.4.8版本
• nonfree模块安装

$ sudo add-apt-repository --yes ppa:xqms/opencv-nonfree  
$ sudo apt-get update  
$ sudo apt-get install libopencv-nonfree-dev

• 编译

rosmake lsd_slam

测试：

• 运行roscore

$ roscore  

• 启动摄像头

$ rosrun uvc_camera uvc_camera_node device:=/dev/video0  

• 启动LSD-viewer查看点云

$ rosrun lsd_slam_viewer viewer 

• 启动LSD-core

$ rosrun lsd_slam_core live_slam /image:=image_raw _calib:=<your path>/LSD_room/cameraCalibration.cfg  

• 或

$ rosrun lsd_slam_core dataset_slam _files:=<your path>/LSD_room/images _hz:=0 _calib:=<your path>/LSD_room/cameraCalibration.cfg  

• _calib校准文件，/image选择视频流

参考：

• https://github.com/tum-vision/lsd_slam
• https://blog.csdn.net/xueyinhualuo/article/details/48490939
• http://vision.in.tum.de/research/vslam/lsdslam?redirect=1
• https://blog.csdn.net/gobitan/article/details/51541977