ORB_SLAM2学习记录1-ORB_SLAM2的安装与运行

(一)、环境的配置

1.ros环境的安装，可直接参开wiki.ros

2.building ORB_SLAM2

   git clone https://github.com/raulmur/ORB_SLAM2.git ORB_SLAM2

3.编译

cd ORB_SLAM2
chmod +x build.sh
. /build.sh

4.Monocular  Example

## TUM Dataset

1. Download a sequence from http://vision.in.tum.de/data/datasets/rgbd-dataset/download and uncompress it.

2. Execute the following command. Change `TUMX.yaml` to TUM1.yaml,TUM2.yaml or TUM3.yaml for freiburg1, freiburg2 and freiburg3 sequences respectively. Change `PATH_TO_SEQUENCE_FOLDER`to the uncompressed sequence folder.
```
./Examples/Monocular/mono_tum Vocabulary/ORBvoc.txt Examples/Monocular/TUMX.yaml PATH_TO_SEQUENCE_FOLDER  

5. ROS Example

a. 需要再.bashrc文件中将路径设置一下,eg: export ROS_PACKAGE_PATH=${ROS_PACKAGE_PATH}:PATH/ORB_SLAM2/Examples/ROS

        b. 执行build_ros.sh 脚本

  chmod +x build_ros.sh
   ./build_ros.sh

        c. 跑一个Monocular 的例子

1. rosrun ORB_SLAM2 Mono PATH_TO_VOCABULARY PATH_TO_SETTINGS_FILE

                2.  rosbag play --pause  Example.bag

              3.  注意下ros_mono.cc中处理相机的topic和Example.bag 中topic 要一致。

6. 建图

a. 需要安装usb_cam，再ros上下载这个包，然后编译一下。

b.启动相机节点，rosrun  usb_cam  usb_cam_node

        c. rosrun ORB_SLAM2 Mono PATH_TO_VOCABULARY PATH_TO_SETTINGS_FILE

       d. 注意usb_cam 中相机发出的topic与ORB_SLAM2 系统中接收的topic 一致。