ROS与VSLAM入门教程-ORB-SLAM2安装

ROS与VSLAM入门教程-ORB-SLAM2安装

说明：

• 介绍如何安装ORB-SLAM2

环境：

• Ubuntu14.04 + ROS indigo
• Kinect V1.

准备：

• 安装ROS版本indigo，参考文章
• 安装Boost

sudo apt-get install libboost-all-dev

• 安装Pangolin：

git clone https://github.com/stevenlovegrove/Pangolin.git 
cd Pangolin 
mkdir build 
cd build 
cmake .. 
make -j 

• 安装OpenCV，版本为OpenCV2.4.11，参考文章
• 安装Eigen3

sudo apt-get install libeigen3-dev
#ls查看，含有3个文件： Eigen  signature_of_eigen3_matrix_library  unsupported
cd /usr/include/eigen3     
#将Eigen文件夹放在 /usr/include 下面  
sudo cp Eigen/ .. -R               

• DBoW2和g2o (included in Thirdparty) 在ORB-SLAM2的Thirdparty文件夹里面，无需安装。

安装ORB-SLAM2：

• 下载编译ORB-SLAM2：

cd ~
git clone https://github.com/raulmur/ORB_SLAM2.git ORB_SLAM2
cd ORB_SLAM2
chmod +x build.sh
./build.sh

单目测试：

1. TUM Dataset：

• 下载数据集http://vision.in.tum.de/data/datasets/rgbd-dataset/download
• 执行命令：

./Examples/Monocular/mono_tum Vocabulary/ORBvoc.txt Examples/Monocular/TUMX.yaml PATH_TO_SEQUENCE_FOLDER

• 可以改变TUMX.yaml为 TUM1.yaml,TUM2.yaml or TUM3.yaml 针对 freiburg1, freiburg2 和freiburg3
• 改变PATH_TO_SEQUENCE_FOLDER为对应解压后的目录

2. KITTI Dataset：

• 下载数据集http://www.cvlibs.net/datasets/kitti/eval_odometry.php
• 执行命令：

./Examples/Monocular/mono_kitti Vocabulary/ORBvoc.txt Examples/Monocular/KITTIX.yaml PATH_TO_DATASET_FOLDER/dataset/sequences/SEQUENCE_NUMBER

• 改变KITTIX.yaml为 KITTI00-02.yaml, KITTI03.yaml or KITTI04-12.yaml
• 针对0 to 2, 3, and 4 to 12
• 改变PATH_TO_DATASET_FOLDER为解压的目录
• 改变SEQUENCE_NUMBER 为00, 01, 02,.., 11.

3. EuRoC Dataset：

• 下载数据集 http://projects.asl.ethz.ch/datasets/doku.php?id=kmavvisualinertialdatasets
• 执行命令，针对V1和V2 sequences.：

./Examples/Monocular/mono_euroc Vocabulary/ORBvoc.txt Examples/Monocular/EuRoC.yaml PATH_TO_SEQUENCE_FOLDER/mav0/cam0/data Examples/Monocular/EuRoC_TimeStamps/SEQUENCE.txt 

• 执行命令，针对MH sequences.

./Examples/Monocular/mono_euroc Vocabulary/ORBvoc.txt Examples/Monocular/EuRoC.yaml PATH_TO_SEQUENCE/cam0/data Examples/Monocular/EuRoC_TimeStamps/SEQUENCE.txt

• 改变PATH_TO_SEQUENCE_FOLDER和SEQUENCE为你想要执行的数据

双目测试：

1. KITTI Dataset

• 下载数据集http://www.cvlibs.net/datasets/kitti/eval_odometry.php
• 执行命令：

./Examples/Stereo/stereo_kitti Vocabulary/ORBvoc.txt Examples/Stereo/KITTIX.yaml PATH_TO_DATASET_FOLDER/dataset/sequences/SEQUENCE_NUMBER

• 改变KITTIX.yaml为KITTI00-02.yaml, KITTI03.yaml or KITTI04-12.yaml
• 针对序列0 to 2, 3, and 4 to 12
• 改变PATH_TO_DATASET_FOLDER为下载的数据集
• 改变SEQUENCE_NUMBER为00, 01, 02,.., 11.

2. EuRoC Dataset

• 下载数据集 http://projects.asl.ethz.ch/datasets/doku.php?id=kmavvisualinertialdatasets
• 执行命令， 针对 V1 and V2 序列：

./Examples/Stereo/stereo_euroc Vocabulary/ORBvoc.txt Examples/Stereo/EuRoC.yaml PATH_TO_SEQUENCE/mav0/cam0/data PATH_TO_SEQUENCE/mav0/cam1/data Examples/Stereo/EuRoC_TimeStamps/SEQUENCE.txt

• 执行命令，针对MH sequences

./Examples/Stereo/stereo_euroc Vocabulary/ORBvoc.txt Examples/Stereo/EuRoC.yaml PATH_TO_SEQUENCE/cam0/data PATH_TO_SEQUENCE/cam1/data Examples/Stereo/EuRoC_TimeStamps/SEQUENCE.txt

• PATH_TO_SEQUENCE_FOLDER and SEQUENCE 更改你想执行的数据集

RGB-D 例子测试：

1. TUM Dataset

• 下载数据库http://vision.in.tum.de/data/datasets/rgbd-dataset/download
• 关联RGB图和深度图，可以使用associate.py脚本
• 在Examples/RGB-D/associations/.有一些现成的associations文件
• 或者生产自己的associations文件

python associate.py PATH_TO_SEQUENCE/rgb.txt PATH_TO_SEQUENCE/depth.txt > associations.txt

• 执行命令：

./Examples/RGB-D/rgbd_tum Vocabulary/ORBvoc.txt Examples/RGB-D/TUMX.yaml PATH_TO_SEQUENCE_FOLDER ASSOCIATIONS_FILE

• 改变TUMX.yaml为TUM1.yaml,TUM2.yaml or TUM3.yaml ，针对 freiburg1, freiburg2 and freiburg3 sequences
• PATH_TO_SEQUENCE_FOLDER为解压的目录
• ASSOCIATIONS_FILE为对应的associations文件

ROS Examples

1. 针对 mono, monoAR, stereo and RGB-D

• 添加路径到 .bashrc

export ROS_PACKAGE_PATH=${ROS_PACKAGE_PATH}:PATH/ORB_SLAM2/Examples/ROS

• 执行编译

chmod +x build_ros.sh
./build_ros.sh

• 运行 Monocular Node

rosrun ORB_SLAM2 Mono PATH_TO_VOCABULARY PATH_TO_SETTINGS_FILE

• 输入图像话题是/camera/image_raw
• 运行 Monocular Augmented Reality Demo

rosrun ORB_SLAM2 MonoAR PATH_TO_VOCABULARY PATH_TO_SETTINGS_FILE

• 输入图像话题是/camera/image_raw
• 这是增强现实的演示，您可以使用界面在场景的平面区域中插入虚拟立方体
• 运行 Stereo Node

rosrun ORB_SLAM2 Stereo PATH_TO_VOCABULARY PATH_TO_SETTINGS_FILE ONLINE_RECTIFICATION

• 输入话题/camera/left/image_raw and /camera/right/image_raw
• 运行RGB_D Node

rosrun ORB_SLAM2 RGBD PATH_TO_VOCABULARY PATH_TO_SETTINGS_FILE

• 输入话题/camera/rgb/image_raw and /camera/depth_registered/image_raw

参考：

• https://github.com/raulmur/ORB_SLAM2.git
• http://www.cnblogs.com/zengcv/p/6021512.html