Ubuntu16.04（ROS-kinetic）编译测试ORB-SLAM2

2022-02-24 15:13:24

Ubuntu16.04（ROS-kinetic）编译测试ORB-SLAM2

参考
安装依赖项
安装ROS kinetic
ORB-SLAM2测试自己的USB摄像头

参考

https://blog.csdn.net/learning_tortosie/article/details/79881165
https://blog.csdn.net/lixujie666/article/details/80475451

安装依赖项

具体的依赖项安装参考：
https://blog.csdn.net/learning_tortosie/article/details/79881165

安装ROS kinetic

为了能够在线实时地运行ORB-SLAM2，需要借助ROS。
ubuntu的版本要和ROS版本对应：

column1	column2
Ubuntu 14.04	ROS Indigo Igloo
Ubuntu 16.04	ROS Kinetic Kame
Ubuntu 18.04	ROS Melodic Morenia

我的是ubuntu16.04,对应安装 ROS Kinetic Kame，
官网安装教程http://wiki.ros.org/kinetic/Installation/Ubuntu
个人安装步骤记录如下：

设置ROS软件源
添加ROS官方软件源：

sudo sh -c 'echo "deb http://packages.ros.org/ros/ubuntu $(lsb_release -sc) main" > /etc/apt/sources.list.d/ros-latest.list'

一般地，ROS官方源速度很慢或者连接不上，推荐使用中科大的软件源.

sudo sh -c '. /etc/lsb-release && echo "deb http://mirrors.ustc.edu.cn/ros/ubuntu/ $DISTRIB_CODENAME main" > /etc/apt/sources.list.d/ros-latest.list'

题外话：
网上好多推荐使用清华大学的软件源，但后面安装时出现了如下问题

解决方法就是换成中科大的源。

设置公钥

sudo apt-key adv --keyserver 'hkp://keyserver.ubuntu.com:80' --recv-key C1CF6E31E6BADE8868B172B4F42ED6FBAB17C654

更新

sudo apt-get update

安装Desktop-Full Install（桌面完整版）

sudo apt-get install ros-kinetic-desktop-full

初始化rosdep

sudo rosdep init
rosdep update

环境设置

echo "source /opt/ros/kinetic/setup.bash" >> ~/.bashrc
source ~/.bashrc

安装相关依赖项

sudo apt install python-rosinstall python-rosinstall-generator python-wstool build-essential

刷新配置

source /opt/ros/kinetic/setup.bash

创建一个ROS工作空间并初始化

mkdir -p ~/catkin_ws/src
cd ~/catkin_ws/
catkin_make

刷新，将工作空间添加到ROS系统环境中

$ source ~/catkin_ws/devel/setup.bash

为了避免每打开一个终端都需要运行这句指令，可以如下操作，使其自动进行

 echo “source ~/catkin_ws/devel/setup.bash” >>~/.bashrc

ORB-SLAM2测试自己的USB摄像头

参考：https://blog.csdn.net/lixujie666/article/details/80475451
ORB-SLAM官方主页：http://webdiis.unizar.es/~raulmur/orbslam/
ORB-SLAM2源码地址：https://github.com/raulmur/ORB_SLAM2

安装依赖库
编译ORB-SLAM2之前需要安装一些必要的依赖库，按照源码中的README操作即可
将ORB_SLAM2源码整体下载，然后移到~/catkin_ws/src/目录下
将包含 Examples/ROS/ORB_SLAM2文件的路径添加到 ROS_PACKAGE_PATH 这个环境变量。具体操作如下

export ROS_PACKAGE_PATH=${ROS_PACKAGE_PATH}:~/catkin_ws/src/ORB_SLAM2/Examples/ROS

执行build_ros.sh脚本

chmod +x build_ros.sh
./build_ros.sh

我在这里遇到编译出错：
undefined reference to symbol '_ZN5boost6system15system_categoryEv'
解决：https://github.com/raulmur/ORB_SLAM2/issues/494
https://blog.csdn.net/sinat_38343378/article/details/78883919
具体操作就是改一下~/ORB_SLAM2/Examples/ROS/ORB_SLAM2/中的CMakeList.txt文件
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
)

利用ros提供的camera_calibration包进行相机标定
参考：
https://blog.csdn.net/heyijia0327/article/details/43538695
https://blog.csdn.net/qq_30460905/article/details/80390576

先下载读取usb摄像头的包usb_cam，下载地址：https://github.com/bosch-ros-pkg/usb_cam，下载完成后编译安装。或者直接运行指令sudo apt-get install ros-kinetic-usb-cam安装也行。

开启roscore，打开相机
//launch文件里面默认设备为/dev/video0,
roscore
roslaunch usb_cam usb_cam-test.launch
我这里出现错误：[ERROR] [1567914098.829566811]: select timeout
解决方法：
https://devtalk.nvidia.com/default/topic/1036105/logitech-brio-usb-cam-select-timeout-while-capturing/
大致就是让ubuntu切换到usb3.0模式，然后，将usb_cam的usb接口插到usb3.0的接口。

检查usb_cam package发布的消息：
rostopic list
看是否有如下消息，并记住名称
/usb_cam_node/camera_info
/usb_cam_node/image_raw

安装camera_calibration
rosdep install camera_calibration
#All required rosdeps installed successfully

启动标定程序：
rosrun camera_calibration cameracalibrator.py --size 7x5 --square 0.025 image:=/usb_cam/image_raw camera:=/usb_cam
其中参数size 7x5 注意是字母x，他是棋盘内部角点个数，如下图所示。square为棋盘正方形边长，注意刚刚开始标定的时候，CALIBRATE按钮是灰色的。
不断移动标定板,直到CALIBRATE按钮变亮，点击该按钮就会进行标定。耐心等待几分钟即可。
标定完成后点击COMMIT按钮将结果保存到默认文件夹，在usb_cam窗口中可以看到如下信息，说明标定结果已经保存在相应文件夹下下次启动usb_cam节点时，会自动调用。

图片来自https://blog.csdn.net/heyijia0327/article/details/43538695

标定完成后，将相应的相机参数保存到~/catkin_ws/src/ORB_SLAM2-master/Examples/ROS/ORB_SLAM2/default.yaml
default.yaml是相机的配置参数文件，我的default.yaml内容如下：

%YAML:1.0

#--------------------------------------------------------------------------------------------
# Camera Parameters. Adjust them!
#--------------------------------------------------------------------------------------------

# Camera calibration and distortion parameters (OpenCV) 
Camera.fx: 728.4
Camera.fy: 722.9
Camera.cx: 304.2
Camera.cy: 227.6

Camera.k1: -0.002
Camera.k2: -0.61
Camera.p1: 0.02
Camera.p2: -0.0005

Camera.width: 640
Camera.height: 480

# Camera frames per second 
Camera.fps: 30.0

# IR projector baseline times fx (aprox.)
Camera.bf: 40.0

# Color order of the images (0: BGR, 1: RGB. It is ignored if images are grayscale)
Camera.RGB: 1

# Close/Far threshold. Baseline times.
ThDepth: 40.0

# Deptmap values factor
DepthMapFactor: 1.0

#--------------------------------------------------------------------------------------------
# ORB Parameters
#--------------------------------------------------------------------------------------------

# ORB Extractor: Number of features per image
ORBextractor.nFeatures: 1000

# ORB Extractor: Scale factor between levels in the scale pyramid 	
ORBextractor.scaleFactor: 1.2

# ORB Extractor: Number of levels in the scale pyramid	
ORBextractor.nLevels: 8

# ORB Extractor: Fast threshold
# Image is divided in a grid. At each cell FAST are extracted imposing a minimum response.
# Firstly we impose iniThFAST. If no corners are detected we impose a lower value minThFAST
# You can lower these values if your images have low contrast			
ORBextractor.iniThFAST: 20
ORBextractor.minThFAST: 7

#--------------------------------------------------------------------------------------------
# Viewer Parameters
#--------------------------------------------------------------------------------------------
Viewer.KeyFrameSize: 0.05
Viewer.KeyFrameLineWidth: 1
Viewer.GraphLineWidth: 0.9
Viewer.PointSize:2
Viewer.CameraSize: 0.08
Viewer.CameraLineWidth: 3
Viewer.ViewpointX: 0
Viewer.ViewpointY: -0.7
Viewer.ViewpointZ: -1.8
Viewer.ViewpointF: 500

启动相机节点，利用usb_cam功能包,发布/camera/image_raw话题
如果还没有安装usb_cam功能包的话，运行命令安装：

sudo apt-get install ros-kinetic-usb-cam

然后在~/catkin_ws/src文件夹下新建一个名为“usb_cam_node.launch”的launch文件，用来启动usb_cam_node节点，usb_cam_node.launch文件的内容如下：

<launch>
  <node name="usb_cam" pkg="usb_cam" type="usb_cam_node" output="screen" >
    <param name="video_device" value="/dev/video1" />
    <param name="image_width" value="640" />
    <param name="image_height" value="480" />
    <param name="pixel_format" value="yuyv" />
    <param name="camera_frame_id" value="usb_cam" />
    <param name="io_method" value="mmap" />
    <remap from="/usb_cam/image_raw" to="/camera/image_raw" />
  </node>
</launch>

保存文件，然后运行命令启动节点：

roscd ~/catkin_ws/src
roslaunch usb_cam_node.launch

新打开一个终端，查看相机节点发布的消息

rostopic list

7.运行ORB-SLAM2 中的Mono

rosrun ORB_SLAM2 Mono /home/selfsongs/catkin_ws/src/ORB_SLAM2-master/Vocabulary/ORBvoc.txt /home/selfsongs/catkin_ws/src/ORB_SLAM2-master/Examples/ROS/ORB_SLAM2/default.yaml

其中default.yaml就是前面标定后保存的相机参数文件

码农公寓

Ubuntu16.04（ROS-kinetic）编译测试ORB-SLAM2

参考

安装依赖项

安装ROS kinetic

ORB-SLAM2测试自己的USB摄像头

相关文章