乐视体感astra pro深度摄像头在ros系统获取 深度图像 彩色图像 无色彩点云数据 彩色点云数据
生活随笔
收集整理的這篇文章主要介紹了
乐视体感astra pro深度摄像头在ros系统获取 深度图像 彩色图像 无色彩点云数据 彩色点云数据
小編覺得挺不錯的,現在分享給大家,幫大家做個參考.
?
?
-
1.astra pro深度攝像頭介紹
-
2.astra pro驅動安裝
-
3.astra pro獲取深度圖像? ?無色彩pointCloud2
-
4.astra pro獲取彩色圖像? 帶彩色的pointCloud2
?
1.astra pro深度攝像頭介紹
??
攝像頭有四個鏡頭,從左到右的鏡頭分別是1 ir發射源? 2 最小距離傳感器? 3 彩色攝像頭 4 ir接收器
?
2.astra pro驅動安裝
2.1下載驅動及依賴
ubuntu16 kinetic及ubuntu18 melodic下載以下驅
OpenNI-Linux-x64-2.3.tar.bz2
$sudo apt-get install build-essential freeglut3 freeglut3-dev $ldconfig -p | grep libudev.so.1 $cd /lib/x86_64-linux-gnu $sudo ln -s libudev.so.x.x.x libudev.so.1?
2.2編譯驅動
?解壓下載的OpenNI-Linux-x64-2.3驅動
$ cd OpenNI-Linux-x64-2.3 $ sudo chmod a+x install.sh- 安裝
插拔攝像頭,source環境
$ source OpenNIDevEnvironment- 編譯
- 連接設備，執行示例
?
編譯安裝libuvc
$ cd ~ $ git clone https://github.com/ktossell/libuvc $ cd libuvc $ mkdir build $ cd build $ cmake .. $ make && sudo make install $ sudo cp /usr/include/libusb-1.0/libusb.h /usr/local/include/libuvc/?
2.3 安裝ros的官方astra_launch? astra_camera libuvc rgbd包， ubuntu melodic的需要下載源碼安裝這些包，因為apt-get不到
如果提示源碼安裝找不到包，到ros wiki上更新一下本地的ros軟件源
$ sudo apt-get install ros-kinetic-astra-camera $ sudo apt-get install ros-kinetic-astra-launch $ sudo apt-get install ros-kinetic-libuvc-* $ sudo apt-get install ros-kinetic-rgbd-launch3.astra pro獲取深度圖像? ?無色彩pointCloud2
$ roslaunch astra_launch astra.launch打開rqt_image_view查看圖像話題
$ rqt_image_view?
打開rviz查看無彩色點云數據
?
$ rviz?
4.astra pro獲取彩色圖像? 帶彩色的pointCloud2
因為astra的驅動無發布彩色圖像，導致點云數據也無彩色數據.
有三種思路取解決：
? 1.修改官方驅動
? 2.修改ros的底層astra_camera 和 rgbd_launch 的適配
? 3.另外新開一個節點監聽無彩色pointCloud2數據和彩色數據，用彩色數據的rgb通道數值填充pointCloud2的rgbd的通道，在重新發布出來就是彩色的點云數據
?
這里采用第二種做法，第一做法難度大，第三做法耗電腦資源
4.1獲取彩色圖像
? ? 這里采用ros的uvc_camera包來獲取彩色圖像
$ sudo apt-get install uvc_camera新建一個launch文件來啟動uvc_camera
<launch><node pkg="uvc_camera" type="uvc_camera_node" name="uvc_camera" output="screen"><param name="device" type="string" value="/dev/video1" /> <param name="width" type="int" value="640" /><param name="height" type="int" value="480" /><param name="fps" type="int" value="30" /><param name="frame_id" type="string" value="camera_rgb_optical_frame" /></node> </launch>/dev/video1時攝像頭的設備號,查看一下攝像頭的設備號
$ ls /dev啟動上面的launch文件
$ roslauch uvc.launch使用rqt_image_view查看
當然也可以采用usb_cam來獲取彩色圖像，參數ros wiki上有
?
4.2 校準彩色攝像頭和深度攝像頭
獲取彩色點云數據需要對相機進行校準(個人感覺比kinect校準難，校準了好多遍)
校準深度攝像頭
$ roslaunch astra_launch astrapro.launch $ rosrun camera_calibration cameracalibrator.py image:=/camera/ir/image camera:=/camera/ir --size 8x6 --square 0.024把校準得到的yaml文件的camera_name值設為?camera_name: depth_Astra_Orbbec
校準彩色攝像頭
$ rosrun uvc_camera uvc_camera_node device:=/dev/video1 $ rosrun camera_calibration cameracalibrator.py image:=/image_raw camera:=/ --size 8x6 --square 0.024把校準得到的yaml文件的camera_name值設為 camera_name: rgb_Astra_Orbbec
?
創建launch文件
<launch><!-- "camera" should uniquely identify the device. All topics are pushed downinto the "camera" namespace, and it is prepended to tf frame ids. --><arg name="camera" default="camera" /><arg name="rgb_frame_id" default="$(arg camera)_rgb_optical_frame" /><arg name="depth_frame_id" default="$(arg camera)_depth_optical_frame" /><!-- device_id can have the following formats:"#n" : the nth device found, starts from 1"2@n" : the nth device on USB bus 2, n starts from 1"2bc5/0401@1/6" : uri in format <vendor ID>/<product ID>@<bus number>/<device number>"15120410023" : serial number --><arg name="device_id" default="#1" /><arg name="bootorder" default="0" /><arg name="devnums" default="1" /><!-- By default, calibrations are stored to file://${ROS_HOME}/camera_info/${NAME}.yaml,where ${NAME} is of the form "[rgb|depth]_[serial#]", e.g. "depth_B00367707227042B".See camera_info_manager docs for calibration URL details. --><!--<arg name="rgb_camera_info_url" default="" /><arg name="depth_camera_info_url" default="" />--><arg name="rgb_camera_info_url" default="file://$(find drive)/rgb.yaml" /><arg name="depth_camera_info_url" default="file://$(find drive)/ir.yaml" /><!-- Hardware depth registration --><arg name="depth_registration" default="false" /><!-- Driver parameters --><arg name="color_depth_synchronization" default="false" /><arg name="auto_exposure" default="true" /><arg name="auto_white_balance" default="true" /><!-- Arguments for remapping all device namespaces --><arg name="rgb" default="rgb" /><arg name="ir" default="ir" /><arg name="depth" default="depth" /><!-- Optionally suppress loading the driver nodelet and/or publishing the default tftree. Useful if you are playing back recorded raw data from a bag, or aresupplying a more accurate tf tree from calibration. --><arg name="load_driver" default="true" /><arg name="publish_tf" default="true" /><!-- Processing Modules --><arg name="rgb_processing" default="true" /><arg name="debayer_processing" default="false" /><arg name="ir_processing" default="false" /><arg name="depth_processing" default="true" /><arg name="depth_registered_processing" default="true" /><arg name="disparity_processing" default="false" /><arg name="disparity_registered_processing" default="false" /><arg name="hw_registered_processing" default="true" if="$(arg depth_registration)" /><arg name="sw_registered_processing" default="false" if="$(arg depth_registration)" /><arg name="hw_registered_processing" default="false" unless="$(arg depth_registration)" /><arg name="sw_registered_processing" default="true" unless="$(arg depth_registration)" /><!-- Disable bond topics by default --><arg name="respawn" default="false" /><!-- Worker threads for the nodelet manager --><arg name="num_worker_threads" default="4" /><!-- Push down all topics/nodelets into "camera" namespace --><group ns="$(arg camera)"><!-- Start nodelet manager --><arg name="manager" value="$(arg camera)_nodelet_manager" /><arg name="debug" default="false" /> <!-- Run manager in GDB? --><include file="$(find rgbd_launch)/launch/includes/manager.launch.xml"><arg name="name" value="$(arg manager)" /><arg name="debug" value="$(arg debug)" /><arg name="num_worker_threads" value="$(arg num_worker_threads)" /></include><!-- Load driver --><include file="$(find astra_launch)/launch/includes/device.launch.xml" if="$(arg load_driver)"><arg name="manager" value="$(arg manager)" /><arg name="device_id" value="$(arg device_id)" /><arg name="bootorder" value="$(arg bootorder)" /><arg name="devnums" value="$(arg devnums)" /><arg name="rgb_frame_id" value="$(arg rgb_frame_id)" /><arg name="depth_frame_id" value="$(arg depth_frame_id)" /><arg name="rgb_camera_info_url" value="$(arg rgb_camera_info_url)" /><arg name="depth_camera_info_url" value="$(arg depth_camera_info_url)" /><arg name="rgb" value="$(arg rgb)" /><arg name="ir" value="$(arg ir)" /><arg name="depth" value="$(arg depth)" /><arg name="respawn" value="$(arg respawn)" /><arg name="depth_registration" value="$(arg depth_registration)" /><arg name="color_depth_synchronization" value="$(arg color_depth_synchronization)" /><arg name="auto_exposure" value="$(arg auto_exposure)" /><arg name="auto_white_balance" value="$(arg auto_white_balance)" /></include><!-- Load standard constellation of processing nodelets --><include file="$(find rgbd_launch)/launch/includes/processing.launch.xml"><arg name="manager" value="$(arg manager)" /><arg name="rgb" value="$(arg rgb)" /><arg name="ir" value="$(arg ir)" /><arg name="depth" value="$(arg depth)" /><arg name="respawn" value="$(arg respawn)" /><arg name="rgb_processing" value="$(arg rgb_processing)" /><arg name="debayer_processing" value="$(arg debayer_processing)" /><arg name="ir_processing" value="$(arg ir_processing)" /><arg name="depth_processing" value="$(arg depth_processing)" /><arg name="depth_registered_processing" value="$(arg depth_registered_processing)" /><arg name="disparity_processing" value="$(arg disparity_processing)" /><arg name="disparity_registered_processing" value="$(arg disparity_registered_processing)" /><arg name="hw_registered_processing" value="$(arg hw_registered_processing)" /><arg name="sw_registered_processing" value="$(arg sw_registered_processing)" /></include><node pkg="uvc_camera" type="uvc_camera_node" name="uvc_camera" output="screen"><param name="device" value="/dev/video1" /> <param name="camera_info_url" value="$(arg rgb_camera_info_url)" /><param name="camera_name" value="rgb_Astra_Orbbec"/><param name="width" value="640" /><param name="height" value="480" /><param name="fps" value="30" /><param name="frame_id" value="camera_rgb_optical_frame" /><remap from="/camera/camera_info" to="/camera/rgb/camera_info"/><remap from="/camera/image_raw" to="/camera/rgb/image_raw"/></node></group> <!-- camera --><!-- Load reasonable defaults for the relative pose between cameras --><include file="$(find astra_launch)/launch/includes/astra_frames.launch" if="$(arg publish_tf)"><arg name="camera" value="$(arg camera)" /></include></launch>?
自行修改ir 和 rgb兩個文件的路徑，啟動這個launch文件打開rviz訂閱/camera/depth_registered/points就可以看到彩色點云了
?
總結：后期可以利用這些數據進行opencv tensorFlow 開發，及move_base的導航
?
總結
以上是生活随笔為你收集整理的乐视体感astra pro深度摄像头在ros系统获取 深度图像 彩色图像 无色彩点云数据 彩色点云数据的全部內容，希望文章能夠幫你解決所遇到的問題。
- 上一篇： 精益思想Lean thinking
- 下一篇： CC2541延时函数