Turtlebot3自动驾驶2020入门教程-相机内标定

Turtlebot3自动驾驶2020入门教程-相机内标定

说明：

• 本教程介绍如何进行树莓派摄像头的内标定

操作步骤

• [Remote PC] 新终端，启动roscore

$ roscore

• [TurtleBot SBC] 新终端，启动摄像头

$ roslaunch turtlebot3_autorace_camera turtlebot3_autorace_camera_pi.launch

• 将PC上的turtlebot3_autorace_camera/data文件夹里的checkerboard_for_calibration.pdf的内容打印到一张A4纸上

• [Remote PC] 根据打印出来的格子直径修改turtlebot3_autorace_camera/launch文件夹里的intrinsic_camera_calibration.launch的--square 0.108

$ rosed turtlebot3_autorace_camera intrinsic_camera_calibration.launch

 <node if="$(eval calibration_mode == 'calibration')" pkg="camera_calibration" type="cameracalibrator.py" name="cameracalibrator" args="--size 8x6 --square 0.108 image:=/camera/image camera:=/camera" output="screen"/>

###将--square 0.108修改为--square 0.0245 

<node if="$(eval calibration_mode == 'calibration')" pkg="camera_calibration" type="cameracalibrator.py" name="cameracalibrator" args="--size 8x6 --square 0.0245 image:=/camera/image camera:=/camera" output="screen"/>

• [Remote PC] 新终端，执行calibration模式下的内标定程序

$ roslaunch turtlebot3_autorace_camera intrinsic_camera_calibration.launch mode:=calibration

• 可以参考官方教程进行标定：参考链接

• [TurtleBot SBC] 标定完成之后将树莓派下的turtlebot3_autorace_camera/calibration/intrinsic_calibration/camerav2_320x240_30fps.yaml的数据换成标定好的数据

$ rosed turtlebot3_autorace_camera camerav2_320x240_30fps.yaml
## 以下为参考内容，请用实际标定的数据来替换
---
image_width: 320
image_height: 240
camera_name: camera
camera_matrix:
  rows: 3
  cols: 3
  data: [245.312887, 0, 165.227376, 0, 245.201850, 123.723979, 0, 0, 1]
distortion_model: plumb_bob
distortion_coefficients:
  rows: 1
  cols: 5
  data: [0.087617, -0.187180, 0.002487, 0.004910, 0]
rectification_matrix:
  rows: 3
  cols: 3
  data: [1, 0, 0, 0, 1, 0, 0, 0, 1]
projection_matrix:
  rows: 3
  cols: 4
  data: [245.068726, 0, 166.670019, 0, 0, 247.035309, 123.715978, 0, 0, 0, 1, 0]

演示视频