位置: IT常识 - 正文
推荐整理分享Realsense D455/435内参标定以及手眼标定,希望有所帮助,仅作参考,欢迎阅读内容。
文章相关热门搜索词:,内容如对您有帮助,希望把文章链接给更多的朋友!
内参矩阵:
fx s x0K = 0 fy y0 0 0 1fx, fy为焦距,一般情况下,两者相等, x0,y0为主点坐标,s为坐标轴倾斜参数,理想情况下为0 外参数矩阵:包括旋转和平移矩阵
相机的位姿估计参考链接: 即像素坐标 Px 乘以深度 zc =相机内参K乘以相机坐标 Pc . 相关链接:
https://zhuanlan.zhihu.com/p/144307108https://www.cnblogs.com/singlex/p/pose_estimation_1.html内参标定和估计相关链接:
https://learnopencv.com/camera-calibration-using-opencv/
https://visp-doc.inria.fr/doxygen/visp-daily/tutorial-calibration-intrinsic.html
/home/jialiangfan/visp/build/example/calibration
/home/jialiangfan/visp/build/tutorial/grabber
mv /home/jialiangfan/visp/build/tutorial/grabber/chessboard-* /home/jialiangfan/visp/build/example/calibration
./calibrate-camera default-chessboard.cfg
通过ros_calibration获得较高精度的内参标定rosdep install camera_calibration普通相机的话,安装usb-cam工具,realsense也可配置,usbcam的配置方法 为https://blog.csdn.net/qq_27865227/article/details/120975769realsense 或者安装 sudo apt-get install ros-kinetic-realsense2-camera,然后运行 roslaunch realsense2_camera rs_camera.launch align_depth:=trueusb-cam配置下的校对命令:~/ rosrun camera_calibration cameracalibrator.py --size 8x6 --square 0.25 image:=/usb_cam/image_raw camera:=/usb_camrosrun camera_calibration cameracalibrator.py --size 8x6 --square 0.028 image:=/usb_cam/image_raw标定好的Realsense D455参数 [[400.50715871 0. 313.03444875] [ 0. 413.68114326 234.14594096] [ 0. 0. 1. ]]
opencv 标定Realsense D455参数cameraMatrix : [392.716970864628, 0, 243.0185503073266; 0, 387.129884776694, 215.7363588792927; 0, 0, 1] distCoeffs : [0.06146982267847866, -0.05119212933712309, -0.007642430456467396, -0.05887116845433386, 0.009214258584880468]
从realsense本身api获取的结果p[319.435 241.826] f[380.528 380.19]
ros_calibration 标定结果390.989992 0.000000 291.088402 0.000000 386.367613 236.286866 0.000000 0.000000 1.000000
distortion -0.030756 0.135162 -0.006918 -0.015546 0.000000
rectification
1.000000 0.000000 0.000000 0.000000 1.000000 0.000000 0.000000 0.000000 1.000000
projection
423.408600 0.000000 285.763055 0.000000 0.000000 418.590729 232.499668 0.000000 0.000000 0.000000 1.000000 0.000000
外参数标定python camera_calibration_show_extrinsics.py --calibration camera.xml --scale_focal 20
通过对若干个图形的姿态确立,初始坐标一般确定为棋盘左上角,反向求解出相机在初始坐标系下的姿态。
参考链接:https://blog.csdn.net/jiaoyangwm/article/details/97752238
realsense 可视化界面命令行输入:realsense-viewer rgb相机 帧率最高 60, 画质424*240,帧率30,画质为640x480 深度相机 帧率最高90, 画质比较低, 画质会随着帧率的升高而降低
Realsense机械臂手眼标定技术介绍 https://blog.csdn.net/yaked/article/details/77161160https://editor.csdn.net/md/?not_checkout=1&articleId=128649152https://zhuanlan.zhihu.com/p/576861119手眼标定流程记录:
aruco_ros等功能包
easy_handeye功能包 Marker id: 6,大小: 5cm
改写 easy_hand_eye中的参数
技术教程Franka+realsense: https://zhuanlan.zhihu.com/p/576861119visp package: http://wiki.ros.org/visp_hand2eye_calibrationKinova hand-eye-calibration: https://blog.csdn.net/qq_39367282/article/details/89515338上一篇:H5移动端适配方案rem/vw(移动端h5页面适配)
友情链接: 武汉网站建设