Attention: Answers.ros.org is deprecated as of August the 11th, 2023. Please visit robotics.stackexchange.com to ask a new question. This site will remain online in read-only mode during the transition and into the foreseeable future. Selected questions and answers have been migrated, and redirects have been put in place to direct users to the corresponding questions on Robotics Stack Exchange. Additional details are available here.

Acceptable value of re-projection error for single camera calibration

asked 2018-06-17 23:45:17 -0600

malharjajoo
121 ●23 ●31 ●37

Hi,

While going through this tutorial on stereo calibration, it mentions 0.25 as acceptable value for epipolar error of stereo calibration but I could not find some similar statement for re-projection error for single camera calibration.

Can anyone point me to an official statement in the ROS wiki or somewhere mentioning the acceptable value of re-projection error for single camera calibration ?

Thanks!

edit retag flag offensive close merge delete

add a comment

1 Answer

Sort by » oldest newest most voted

answered 2018-06-18 01:41:22 -0600

tuandl
358 ●10 ●16 ●21

I believe there is no "official" value of reprojection error since theoretically, you would want it to be zero. Hence, all those "recommended" values are for reference only. And as rule of thumb, the lower reprojection error is, the better. I would suggest you check out kalibr. It is widely used and well-maintained package for camera-imu calibration.

edit flag offensive delete link

add a comment

Question Tools

2 followers

Stats

Asked: 2018-06-17 23:45:17 -0600

Seen: 1,812 times

Last updated: Jun 18 '18

Acceptable value of re-projection error for single camera calibration edit

1 Answer

Question Tools

Stats

Related questions

Acceptable value of re-projection error for single camera calibration