Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Any suggestions on getting better extrinsic calibration results? #109

Open
summerdays12 opened this issue Mar 10, 2021 · 2 comments
Open

Comments

@summerdays12
Copy link

Hi professors and everyone,
I've got poor Odom-cam extrinsic results running the extrinsic_calib, and the results are not stable.
In my case, I used Scaramuzza camera model, having 3 cameras(front, left, right side of the car), and I got poor results as the left and right camera positions are not symmetry(they should be...). And also, results of multiple running are not stable.
I also tried to use only the "CamOdoCalibration" class and an external VO(ORB-SLAM2) to compute the extrinsic, and I have had relatively good results this way. And I used these results to replace the intermediate stage 0 results and rerun the extrinsic_calib with "begin-stage=1"(so it reads the replaced extrinsics), but finally I still got bad results.
Any suggestions on getting better extrinsic calibration results?

@Vslamer
Copy link

Vslamer commented Dec 29, 2021

Me too, I think the VO has some problem, the results are also not good.

@wxz1996
Copy link

wxz1996 commented Feb 14, 2022

@summerdays12 I am also looking for a better self-calibration method, did you find a solution?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants