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

Localization with Respect to an Object #50

Open
mzahana opened this issue Mar 4, 2019 · 1 comment
Open

Localization with Respect to an Object #50

mzahana opened this issue Mar 4, 2019 · 1 comment

Comments

@mzahana
Copy link

mzahana commented Mar 4, 2019

Hello @stephanweiss

I am trying to localize a moving depth camera with respect to a static object. The depth camera (Intel D435i) provides a point cloud which is used to detect and localize the static object. Sometimes there is false detection which leads to false localization. So, I'd like to use the IMU that is also embedded in the depth camera to predict where the static object would be w.r.t the moving depth camera in order to reduce the false detection.

So, I was wondering if it is possible to use this sensor fusion framework to do this task.

Any advice is appreciated.

Thanks.

@mzahana
Copy link
Author

mzahana commented Mar 12, 2019

I was able to localize the depth camera with IMU (D435i) with respect of the static object of interest. I assumed that the world coordinate frame is attached to the object. I used the pose_sensor example in ssf_update with no modifications. I just adjusted the parameters in the corresponding yaml file.

Now the issue is the that the position estimate is always offset from the actual one, but not significantly. I am suspecting that the p_ci and q_ci (which I did not adjust as I don't know them yet) could be one reason. Are there any other possible reasons?

Thanks.

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

1 participant