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

Possible noise model for depth image #259

Open
Astik-2002 opened this issue Jan 7, 2025 · 2 comments
Open

Possible noise model for depth image #259

Astik-2002 opened this issue Jan 7, 2025 · 2 comments
Labels
question Further information is requested

Comments

@Astik-2002
Copy link

@JacopoPan is it possible to add some kind of a sensor model, that adds noise to the depth image? I found this repo https://github.com/ankurhanda/simkinect where noise is added to a rendered depth map, but the code requires disparity computation, which is hard to do as in pybullet we just have a single depth image (unlike a stereo camera with two rgb images, separated by a distance). Can you share if there's any other way to add noise to the image so that it's more alike to depth image from cameras like zed2 or intel realsense?

@Astik-2002
Copy link
Author

Also, can you share the limits of acceleration/deceleration for the base crazyflie model used in the simulation?

@JacopoPan JacopoPan added the question Further information is requested label Jan 7, 2025
@JacopoPan
Copy link
Member

In CtrlAviary, RPMs are capped by self.MAX_RPM and the thrust of each of the 4 motors is equal to rpm^2 * self.KF, so you can compute the maximum thrust from there

the depth frame is created here, you can add noise there

dep = np.reshape(dep, (h, w))
seg = np.reshape(seg, (h, w))

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

No branches or pull requests

2 participants