You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
@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?
The text was updated successfully, but these errors were encountered:
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
@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?
The text was updated successfully, but these errors were encountered: