utiasDSL / gym-pybullet-drones

PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control
https://utiasDSL.github.io/gym-pybullet-drones/
MIT License
1.18k stars 349 forks source link

Occupancy grid and disparity map from depth image #228

Open Astik-2002 opened 1 month ago

Astik-2002 commented 1 month ago

Greetings. I want to create a 3D occupancy map from the depth images that we get from visionAviary. Most formulations I've seen rely on creating a disparity map from left and right camera images. Can someone share how to do it? Or any other alternative ways to create an occupancy map?

Also, rn I'm using matplotlib.pyplot.imshow to view depth images. Can I increase the update rate for this. The code I'm using can be found here https://github.com/Astik-2002/gym-pybullet-drones/blob/master_dev/gym_pybullet_drones/examples/fly_im.py. Also pinned below is a reference video Screencast from 07-10-2024 04:57:22 PM.webm

Astik-2002 commented 1 month ago

Hello. As an update to previous issue, I've managed to create an occupancy map using open3d, but the update rate is very low, hence the map is not usable. Can someone share how to improve it?

The video for current map can be found here: https://drive.google.com/file/d/18TR8p-jfaahy2NeE2IaZJ2SsY3mGCTRR/view?usp=drivesdk