Ask Your Question
0

Transferring and processing video from Raspberry pi to a computer

asked 2018-08-16 12:49:13 -0500

DjalilH gravatar image

Hello! I'm a complete newcomer to ROS. I have a task: I need to bypass the obstruction with the help of deep vision. I want to transfer the signal from Raspberry pi from two cameras to the server, process the image on the server and warn about the obstacles on Raspberry pi. Question: How can I transfer video from two Raspberry pi cameras at once for machine vision to the server and what algorithm is needed to detect obstacles (walls, tables, trees). Thank you

edit retag flag offensive close merge delete

1 Answer

Sort by ยป oldest newest most voted
0

answered 2018-08-17 08:14:48 -0500

You can have a look at https://github.com/ros2/ros2/wiki/Des... for getting a good DDS configuration for video streaming.

There is a demo: https://github.com/ros2/demos/tree/71... showing how to transfer images. In your case you will have a topic "video" where you have a subscriber (the server) and two publisher (the 2 Raspberry PI)

For the processing part of the images, I cannot really help you about which algorithm you should use. There are lots of website describing how to detect obstacles. I would suggest using OpenCV as a base and look for obstacle detection algorithms. https://www.intorobotics.com/how-to-d...

edit flag offensive delete link more

Your Answer

Please start posting anonymously - your entry will be published after you log in or create a new account.

Add Answer

Question Tools

Stats

Asked: 2018-08-16 12:49:13 -0500

Seen: 89 times

Last updated: Aug 17 '18