mediapipe
mediapipe copied to clipboard
Using frames from python script ( RealSense + MediaPipe )
Hello! I'm just newbie to MediaPipe workflow, so I'm trying to figure out the possibility of using RealSense RGBD stream with MP solutions.
The problem is: I can only get rgb-frame and depth-frame from RealSense camera via RS SDK and librealsense in python script, like the others flow just in loop. Can the sink nodes of MP or some other method be the bridge to connect image frames from my script to MediaPipe graph solution?
Another side of the problem is that I'm using Jetson NX, and the only solution to use mediapipe with GPU support is to use it like here ( docker + bazel + mediapipe ): https://github.com/AndreV84/mediapipe
Please help me to understand of how to!
Hi @iklemyshev . Could you provide more information to investigate further on this issue.
Hi, @sureshdagooglecom!
Well, my hardware is: Jetson Xavier NX with JetPack (Ubuntu 18.04 Linux4Tegra) + RealSense 435
Camera gives me (RGB + Depth) images via RealSense SDK, which I can use in my .py script. On the other hand, I can build docker container using bazel ( as written in link I gave before ), which will use mediapipe 0.8.9.1 with my jetson's GPU and using device like /dev/video0 - for example my web-camera. it's ok. well, the only problem - I can't build mediapipe 0.8.9.1 on my Jetson with utilizing it's GPU, because I don't know how to do it. and I also can't using RealSenseSDK to have RGB+D images from my RealSense camera inside bazel's build. So, what can i do to use RealSense SDK and actual new MediaPipe with l4t GPU?
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you.
Closing as stale. Please reopen if you'd like to work on this further.
Closing as stale. Please reopen if you'd like to work on this further.
I want to continue with this question..
@iklemyshev,
Thanks for raising this request. However, We will be not supporting MediaPipe plus RealSense and feature is in not our roadmap.
This issue has been marked stale because it has no recent activity since 7 days. It will be closed if no further activity occurs. Thank you.
This issue was closed due to lack of activity after being marked stale for past 7 days.