Have you ever wanted your Raspberry Pi 4 Model B single-board computer to be able to identify every joint in the fingers of your hands, live? Or perhaps use hand gestures to send commands. Or utilise hand key-point detection or hand pose detection? Then this video is exactly where you need to be. Machine and deep learning have never been more accessible as this video will demonstrate. By the end of this video, you will have the knowledge to control hardware (Colour of a GlowBit) and software (VLC Media Control) through simple hand gestures.
The system built here will use Open-CV particularly CVzone. This is a huge package that helps solve real-time computer vision and image processing problems. This system will also be using MediaPipe for real-time Hand Identification, which will run a TensorFlow Lite delegate during script operation for hardware acceleration (this guide has it all!).
Hello, thank you for this tutorial. I am having a problem, hopefully you can help. I followed the whole tutorial including opencv one and everything installs without any issue. However, when I run the code, specifically the:
I get the error:
from mediapipe.python import *
No module named ‘mediapipe.python.framework_bindings’
I run the simple hand tracker script yesterday and everything worked well. Today - nothing changed - i run the script and the window pops up, but my hands dont get tracked. I already updated the system and also downloaded the script again, but it wont work… anybody has an idea how to fix it? the shell does not show any errors
I have a conflict with Mediapipe and OpenCv. Mediapipe is using gtk 3.0, while OpenCV uses gtk 2.0. When the script runs, this message appears: Gtk-ERROR **: 16:16:49.300: GTK+ 2.x symbols detected. Using GTK+ 2.x and GTK+ 3 in the same process is not supported