Category Archives: OpenCV

AI for Everyone LESSON 29: Control of Real World Objects with Gesture Recognition in Mediapipe

In this video lesson we show you how you can control objects in the real world using OpenCV, Python, Mediapipa and our old friend, the Arduino. On the Python side, we recognize hand gestures, and then we pass the recognized gesture to Arduino and Arduino lights LED in response to what hand signal is seen. This is a simple example, but a very powerful method. Instead of LED, you could operate servos, stepper motors or relays to control any manner of different devices. For your convenience, this is the code we used on the Arduino side:

And on the python side, we used the following code.


Improved Gesture Recognition in Python and MediaPipe

In this video lesson we show you how you can improve the accuracy of your gesture recognition program developed in the last lesson. We do this by normalizing the hand landmarks distance matrix to a standard size. By doing this, you get accurate results independent of the distance your hand is from the camera. For your convenience, I include the code below which we develop in this lesson. Enjoy!


s lesson. Enjoy!

Parsing Mediapipe Data for Face Mesh, Pose, and Hand Landmarks

We all love the incredibly powerful features of the Mediapipe AI library. But, lets face it, the data is very hard to interpret, and the returned data structures are complex, and poorly documented. The purpose of this lesson is to show you how to parse the complex data structures coming from Mediapipe, and to create simple, intuitive arrays for the landmark data. We create classes in python which do the parsing, and the classes are easy to work with. With these classes, you can use mediapipe simply, and get simple to understand data structures back. The video explains what we are doing and how we are doing it. For your convenience the resulting code is posted below.


Parsing Mediapipe Data for Pose Landmarks, Hand Landmarks and Face Bounding Box


In this lesson we show how to create python classes to parse the data coming from Mediapipe for hand Landmarks, Pose Landmarks and the bounding boxes for found faces. Creating these classes allows the difficult parsing to be done in the class, and then have a simple way to parse and use all the data.


AI For Everyone: Parsing Pose and Hand Data Landmarks from Mediapipe

 In this video lesson we show you how to create simple Python classes to parse the data from mediapipe hand Landmarks and pose estimation. With these two classes, it is very easy to parse the most important data generated by mediapipe.