Want to start decoding body language?

Need to see who’s really saying what in that interview?

Trying to work out what’s the sign for Wakanda Forever? 🤣

You’ll learn how to do exactly that in this Python AI tutorial. In this video you’ll learn how to leverage Mediapipe to estimate both facial and body landmarks. With that data you’ll then be able to build custom pose classification models that allow you to decode what a person might be saying with their body language with fine grain accuracy. Best of all, you can customise this to suit your own needs. If you wanted to extend this to perform drowsiness detection or extended pose classification with hand models you could!

You’ll learn how to:

1. Set up MediaPipe for Python
2. Estimate Face and Body poses using your Webcam and OpenCV
3. Collect and process Joint Coordinates using Pandas
4. Train a custom Pose Classification model using Scikit-Learn
5. Decode Body Language in Real time

Chapters:
0:00​ - Start
0:22​ - Introduction
1:05​ - How it Works
3:15​ - Tutorial Start
5:09​ - Installing Mediapipe and Dependencies
19:24​ - Capture Landmarks using OpenCV and CSV
41:48​ - Load Pose and Face Data using Pandas
49:08​ - Train Sciki-Learn Pose Classification Model
57:04​ - Evaluate Classification Model and Pickle
1:05:28​ - Making Detections using the Model
1:19:09​ - Decoded Body Language Demo
1:24:41​ - Displaying Probabilities
1:26:00​ - Adding in New Poses
1:32:16​ - Wrap Up

GET THE CODE FROM THE VIDEO: https://github.com/nicknochnack/Body-…

Subscribe: https://www.youtube.com/channel/UCHXa4OpASJEwrHrLeIzw7Yg

#python #mediapipe #ai