Skip to article frontmatterSkip to article content
Site not loading correctly?

This may be due to an incorrect BASE_URL configuration. See the MyST Documentation for reference.

An end-to-end pipeline that turns raw video into quantified, classifiable behavior: video processing, pose estimation (MediaPipe and YOLO), joint angles, derived indices, and sequence-based classification. Work through it in numbered order.

Prerequisites: Module 00B (Python Fundamentals)
Estimated time: ~12–18 hours

After this module you can extract body keypoints from video, compute kinematic features, and train a behavior classifier.

StageNotebookWhat it covers
00Getting StartedLoading and inspecting video frames in Python
01Video Processing - Frame ReductionLowering frame rate while preserving clip duration
01Video Processing - Video ClippingGenerating paired clips from longer recordings
01Video Processing - Video ChunkerSplitting a video into fixed-frame-count chunks
02Pose Estimation - MediaPipeExtracting body keypoints from video with MediaPipe
02Pose Estimation - YOLOPose estimation for biomechanics applications with YOLO
02Pose Estimation - YOLOv8 GPU (Colab)GPU-based keypoint extraction for single files and batches
02Training a Custom YOLO ModelTraining a model to track custom keypoints or objects (Label Studio to training pipeline)
03Extracting Joint AnglesComputing joint angles from MediaPipe and YOLO landmarks
04Deriving Indices from AnglesConverting angle time series into biomechanical indices
05Sequence-Based ClassificationPreparing data for training behavior classification models from pose sequences
05Sequence-Based ClassificationTraining behavior classification models

Content in this module