Overview
This is peer-reviewed work, presented at the 4th IEEE International Conference on Artificial Intelligence and Signal Processing in October 2024. I am one of six authors on the paper, “Real-Time Human Pose Estimation Using MediaPipe and Artificial Intelligence Applications in Health and Fitness”.
The engineering problem is keeping a four-stage chain, from landmark detection to repetition counting, at real-time frame rates end to end, not just in the detector.
What the pipeline does
- Landmark detection of the full 33-point body skeleton through MediaPipe.
- Spatial features computed from the raw landmarks: 3D joint angles and per-joint velocities, which turn a set of points into a signal you can reason about.
- Activity classification with LSTM networks over the landmark time series.
- Repetition counting for exercise tracking, driven by the angle and velocity signals instead of raw position.
Reported results
- 85% mAP on the COCO standard.
- 0.78 IoU.
- 30+ FPS on GPU across the full 33-landmark pipeline.
What these numbers are
These figures were measured in the study and reported in the peer-reviewed paper. They are not produced by this repository’s test suite. The repo ships benchmarking utilities so they can be re-run on other hardware and data, and the README keeps the line between “published result” and “what this code asserts” explicit.