This project performs human pose detection in video streams using the MediaPipe Pose model. The detected landmarks are refined with Kalman and Butterworth filters to reduce noise, resulting in smoother and more accurate visualization of body movements.

• Detects body landmarks from video using MediaPipe Pose
• Applies Kalman and Butterworth filters for smoother and more stable tracking
• Handles high-speed videos with reliable pose detection
• Draws pose skeleton with customizable colors
• Outputs a refined video with accurate pose visualization

• OpenCV
• MediaPipe
• NumPy
• SciPy

1. Clone the repository:

git clone https://github.com/nargesyaghoubi/pose_detection

2. Install required libraries:

pip install -r requirements.txt

This project is licensed under the MIT License . see the LICENSE file for details.

For any inquiries, please contact:

• [email protected]