https://github.com/hemjotkaur/human-pose-estimation-opencv

This repository focuses on Human Pose Detection, a critical task in computer vision aimed at identifying and tracking the position and orientation of human figures in images and videos.
https://github.com/hemjotkaur/human-pose-estimation-opencv

cv2-library numpy-library opencv pillow python streamlit

Last synced: about 1 month ago
JSON representation

This repository focuses on Human Pose Detection, a critical task in computer vision aimed at identifying and tracking the position and orientation of human figures in images and videos.

• Host: GitHub
• URL: https://github.com/hemjotkaur/human-pose-estimation-opencv
• Owner: Hemjotkaur
• Created: 2024-12-30T13:36:38.000Z (about 2 months ago)
• Default Branch: main
• Last Pushed: 2024-12-30T14:02:13.000Z (about 2 months ago)
• Last Synced: 2024-12-30T15:18:36.892Z (about 2 months ago)
• Topics: cv2-library, numpy-library, opencv, pillow, python, streamlit
• Language: Python
• Homepage:
• Size: 91.8 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
Welcome to the **Human Pose Estimation App**! This application allows users to perform human pose detection on images and in real-time using advanced machine learning techniques.

## Features

- **Image Pose Estimation**: Upload an image to detect human poses using a pre-trained TensorFlow model.

- **Real-Time Pose Detection**: Experience live pose estimation through your webcam.

- **User-Friendly Interface**: Built with Streamlit for an interactive and easy-to-use experience.

## Technology Stack

- **Model**: TensorFlow (pre-trained model for pose estimation)

- **Libraries**:

  - OpenCV

  - NumPy

  - Pillow

  - cv2

  - time

  - Streamlit

## Demonstration Outputs

-I have included example output images and videos that showcase the results of pose estimation. These examples were generated using the scripts pose_estimation_image.py for images and pose_estimation_video.py for videos.

-These resources are designed to help new users understand the capabilities of the application and provide a visual reference for what to expect when using the pose estimation features. By reviewing these outputs, users can gain insights into how the model detects and represents human poses in both static images and dynamic video streams.