This project was developed as part of an Internship Program under AICET (All India Council for Education & Training).
The objective of this project is to implement Human Pose Estimation using OpenPose (MobileNet model) and OpenCV in Python.
- Internship Organization: AICET
- Project Title: Human Pose Estimation using OpenPose and OpenCV
- Domain: Computer Vision / Artificial Intelligence
- Duration: Internship Project
- Purpose: Academic & Internship Submission
Human Pose Estimation is a computer vision technique used to detect human body keypoints such as head, arms, legs, and torso.
This project detects 18 body keypoints from images or live webcam input and visualizes them using a skeleton structure.
- Detection of human body joints
- Skeleton visualization using lines and points
- Supports image and webcam input
- Fast and lightweight OpenPose MobileNet model
- Easy-to-understand Python implementation
- Python
- OpenCV
- NumPy
- OpenPose (MobileNet)
human-pose-estimation-opencv/ │── openpose.py │── graph_opt.pb │── image.jpg │── output.JPG │── README.md │── .gitignore
- Clone the repository git clone https://github.com/sahare-mayur-0071/human-pose-estimation-opencv.git
cd human-pose-estimation-opencv
- Install dependencies
pip install opencv-python numpy
python openpose.py
python openpose.py --input image.jpg
python openpose.py --input image.jpg --thr 0.5
This project uses the OpenPose MobileNet model:
graph_opt.pb
Ensure the model file is present in the root directory before execution.
- Understanding of human pose estimation
- Hands-on experience with OpenCV
- Practical exposure to AI and computer vision
- Model integration in Python applications
This project is developed solely for educational and internship purposes under AICET.
All resources used are for learning and non-commercial use.
I would like to thank AICET for providing the internship opportunity and guidance for this project.