Hand Detection and Distance Estimation

Uses Tensorflow Object Detection API to detect and track hands in real-time, as well as estimate their distance from the camera

Getting Started

Prerequisites

This projects requires that you have Anaconda installed to get the development enviroment installed

Installation

Included is a .yml file that installs the necessary compoments for this to run. Run the following bash file to setup the enviroment and activate it:

bash setup_enviroment.sh

To run the hand detection python script run:

python hand_detection

License

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

Acknowledgments

• Victor Dibia - Real-time Hand Detection
• Adrian Rosebrock - Find distance from a camera to object/marker using Python and OpenCV
• Edje Electronics - Training Custom Object Detector Using Tensorflow
• EgoHands dataset
• VIVA Hand Detection dataset
• Tensorflow Object Detection API