Real-time Object Detection

A simple repository developed in Reactjs to demonstrate how to implement real-time Object Detection using TensorFlow. Tensorflow.js or TF.js is a library for machine learning in Javascript, which enables ML models to be used directly in the browser or in Node.js.

The purpose of this repository is to create an object detection app via the COCO-SSD model which works in a desktop webcam to detect 80 types of objects.

Packages Used

1. COCO-SSD (https://www.npmjs.com/package/@tensorflow-models/coco-ssd) :: Single Shot multi-box Detection model
2. TensorFlow (https://github.com/tensorflow/tfjs) :: Develop ML models in JavaScript, and use ML directly in the browser or in Node.js.

Setting up

1. Clone the repository.
2. Install NPM packages: yarn.
3. Run the project: yarn start.

Author

Muhammad Anser Naseer (muhammadin87@gmail.com)

GitHub

View Github