Skip to content

Raashika0201/object-detection

Repository files navigation

Detectify- Object Detection with TensorFlow.js

A real-time object detection web app built with Next.js and TensorFlow.js that uses your webcam to identify objects. When a person is detected, the app highlights them in red, plays a beep alarm, and displays all other objects in blue.


🚀 Features

  • 🎥 Real-time object detection via webcam
  • 🔴 Highlights detected people in red
  • 🔔 Plays an alarm sound when a person is detected
  • 🔵 Detects all other objects in blue
  • 🧠 Uses COCO-SSD model from TensorFlow.js
  • 🌐 Built with Next.js 14 (App Router)

📸 Demo

Live Demo: https://object-detection-sigma-seven.vercel.app/


🧑‍💻 Tech Stack

  • Next.js 14 with App Router
  • React Webcam
  • TensorFlow.js + COCO-SSD
  • Custom canvas rendering for bounding boxes
  • Audio alert with throttle

🛠️ Getting Started – Run Locally

Follow these steps to run the project on your local machine:

1. Clone the Repository

git clone https://github.com/Raashika0201/object-detection.git
cd object-detection 

2. Install Dependencies

npm install

3. Run the Development Server

npm run dev

4. Open the App

Visit http://localhost:3000 in your browser.

Releases

No releases published

Packages

No packages published