Overcrowded buses are a common sight in Mangalore, often leading to safety hazards and even fatal accidents. To address this, we developed a real-time crowd density monitoring system that estimates the number of passengers on a bus by analyzing Bluetooth signals from their devices.

Bluetooth Signal Detection: Devices like smartphones and wireless headphones continuously emit Bluetooth signals.

Data Collection: A Raspberry Pi 3, equipped with the Bleak library, captures these signals.

Processing & Analysis: The data, including timestamps and headcounts, is processed using Flask and stored in Supabase (PostgreSQL).

Real-Time Monitoring: Our Next.js frontend visualizes the crowd density, enabling better decision-making for transport authorities.

Next.js: Interactive web application for real-time data visualization.

Supabase (PostgreSQL): Cloud-based database for efficient data storage and retrieval.

Flask: API development and data processing.

Raspberry Pi 3 + Bleak: Capturing Bluetooth signals for headcount estimation.

Prevents Overcrowding: Helps authorities take proactive measures.

Enhances Safety: Reduces the risk of accidents caused by overfilled buses.

Seamless Integration: Works with existing transportation infrastructure.

This project demonstrates my ability to integrate hardware, backend, and frontend technologies to solve real-world problems efficiently.