Real-Time AI-Driven People Tracking and Counting Using Overhead Cameras

TL;DR

This paper introduces a real-time, AI-driven people tracking and counting system using overhead cameras, achieving high accuracy and frame rates suitable for smart building and transportation applications.

Contribution

It presents a novel combination of object detection, tracking, and counting algorithms optimized for real-time performance on low-power devices.

Findings

97% accuracy in real-time counting

20-27 FPS frame rate on edge hardware

Effective in large crowds and emergency scenarios

Abstract

Accurate people counting in smart buildings and intelligent transportation systems is crucial for energy management, safety protocols, and resource allocation. This is especially critical during emergencies, where precise occupant counts are vital for safe evacuation. Existing methods struggle with large crowds, often losing accuracy with even a few additional people. To address this limitation, this study proposes a novel approach combining a new object tracking algorithm, a novel counting algorithm, and a fine-tuned object detection model. This method achieves 97% accuracy in real-time people counting with a frame rate of 20-27 FPS on a low-power edge computer.