Edge-Computing Video Analytics for Real-Time Traffic Monitoring in a Smart City

TLDR

The rapid growth of urban centers creates significant traffic‑management challenges. The study aims to design and evaluate an edge‑computing visual sensor that tracks real‑time multi‑modal transportation while preserving privacy, and to introduce an interoperable framework for sensor data management. We developed a smart visual sensor using computer vision and deep neural networks, evaluated its performance on a town‑center dataset, and integrated it into the Agnosticity framework for multi‑sensor data collection. The Agnosticity framework successfully collected, stored, and accessed data from multiple sensors, yielding positive results in two real‑world experiments.

Abstract

The increasing development of urban centers brings serious challenges for traffic management. In this paper, we introduce a smart visual sensor, developed for a pilot project taking place in the Australian city of Liverpool (NSW). The project’s aim was to design and evaluate an edge-computing device using computer vision and deep neural networks to track in real-time multi-modal transportation while ensuring citizens’ privacy. The performance of the sensor was evaluated on a town center dataset. We also introduce the interoperable Agnosticity framework designed to collect, store and access data from multiple sensors, with results from two real-world experiments.