Pixels to Signals: A Real-Time Framework for Traffic Demand Estimation

TL;DR

This paper introduces a real-time traffic demand estimation framework using camera feeds, focusing on vehicle detection through background subtraction and clustering, aiming to improve urban traffic management.

Contribution

It presents a novel, efficient vehicle detection method based on background averaging and DBSCAN clustering, suitable for real-time traffic demand estimation with minimal infrastructure changes.

Findings

Effective vehicle detection using background averaging and DBSCAN

Computationally efficient with minimal infrastructure needs

Scalable solution for real-world traffic management

Abstract

Traffic congestion is becoming a challenge in the rapidly growing urban cities, resulting in increasing delays and inefficiencies within urban transportation systems. To address this issue a comprehensive methodology is designed to optimize traffic flow and minimize delays. The framework is structured with three primary components: (a) vehicle detection, (b) traffic prediction, and (c) traffic signal optimization. This paper presents the first component, vehicle detection. The methodology involves analyzing multiple sequential frames from a camera feed to compute the background, i.e. the underlying roadway, by averaging pixel values over time. The computed background is then utilized to extract the foreground, where the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm is applied to detect vehicles. With its computational efficiency and minimal infrastructure modification requirements, the proposed methodology offers a practical and scalable solution for real-world deployment.