FU, JUNHAN (The Chinese University of Hong Kong, Shenzhen), LI, Yaxuan (The Chinese University of Hong Kong, Shenzhen), LIAO, RUIZHI (The Chinese University of Hong Kong, Shenzhen)

BusScan: A Simulation Platform for Evaluating Bus-Based On-Street Parking Detection Strategies

Scheduled for presentation during the Video Session "On-Demand Video Presentations" (VP-VP), Saturday, November 22, 2025, 08:00−18:00, On-Demand Platform

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on April 2, 2026

Abstract

Urban on-street parking management faces critical challenges, such as rising car ownership, limited spaces for parking, and a lack of parking occupancy data. This results in drivers circling aimlessly for parking, exacerbating city traffic congestion. Most current smart parking solutions rely on fixed sensors on the spot, but the large-scale installation and maintenance incur prohibitive infrastructure costs. Mobile sensing through public transit vehicles (e.g., buses) offers a cost-effective alternative, yet no dynamic simulation platform exists to validate these systems' performance across different urban settings.

This paper presents BusScan, an open-source and lightweight simulation framework that models real-time parking detection through bus-mounted sensors while accounting for traffic dynamics and driver behavior patterns. The simulation architecture integrates: 1) bus route simulation with configurable traffic models, 2) parking behavior prediction using the Kaplan-Meier estimator, and 3) sensor deployment and model generalization. The modular design of the platform enables municipalities to evaluate parking policies, sensor deployment, and routing strategies through interactive simulations. By bridging the simulation gap in mobile sensing research, BusScan provides urban planners with an evidence-based toolkit for scalable smart city implementations.