XIA, Yehao (Southwest Jiaotong university), Ji, Wen (Southwest Jiaotong university), Han, Ke (Southwest Jiaotong University)

Drive-By Sensing: A Framework for Selecting Vehicle Types and Deploying Sensors in Diverse Monitoring Scenarios

Scheduled for presentation during the Regular Session "S35a-Optimization, Control, and Learning for Efficient and Resilient ITS" (FR-LM-T35), Friday, November 21, 2025, 11:50−12:10, Surfers Paradise 2

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 October 18, 2025

Abstract

Vehicle-Based Urban Sensing, also known as Drive-By Sensing (DS), has gained widespread adoption in smart city applications due to its high mobility and low deployment cost. However, different urban sensing scenarios impose varying requirements on temporal and spatial resolution. This study systematically analyzes these spatial-temporal requirements and classifies typical monitoring tasks into three categories: high-frequency dynamic monitoring, low-frequency deep monitoring, and fixed-point monitoring. For each category, we propose quantitative indicators to evaluate the sensing power of different types of vehicle fleets. Leveraging real-world road networks in Manhattan and Chengdu, we conduct empirical evaluations of taxis, buses, and shared bicycles under each of the three identified monitoring scenarios. These experiments enable us to analyze the sensing power of different vehicle types in diverse urban scenarios. Based on the evaluation results, we formulate tailored recommendations for vehicle type selection and sensor deployment specific to each scenario.