Digital Twinning Mechanism and Building Information Modeling for a Smart Parking Management System

Parking space shortages are attributed to an increased density of vehicle presence in the urban context, necessitating the implementation of effective parking management strategies, especially in areas where facility expansion is constrained by limited land availability. Many parking facilities remain operationally inefficient and underutilized due to manual vehicle profiling methods and having little access to parking resource utilization data. This study develops a digital twin-based smart parking management system integrating machine vision, data modeling, and digital twin technology to automate facility management operations. The system uses YOLOv7 for vehicle and license plate detection, and Deep Text Recognition-Scene Text Recognition (DTR-STR) for license plate recognition (LPR). Findings indicate an 89.89% accuracy for vehicle profiling and LPR-based occupancy tracking tasks, and 94.86% for vehicle detection-based occupancy tracking. The system in the built environment comprises of three features: (1) automated vehicle profiling at parking entry and exit points, (2) occupancy monitoring through LPR, and (3) object detection for occupancy tracking. The 3D BIM digital twin model in Autodesk Revit processes inference data from machine vision models to visualize parking activity. Smart parking automation offers a viable solution for business stakeholders interested in operations optimization through manual labor reduction, improving efficiency, and minimizing congestion.