Implementation and Evaluation of Digital Twin Using LiDAR and 3D City Models

Digital twins, which replicate real-world environments using data collected by devices and sensors, have garnered significant attention in recent years. These systems enable simulations of real-world conditions and predictions of future scenarios. To advance digital twin technologies, Japan's Ministry of Land, Infrastructure, Transport and Tourism (MLIT) has been promoting the development of 3D city models nationwide through Project PLATEAU. However, these models currently include only static objects, limiting their applicability for real-time simulations involving dynamic entities, such as those needed for traffic accident prediction. This paper proposes a method for constructing digital twins by integrating real-time pedestrian and vehicle data captured by LiDAR into 3D city models. The proposed approach, implemented using Unity, a widely used game engine, demonstrates its effectiveness in reflecting dynamic pedestrian and vehicle information in real time.