Xue, Lu, Chen, & Webster @ HKU
Digital Twin City: Clustering city objects in LiDAR data using Gelstalt rules
5 August, 2020
*originaly published in ISPRS J. Photogrammetry & Remote Sensing.
City-scale Light Detection And Ranging (LiDAR) point clouds can be utilized to model city objects (e.g., buildings, roads, and automobiles) for creating Digital Twin Cities (DTCs). Many city objects have invariant cross-sections following the Gestalt design principles, e.g., proximity, connectivity, symmetry, and similarity.
Xue et al. (2020) presents a COSCO approach to process urban LiDAR data to a hierarchy of objects based on symmetric cross-sections in the Gestalt designs. COSCO is effective, unsupervised, capable of understanding the DTC objects in LiDAR data.
The results show that COSCO detected the correct taxonomy and types of 12 cars from 24,126 LiDAR points in 8.28s. Then, a digital twin was created by registering online free 3D car models in 29.58s. This research can help understand and process unstructured LiDAR data for GIScience, AECO, etc.