3D Spatio-Semantic Micro-Morphology for Empirical Decision-Making

Rapid urbanization and evolving infrastructure present unprecedented challenges for urban planners in sustainable development. Thus, the decision support framework in urban planning to enhance spatial analysis and facilitate informed decision-making becomes very crucial. This research advocates for integrating 3D semantics, derived from airborne LiDAR point cloud data, for morphology based 3D semantic analysis. Leveraging point cloud data, the methodology enables precise 3D representations of urban environment for empirical queries that yields insights into urban fabric and provides a comprehensive understanding of 3D semantics over the resultant region. The framework’s efficacy is demonstrated through two of the many possible future applications. The queries encompas spatial impacts for upcoming developments like new construction and road expansion. The output is presented as 3D semantic model, utilitarian insights and in terms of urban morphological parameters, like, regional volumetric analysis, and urban object density and height distribution. The integration of 3D semantics in urban planning provides a versatile framework for data-driven insights, transforming 3D city models into powerful decision support tools, as demonstrated in this work with the application to the Dayton Annotated LiDAR Earth Scan (DALES) dataset.