Constructing large-scale 3D building models via LiDAR point clouds
Constructing large-scale 3D building models via LiDAR point clouds
Social Sciences Hub
Date: Tuesday 30 April 2024
Time: 13:00 - 14:30
Venue: Online (Zoom)
Category: Academic events
Website: www.ubdc.ac.uk/events/constructing-large-scale-3d-building-models-via-lidar-point-clouds
3D City models can be a useful data source not just for 3D visualization of our living environment, but also for urban environment assessment and analysis such as flooding simulation, urban housing planning application, and solar energy analysis. At the Urban Big Data Centre (UBDC), we use high-density airborne LiDAR point clouds and open-source programming tools to generate building footprints, building height attributes, and 3D building models.
In this webinar, we demonstrate how to use classified airborne LiDAR point clouds to generate building footprints and construct 3D building models at LoD1 and LoD2 levels using Glasgow as our example.
In the previous webinar in this series, we talked about applying a weakly-supervised deep learning network to classify airborne LiDAR point clouds. In this webinar, we will share our experience of how to extract building information and construct 3D building models from classified building point clouds.
We will discuss methods of generating building footprint polygons, extracting building height attributes, and introduce the algorithm used to construct LoD2 3D building models with rooftop. A set of Glasgow LiDAR data will be used as an example to demonstrate the workflow.
This webinar is ideal for researchers, students, data scientists, or anybody interested in LiDAR remote sensing, 3D building model construction, or using 3D city models for their research or work.