报告专家：范红超 挪威科技大学教授报告人介绍：Hongchao Fan is professor for 3D Geoinformatics at the Department of Civil and Environmental Engineering at the Norwegian University of Science and Technology (NTNU). He studied Geoinformatics at the Wuhan University from 1996 t0 2000. Then he studied Geodesy and Geoinformatics at the same university and received his master degree (Dipl.-Ing.) in 2006. From 2007 to 2010, he worked as scientific assistant at the Department of Cartography at the Technical University of Munich where he received his PhD (Dr.-Ing.) in October 2010. After the PhD study, he worked as Group Leader for 3D Data Infrastructure at the Heidelberg University in Germany. He was professor at Wuhan University and is now working as professor at NTNU in Trondheim, Norway. His research interests include 3D city modelling, spatial data mining from VGI data, Photogrammetery, and laser scanning.
报告题目：Automated generation of 3D building models in LoD3 from multi-sourced RS data
报告简介：
LoD3 building models are important elements in digital twins of cities. They include complicated roof structures and detailed façade geometries with rich semantic information. In this talk, Prof. Fan will present the recent research findings in automated 3D roof modelling and building façade generation from both image and Lidar point clouds data. He will share his experiences about using deep learning-based methods and conventional rule-based methods for 3D modelling, and discuss the recent tendency of using deep-learning technology in Geomatics.学术报告会现场
