Title:	Visual Sweden City Platform
DNr:	LiU-gpu-2024-12
Project Type:	LiU Compute
Principal Investigator:	Daniel Jönsson <daniel.jonsson@liu.se>
Affiliation:	Linköpings universitet
Duration:	2024-10-14 – 2025-11-01
Classification:	10209
Keywords:

Abstract

The project aims to investigate how different data collection methods can complement each other in creating digital twins. How machine learning (ML) through deep neural networks, synthesis and image analysis can be used to enhance the final results and automate parts of the mapping and 3D reconstruction process. The project also aims to examine and develop methods where synthetic data is used to train neural networks that can be applied in the physical world. This can enable mapping of more types of objects or classes even if there is limited data available for traditional ML training. This method has been successfully used in medical technology research at Linköping University. The ambition is to generate a digital twin with semantic information and metadata with minimal manual effort while increasing mapping capabilities for more objects. The project's stakeholders work together with geodata in various forms, to map and analyze geodata to improve services, methods and to develop society. The challenges that Swedish cities face are also largely common, they are related to climate change, demographics, quality of life, planning of community development or changing transportation systems. This creates a need to develop methods and methodologies that are general and can be applied widely. The project's stakeholders reflect a range of applications and applicability. From ground perspective to regional level, from laser to satellite, from driving simulators (VTI) to disaster management (MAXAR). They all have in common the dependence on creating a geographic digital twin and making it rich in metadata and having a realistic visual expression that supports communication, both between professional actors and citizens (Norrköping municipality, Malmö city, Linköping municipality).