Automatic Detection and Interpretation of Changes in Massive Semantic 3D City Models

Son H. Nguyen

Automatic Detection and Interpretation of Changes in Massive Semantic 3D City Models

Computational Methods

Abstract

This thesis focuses on the digital aspect of urban digital twins, with semantic 3D city models as a key component. The study addresses the current lack of effective methods for tracking und comprehending changes in large city models. It proposes methods for automatic detection and interpretation of changes in these models by leveraging the graph-like structure of city objects and representing them as graphs. This allows for efficient comparison of complex objects and the identification of change patterns. The proposed methods were tested using the datasets of Hamburg as a case study.

Translated title of the contribution	Automatische Erkennung und Interpretation von Änderungen in massiven semantischen 3D-Stadtmodellen
Original language	English
Qualification	Doctor of Philosophy
Awarding Institution	Technical University of Munich
Supervisors/Advisors	Kolbe, Thomas H., Supervisor, External person
Award date	19 Nov 2024
Publication status	Published - 2024

Access to Document

https://mediatum.ub.tum.de/node?id=1765978

Cite this

@phdthesis{c1d732a6f61f4e0eaca2dfca5cab0327,

title = "Automatic Detection and Interpretation of Changes in Massive Semantic 3D City Models",

abstract = "This thesis focuses on the digital aspect of urban digital twins, with semantic 3D city models as a key component. The study addresses the current lack of effective methods for tracking und comprehending changes in large city models. It proposes methods for automatic detection and interpretation of changes in these models by leveraging the graph-like structure of city objects and representing them as graphs. This allows for efficient comparison of complex objects and the identification of change patterns. The proposed methods were tested using the datasets of Hamburg as a case study. ",

author = "Nguyen, \{Son H.\}",

note = "The dissertation was graded with summa cum laude; Excenllent Teaching in Project Work in Geoinformatics (2020); Excenllent Teaching in Exercise for Computer Science 2 (2020); Outstanding Paper Award at the 3DGeoInfo Conference at the New York University (2021); Best Young Researcher Paper Award at the 3DGeoInfo at the University of New South Wales Sydney (2022)",

year = "2024",

language = "English",

school = "Technical University of Munich",

}

TY - BOOK

T1 - Automatic Detection and Interpretation of Changes in Massive Semantic 3D City Models

AU - Nguyen, Son H.

N1 - The dissertation was graded with summa cum laude; Excenllent Teaching in Project Work in Geoinformatics (2020); Excenllent Teaching in Exercise for Computer Science 2 (2020); Outstanding Paper Award at the 3DGeoInfo Conference at the New York University (2021); Best Young Researcher Paper Award at the 3DGeoInfo at the University of New South Wales Sydney (2022)

PY - 2024

Y1 - 2024

N2 - This thesis focuses on the digital aspect of urban digital twins, with semantic 3D city models as a key component. The study addresses the current lack of effective methods for tracking und comprehending changes in large city models. It proposes methods for automatic detection and interpretation of changes in these models by leveraging the graph-like structure of city objects and representing them as graphs. This allows for efficient comparison of complex objects and the identification of change patterns. The proposed methods were tested using the datasets of Hamburg as a case study.

AB - This thesis focuses on the digital aspect of urban digital twins, with semantic 3D city models as a key component. The study addresses the current lack of effective methods for tracking und comprehending changes in large city models. It proposes methods for automatic detection and interpretation of changes in these models by leveraging the graph-like structure of city objects and representing them as graphs. This allows for efficient comparison of complex objects and the identification of change patterns. The proposed methods were tested using the datasets of Hamburg as a case study.

M3 - Doctoral Thesis

ER -