Generating 3D city models without elevation data

Journal article (2017)

Authors

F. Biljecki Urban Data Science - Architecture and the Built Environment

H. Ledoux Urban Data Science - Architecture and the Built Environment

J.E. Stoter Urban Data Science - Architecture and the Built Environment

Research Group

Urban Data Science (Architecture and the Built Environment) (TU Delft)

DOI: https://doi.org/10.1016/j.compenvurbsys.2017.01.001

Lidar GIS Urban morphology CityGML Random forest LOD1 3D city models; GIS; Building height; Lidar; Urban models; Urban morphology; Random forest; CityGML; LOD1 Building height Urban models

To reference this document use:

http://resolver.tudelft.nl/uuid:b4095b0b-b267-410a-add7-fd87d5d6ca8f

More Info

expand_more

Published Date

2017-7

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Architecture and the Built Environment

Department

Urbanism

Research Group

Urban Data Science

Abstract

Elevation datasets (e.g. point clouds) are an essential but often unavailable ingredient for the construction of 3D city models. We investigate in this paper to what extent can 3D city models be generated solely from 2D data without elevation measurements. We show that it is possible to predict the height of buildings from 2D data (their footprints and attributes available in volunteered geoinformation and cadastre), and then extrude their footprints to obtain 3D models suitable for a multitude of applications. The predictions have been carried out with machine learning techniques (random forests) using 10 different attributes and their combinations, which mirror different scenarios of completeness of real-world data. Some of the scenarios resulted in surprisingly good performance (given the circumstances): we have achieved a mean absolute error of 0.8m in the inferred heights, which satisfies the accuracy recommendations of CityGML for LOD1 models and the needs of several GIS analyses. We show that our method can be used in practice to generate 3D city models where there are no elevation data, and to supplement existing datasets with 3D models of newly constructed buildings to facilitate rapid update and maintenance of data.

Files

2017_ceus_inferring_heights.pd... (pdf)

(pdf | 14.1 Mb)

- Embargo expired in 01-07-2019

Unknown license