DSM-to-LoD2: Spaceborne Stereo Digital Surface Model Refinement

Ksenia Bittner,Marco Körner,Peter Reinartz,Pablo D’Angelo

doi:10.3390/rs10121926

Ksenia Bittner, Marco Körner + Show 2 more

Open Access

https://doi.org/10.3390/rs10121926

Copy DOI

Abstract

A digital surface model (DSM) provides the geometry and structure of an urban environment with buildings being the most prominent objects in it. Built-up areas change with time due to the rapid expansion of cities. New buildings are being built, existing ones are expanded, and old buildings are torn down. As a result, 3D surface models can increase the understanding and explanation of complex urban scenarios. They are very useful in numerous fields of remote sensing applications, in tasks related to 3D reconstruction and city modeling, planning, visualization, disaster management, navigation, and decision-making, among others. DSMs are typically derived from various acquisition techniques, like photogrammetry, laser scanning, or synthetic aperture radar (SAR). The generation of DSMs from very high resolution optical stereo satellite imagery leads to high resolution DSMs which often suffer from mismatches, missing values, or blunders, resulting in coarse building shape representation. To overcome these problems, we propose a method for 3D surface model generation with refined building shapes to level of detail (LoD) 2 from stereo half-meter resolution satellite DSMs using deep learning techniques. Mainly, we train a conditional generative adversarial network (cGAN) with an objective function based on least square residuals to generate an accurate LoD2-like DSM with enhanced 3D object shapes directly from the noisy stereo DSM input. In addition, to achieve close to LoD2 shapes of buildings, we introduce a new approach to generate an artificial DSM with accurate and realistic building geometries from city geography markup language (CityGML) data, on which we later perform a training of the proposed cGAN architecture. The experimental results demonstrate the strong potential to create large-scale remote sensing elevation models where the buildings exhibit better-quality shapes and roof forms than just using the matching process. Moreover, the developed model is successfully applied to a different city that is unseen during the training to show its generalization capacity.

Highlights

Worldwide urbanization has transformed vast farmlands and forests into urban landscapes, resulting in the appearance of new houses and infrastructures
The examples of digital surface model (DSM) generated by the DSM-to-LoD2 network for both LoD2-DSM and light detection and ranging (LIDAR)-DSM datasets are depicted in Figures 5 and 6, respectively
By investigating the obtained DSMs, we can see that both conditional generative adversarial network (cGAN) and conditional least square generative adversarial network (cLSGAN) networks are able to generate the elevation models close to the given ground truths

Summary

Introduction

Worldwide urbanization has transformed vast farmlands and forests into urban landscapes, resulting in the appearance of new houses and infrastructures. The main advantage of digital surface models (DSMs) generated using ground surveying and LIDAR is their good quality and detailed object representations Their production is costly and time consuming, and covers relatively small areas compared with images produced with spaceborne remote sensing [2]. Low-textured, homogenous, or shadowed areas caused by a combination of sun to satellite viewing geometries and surface properties often lead to blunders or not-sharp rooftop contours, as the automatic matching of the homologous points fails. The applied interpolation techniques lead to low sharpness Another very common problem in urban areas is the occurrence of occlusions due to tall buildings or trees; these depend on the acquisition viewing angles. These DSMs need to be refined either manually or automatically to make them more useful for remote sensing applications

Objectives

Methods

Results

Conclusion