Abstract
Abstract. Detailed digital surface models (DSMs) from space-borne sensors are the key to successful solutions for many remote sensing problems, like environmental disaster simulations, change detection in rural and urban areas, 3D urban modeling for city planning and management, etc. Traditional methodologies, e.g., stereo matching, used to generate photogrammetric DSMs from stereo imagery, usually deliver low-quality results due to the matching errors in homogeneous areas or the lack of information when observing the scene under different viewing angles. This makes the tasks related to building reconstruction very challenging since in most cases it is difficult to recognize the type of roofs, especially if overlaid with trees. This work represents a continuation of research regarding the automatic optimization of building geometries in photogrammetric DSMs with half-meter resolution and introduces an improved generative adversarial network (GAN) architecture which allows to reconstruct complete and detailed building structures without neglecting even low-rise urban constructions. The generative part of the network is constructed in a way that it simultaneously processes height and intensity information, and combines short and long skip connections within one architecture. To improve different aspects of the surface, several loss terms are used, the contributions of which are automatically balanced during training. The obtained results demonstrate that the proposed methodology can achieve two goals without any manual intervention: improve the roof surfaces by making them more planar and also recognize and optimize even small residential buildings which are hard to detect.
Highlights
1.1 Problem StatementFor humans, it is usually an easy task to understand the realistic shape and appearance of real objects in an image due to accumulated experience and knowledge
In continuation of our previous work (Bittner et al, 2019b), we introduce an improved version of the generative part of a conditional generative adversarial network-based architecture which can reconstruct better building roof structures of big residential and industrial buildings and of low-rise ones
We investigate a so-called ResNet-in-UNet architecture based on a residual network (ResNet) as an encoder which codes back the process with five up-sampled decoder layers combined with five long skip connections resembling the U-shaped structure
Summary
It is usually an easy task to understand the realistic shape and appearance of real objects in an image due to accumulated experience and knowledge. For example, intensity and height information is usually paired to reconstruct building geometries which are one of the prominent objects on the ground surface. This is necessary since digital surface models (DSMs) generated from high-resolution satellite images with different viewing angles still feature noise, inconsistency, and sometimes non-realistic building appearances due to occlusions or errors of stereo matching algorithms. We propose a machine learning approach that can automatically eliminate the vegetation and refine 2.5D building geometries in elevation models after processing pan-chromatic (PAN) and DSM
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
