Abstract

Three-dimensional realistic representations of buildings in urban environments have been increasingly applied as data sources in a growing number of remote sensing fields such as urban planning and city management, navigation, environmental simulation (i.e. flood, earthquake, air pollution), 3D change detection after events like natural disasters or conflicts, etc. With recent technological developments, it becomes possible to acquire high-quality 3D input data. There are two main ways to obtain elevation information: from active remote sensing systems, such as light detection and ranging (LIDAR), and from passive remote sensing systems, such as optical images, which allow the acquisition of stereo images for automatic digital surface models (DSMs) generation. Although airborne laser scanning provides very accurate DSMs, it is a costly method. On the other hand, the DSMs from stereo satellite imagery show a large coverage and lower costs. However, they are not as accurate as LIDAR DSMs. With respect to automatic 3D information extraction, the availability of accurate and detailed DSMs is a crucial issue for automatic 3D building model reconstruction. We present a novel methodology for generating a better-quality stereo DSM with refined buildings shapes using a deep learning framework. To this end, a conditional generative adversarial network (cGAN) is trained to generate accurate LIDAR DSM-like height images from noisy stereo DSMs.

Highlights

  • Three-dimensional realistic representations of buildings in an urban environment have been increasingly applied as a data source in a growing number of remote sensing applications, such as urban planning and city management, navigation, environmental simulation, 3D change detection after events like natural disasters or conflicts, etc

  • There are mainly two main ways to obtain very high-resolution elevation information: from active remote sensing systems, such as light detection and ranging (LIDAR), and from passive remote sensing systems, such as optical images, which allow the acquisition of stereo images for the automatic generation of digital surface models (DSMs)

  • We explore the potential of a deep learning framework on complete depth image reconstruction, using data with continuous values, and present a novel methodology for generating a better-quality stereo DSMs with refined buildings shapes

Read more

Summary

Introduction

Three-dimensional realistic representations of buildings in an urban environment have been increasingly applied as a data source in a growing number of remote sensing applications, such as urban planning and city management, navigation, environmental simulation (i.e., flood, earthquake, air pollution), 3D change detection after events like natural disasters or conflicts, etc. The DSMs from stereo satellite imagery show a large coverage and lower costs. They are not as accurate as LIDAR DSMs, i.e., the 3D building shapes do not feature steep walls and detailed rooftop representations. This is a major problem for stereo DSMs due to occlusions by dense and complex building structures or stereo matching errors during DSMs generation. With respect to automatic 3D information extraction, the availability of accurate and detailed DSMs is a crucial issue for automatic 3D building model reconstruction

Objectives
Methods
Results
Conclusion

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 call

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.