Affordable Access

Access to the full text

Deep Neural Networks for Determining the Parameters of Buildings from Single-Shot Satellite Imagery

Authors
  • Trekin, A. N.1, 2
  • Ignatiev, V. Yu.3, 1
  • Yakubovskii, P. Ya.1
  • 1 Skolkovo Institute of Science and Technology, Moscow, Russia , Moscow (Russia)
  • 2 AEROCOSMOS Research Institute, Moscow, Russia , Moscow (Russia)
  • 3 Institute of Control Sciences, Federal Research Center “Computer Science and Control,” Russian Academy of Sciences, Moscow, Russia , Moscow (Russia)
Type
Published Article
Journal
Journal of Computer and Systems Sciences International
Publisher
Pleiades Publishing
Publication Date
Sep 01, 2020
Volume
59
Issue
5
Pages
755–767
Identifiers
DOI: 10.1134/S106423072005007X
Source
Springer Nature
License
Yellow

Abstract

AbstractThe height of a building is a basic characteristic needed for analytical services. It can be used to evaluate the population and functional zoning of a region. The analysis of the height structure of urban territories can be useful for understanding the population dynamics. In this paper, a novel method for determining a building’s height from a single-shot Earth remote sensing oblique image is proposed. The height is evaluated by a simulation algorithm that uses the masks of shadows and the visible parts of the walls. The image is segmented using convolutional neural networks that makes it possible to extract the masks of roofs, shadows, and building walls. The segmentation models are integrated into a completely automatic system for mapping buildings and evaluating their heights. The test dataset containing a labeled set of various buildings is described. The proposed method is tested on this dataset, and it demonstrates the mean absolute error of less than 4 meters.

Report this publication

Statistics

Seen <100 times