Deep Neural Networks for Determining the Parameters of Buildings from Single-Shot Satellite Imagery
| Autor: | Alexey Trekin, V. Yu. Ignatiev, P. Ya. Yakubovskii |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
0209 industrial biotechnology
Computer Networks and Communications Functional zoning Computer science Population 02 engineering and technology 01 natural sciences Convolutional neural network Theoretical Computer Science Image (mathematics) Set (abstract data type) 020901 industrial engineering & automation Segmentation Computer vision Satellite imagery 0101 mathematics education education.field_of_study business.industry Applied Mathematics 010102 general mathematics Oblique case Control and Systems Engineering Computer Vision and Pattern Recognition Artificial intelligence business Software Information Systems |
| Zdroj: | Journal of Computer and Systems Sciences International. 59:755-767 |
| ISSN: | 1555-6530 1064-2307 |
| DOI: | 10.1134/s106423072005007x |
| Popis: | The 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink