Urban areas analysis using satellite image segmentation and deep neural network

The goal of our research was to develop methods based on convolutional neural networks for automatically extracting the locations of buildings from high-resolution aerial images. To analyze the quality of developed deep learning algorithms, there was used Sorensen-Dice coefficient of similarity which compares results of algorithms with real masks. These masks were generated automatically from json files and sliced on smaller parts together with respective aerial photos before the training of developed convolutional neural networks. This approach allows us to cope with the problem of segmentation for high-resolution satellite images. All in all we show how deep neural networks implemented and launched on modern GPUS of high-performance supercomputer NVIDIA DGX-1 can be used to efficiently learn and detect needed objects. The problem of building detection on satellite images can be put into practice for urban planning, building control of some municipal objects, search of the best locations for future outlets etc. © The Authors, published by EDP Sciences, 2019.

Авторы
Khryaschev V.1 , Ivanovsky L. 2
Журнал
Издательство
EDP Sciences
Язык
Английский
Статус
Опубликовано
Номер
01064
Том
135
Год
2019
Организации
  • 1 P.G. Demidov Yaroslavl State University, Sovetskaya str. 14, Yaroslavl, 150003, Russian Federation
  • 2 People's Friendship University of Russia (RUDN University), Miklukho-Maklaya str.6, Moscow, 117198, Russian Federation
Ключевые слова
Antennas; Convolution; Environmental technology; Image segmentation; Neural networks; Object detection; Satellites; Supercomputers; Urban planning; Aerial photos; Building controls; Building detection; Convolutional neural network; Dice coefficient; High resolution satellite images; High-resolution aerial images; Satellite images; Deep neural networks
Дата создания
10.02.2020
Дата изменения
10.02.2020
Постоянная ссылка
https://repository.rudn.ru/ru/records/article/record/56294/
Поделиться

Другие записи