Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Roman Larionov"'
Publikováno v:
Proceedings of the XXth Conference of Open Innovations Association FRUCT, Vol 26, Iss 1, Pp 256-261 (2020)
Deep learning and modern type of neural network technologies are increasingly used for the detection, segmentation and classification of different objects in aerial multichannel images. The goal of given research was to develop a deep learning algori
Externí odkaz:
https://doaj.org/article/0ab92e177b1c4c58b7e9aa8962210845
Publikováno v:
2022 Systems of Signal Synchronization, Generating and Processing in Telecommunications (SYNCHROINFO).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b07085bedbc7850e439b610b201a289a
https://doi.org/10.1109/synchroinfo55067.2022.9840934
https://doi.org/10.1109/synchroinfo55067.2022.9840934
Publikováno v:
Proceedings of the XXth Conference of Open Innovations Association FRUCT, Vol 26, Iss 1, Pp 256-261 (2020)
FRUCT
FRUCT
Deep learning and modern type of neural network technologies are increasingly used for the detection, segmentation and classification of different objects in aerial multichannel images. The goal of given research was to develop a deep learning algori
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::395d4de69f44d57becb70c76774fb959
https://www.fruct.org/publications/fruct26/files/Lar.pdf
https://www.fruct.org/publications/fruct26/files/Lar.pdf
Publikováno v:
EWDTS
Agricultural fields segmentation algorithms in satellite images are presented. Three convolutional neural networks were developed: U-Net with ResNet-34 and SE-ResNeXt-50 backbones and Deeplabv3+ with Xception backbone. All backbones were pretrained i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c7c387edf04233df269bb75903429567
https://doi.org/10.1109/ewdts52692.2021.9581006
https://doi.org/10.1109/ewdts52692.2021.9581006
Autor:
Roman Larionov, Vladimir Khryashchev
Publikováno v:
2020 Moscow Workshop on Electronic and Networking Technologies (MWENT).
Deep learning and convolutional neural network technologies are increasingly used in the problems of analysis, segmentation and recognition of objects in images. In this article a convolutional neural network for automated wildfire detection on high-
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4712106b5d543011d94585c70edbdb46
https://doi.org/10.1109/mwent47943.2020.9067475
https://doi.org/10.1109/mwent47943.2020.9067475
Publikováno v:
EWDTS
Results of training of convolutional neural network for satellite four-channel image segmentation are performed. Input images contain blue, green, red and near-infrared channels. The algorithm was trained to detect buildings and other urban areas. Mo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ea53e3a19fee0ff987fbb9eed6c86f46
https://doi.org/10.1109/ewdts.2019.8884452
https://doi.org/10.1109/ewdts.2019.8884452
Publikováno v:
2019 Systems of Signal Synchronization, Generating and Processing in Telecommunications (SYNCHROINFO).
Results of training a convolutional neural network for the satellite image segmentation are presented. Input images use four channels: Red, Green, Blue and Near-infrared. The convolutional neural network was trained to mark areas containing buildings
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8031fbca3842f2da5411eb550533bcef
https://doi.org/10.1109/synchroinfo.2019.8814279
https://doi.org/10.1109/synchroinfo.2019.8814279
Publikováno v:
Procedia Engineering. 165:96-103
The subway construction in St. Petersburg is a very important challenge for the development of the city. The existing stations are dramatically deficient, especially in the city's bedroom suburbs. The end stations are overloaded, and parallel subway
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fff95a08cbe463e27c013ea54e409543
https://doi.org/10.1016/j.proeng.2016.11.740
https://doi.org/10.1016/j.proeng.2016.11.740