Recognition of underlying surface using a convolutional neural network on a single-board computer
The results of the development of hardware and software system (micromodule), which detects and classifies underlying surface images of the Earth are presented. The micromodule can be installed on board of a light unmanned aerial vehicle (drone). The device has the size 5.2×7.4×3.1 cm, the weight52...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | Russian |
| Published: |
National Academy of Sciences of Belarus, the United Institute of Informatics Problems
2020-09-01
|
| Series: | Informatika |
| Subjects: | |
| Online Access: | https://inf.grid.by/jour/article/view/1053 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849240248402313216 |
|---|---|
| author | D. A. Paulenka V. A. Kovalev E. V. Snezhko V. A. Liauchuk E. I. Pechkovsky |
| author_facet | D. A. Paulenka V. A. Kovalev E. V. Snezhko V. A. Liauchuk E. I. Pechkovsky |
| author_sort | D. A. Paulenka |
| collection | DOAJ |
| description | The results of the development of hardware and software system (micromodule), which detects and classifies underlying surface images of the Earth are presented. The micromodule can be installed on board of a light unmanned aerial vehicle (drone). The device has the size 5.2×7.4×3.1 cm, the weight52 g, runs on a Raspberry Pi Zero Wireless single-board microcomputer and uses a convolutional neural network based on MobileNetV2 architecture for real-time image classification. When developing the micromodule, the authors aimed to achieve a real-time image classification on inexpensive mobile equipment with low computing power so that the classification quality is comparable to popular deep convolutional network architectures. The provided information could be useful for engineers and researchers who are developing compact budget mobile systems for processing, analyzing and recognition of images. |
| format | Article |
| id | doaj-art-bfc971b3008343f594399f17103e08f9 |
| institution | Kabale University |
| issn | 1816-0301 |
| language | Russian |
| publishDate | 2020-09-01 |
| publisher | National Academy of Sciences of Belarus, the United Institute of Informatics Problems |
| record_format | Article |
| series | Informatika |
| spelling | doaj-art-bfc971b3008343f594399f17103e08f92025-08-20T04:00:40ZrusNational Academy of Sciences of Belarus, the United Institute of Informatics ProblemsInformatika1816-03012020-09-01173364310.37661/1816-0301-2020-17-3-36-43936Recognition of underlying surface using a convolutional neural network on a single-board computerD. A. Paulenka0V. A. Kovalev1E. V. Snezhko2V. A. Liauchuk3E. I. Pechkovsky4The United Institute of Informatics Problems of the National Academy of Sciences of BelarusThe United Institute of Informatics Problems of the National Academy of Sciences of BelarusThe United Institute of Informatics Problems of the National Academy of Sciences of BelarusThe United Institute of Informatics Problems of the National Academy of Sciences of BelarusThe United Institute of Informatics Problems of the National Academy of Sciences of BelarusThe results of the development of hardware and software system (micromodule), which detects and classifies underlying surface images of the Earth are presented. The micromodule can be installed on board of a light unmanned aerial vehicle (drone). The device has the size 5.2×7.4×3.1 cm, the weight52 g, runs on a Raspberry Pi Zero Wireless single-board microcomputer and uses a convolutional neural network based on MobileNetV2 architecture for real-time image classification. When developing the micromodule, the authors aimed to achieve a real-time image classification on inexpensive mobile equipment with low computing power so that the classification quality is comparable to popular deep convolutional network architectures. The provided information could be useful for engineers and researchers who are developing compact budget mobile systems for processing, analyzing and recognition of images.https://inf.grid.by/jour/article/view/1053image recognitionconvolutional neural networkdeep learningsingle-board computermobile system |
| spellingShingle | D. A. Paulenka V. A. Kovalev E. V. Snezhko V. A. Liauchuk E. I. Pechkovsky Recognition of underlying surface using a convolutional neural network on a single-board computer Informatika image recognition convolutional neural network deep learning single-board computer mobile system |
| title | Recognition of underlying surface using a convolutional neural network on a single-board computer |
| title_full | Recognition of underlying surface using a convolutional neural network on a single-board computer |
| title_fullStr | Recognition of underlying surface using a convolutional neural network on a single-board computer |
| title_full_unstemmed | Recognition of underlying surface using a convolutional neural network on a single-board computer |
| title_short | Recognition of underlying surface using a convolutional neural network on a single-board computer |
| title_sort | recognition of underlying surface using a convolutional neural network on a single board computer |
| topic | image recognition convolutional neural network deep learning single-board computer mobile system |
| url | https://inf.grid.by/jour/article/view/1053 |
| work_keys_str_mv | AT dapaulenka recognitionofunderlyingsurfaceusingaconvolutionalneuralnetworkonasingleboardcomputer AT vakovalev recognitionofunderlyingsurfaceusingaconvolutionalneuralnetworkonasingleboardcomputer AT evsnezhko recognitionofunderlyingsurfaceusingaconvolutionalneuralnetworkonasingleboardcomputer AT valiauchuk recognitionofunderlyingsurfaceusingaconvolutionalneuralnetworkonasingleboardcomputer AT eipechkovsky recognitionofunderlyingsurfaceusingaconvolutionalneuralnetworkonasingleboardcomputer |