Semantic segmentation of Earth scanning images using neural network algorithms

Alexey A. Druki, Vladimir V. Spitsyn, Yulia A. Bolotova, Artyom A. Bashlykov

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The relevance of the research is caused by the need to develop methods, algorithms and software to improve the effectiveness of semantic segmentation of the Earth scanning images. Today there is a need to improve the quality of semantic segmentation of objects in images, despite the intensive development of modern methods and algorithms, often they do not provide the required quality of work and reliability. The main aim of the research is to develop the algorithms to solve the problem of semantic segmentation of the Earth scanning images. Objects: neural network algorithms which provide semantic segmentation of images; methods of implementation and training of artificial neural networks; image processing algorithms. Methods: To solve the tasks, the authors have used the methods of computational Intelligence; methods of pattern classification on images; theory of artificial neural networks; methods for training of artificial neural networks using Visual Studio software; deep learning framework Caffe for implementation of neural network algorithms. Results: The authors made a review of methods and algorithms which allow carrying out semantic segmentation of images. Based on the analysis, it was concluded that neural network algorithms provide more efficient results. The authors developed the convolutional neural network with the original architecture consisting of six layers. Software implementation of the described algorithms is implemented. It allows building a map of segmented buildings, roads and background based on input data. The paper introduces the comparison of results of using different learning algorithms for the developed neural network.

Original languageEnglish
Pages (from-to)59-68
Number of pages10
JournalBulletin of the Tomsk Polytechnic University, Geo Assets Engineering
Volume329
Issue number1
Publication statusPublished - 1 Jan 2018

Fingerprint

segmentation
Earth (planet)
Semantics
Neural networks
Scanning
artificial neural network
software
learning
Studios
method
Learning algorithms
Pattern recognition
Artificial intelligence
image processing
Image processing
road

Keywords

  • Image processing
  • Neural networks
  • Pattern classification
  • Remote scanning of the Earth
  • Semantic segmentation

ASJC Scopus subject areas

  • Materials Science (miscellaneous)
  • Fuel Technology
  • Geotechnical Engineering and Engineering Geology
  • Waste Management and Disposal
  • Economic Geology
  • Management, Monitoring, Policy and Law

Cite this

Semantic segmentation of Earth scanning images using neural network algorithms. / Druki, Alexey A.; Spitsyn, Vladimir V.; Bolotova, Yulia A.; Bashlykov, Artyom A.

In: Bulletin of the Tomsk Polytechnic University, Geo Assets Engineering, Vol. 329, No. 1, 01.01.2018, p. 59-68.

Research output: Contribution to journalArticle

Druki, Alexey A. ; Spitsyn, Vladimir V. ; Bolotova, Yulia A. ; Bashlykov, Artyom A. / Semantic segmentation of Earth scanning images using neural network algorithms. In: Bulletin of the Tomsk Polytechnic University, Geo Assets Engineering. 2018 ; Vol. 329, No. 1. pp. 59-68.
@article{f38fbeb560ae43acb4a113fb92a9869b,
title = "Semantic segmentation of Earth scanning images using neural network algorithms",
abstract = "The relevance of the research is caused by the need to develop methods, algorithms and software to improve the effectiveness of semantic segmentation of the Earth scanning images. Today there is a need to improve the quality of semantic segmentation of objects in images, despite the intensive development of modern methods and algorithms, often they do not provide the required quality of work and reliability. The main aim of the research is to develop the algorithms to solve the problem of semantic segmentation of the Earth scanning images. Objects: neural network algorithms which provide semantic segmentation of images; methods of implementation and training of artificial neural networks; image processing algorithms. Methods: To solve the tasks, the authors have used the methods of computational Intelligence; methods of pattern classification on images; theory of artificial neural networks; methods for training of artificial neural networks using Visual Studio software; deep learning framework Caffe for implementation of neural network algorithms. Results: The authors made a review of methods and algorithms which allow carrying out semantic segmentation of images. Based on the analysis, it was concluded that neural network algorithms provide more efficient results. The authors developed the convolutional neural network with the original architecture consisting of six layers. Software implementation of the described algorithms is implemented. It allows building a map of segmented buildings, roads and background based on input data. The paper introduces the comparison of results of using different learning algorithms for the developed neural network.",
keywords = "Image processing, Neural networks, Pattern classification, Remote scanning of the Earth, Semantic segmentation",
author = "Druki, {Alexey A.} and Spitsyn, {Vladimir V.} and Bolotova, {Yulia A.} and Bashlykov, {Artyom A.}",
year = "2018",
month = "1",
day = "1",
language = "English",
volume = "329",
pages = "59--68",
journal = "Bulletin of the Tomsk Polytechnic University, Geo Assets Engineering",
issn = "2500-1019",
publisher = "Tomsk Polytechnic University",
number = "1",

}

TY - JOUR

T1 - Semantic segmentation of Earth scanning images using neural network algorithms

AU - Druki, Alexey A.

AU - Spitsyn, Vladimir V.

AU - Bolotova, Yulia A.

AU - Bashlykov, Artyom A.

PY - 2018/1/1

Y1 - 2018/1/1

N2 - The relevance of the research is caused by the need to develop methods, algorithms and software to improve the effectiveness of semantic segmentation of the Earth scanning images. Today there is a need to improve the quality of semantic segmentation of objects in images, despite the intensive development of modern methods and algorithms, often they do not provide the required quality of work and reliability. The main aim of the research is to develop the algorithms to solve the problem of semantic segmentation of the Earth scanning images. Objects: neural network algorithms which provide semantic segmentation of images; methods of implementation and training of artificial neural networks; image processing algorithms. Methods: To solve the tasks, the authors have used the methods of computational Intelligence; methods of pattern classification on images; theory of artificial neural networks; methods for training of artificial neural networks using Visual Studio software; deep learning framework Caffe for implementation of neural network algorithms. Results: The authors made a review of methods and algorithms which allow carrying out semantic segmentation of images. Based on the analysis, it was concluded that neural network algorithms provide more efficient results. The authors developed the convolutional neural network with the original architecture consisting of six layers. Software implementation of the described algorithms is implemented. It allows building a map of segmented buildings, roads and background based on input data. The paper introduces the comparison of results of using different learning algorithms for the developed neural network.

AB - The relevance of the research is caused by the need to develop methods, algorithms and software to improve the effectiveness of semantic segmentation of the Earth scanning images. Today there is a need to improve the quality of semantic segmentation of objects in images, despite the intensive development of modern methods and algorithms, often they do not provide the required quality of work and reliability. The main aim of the research is to develop the algorithms to solve the problem of semantic segmentation of the Earth scanning images. Objects: neural network algorithms which provide semantic segmentation of images; methods of implementation and training of artificial neural networks; image processing algorithms. Methods: To solve the tasks, the authors have used the methods of computational Intelligence; methods of pattern classification on images; theory of artificial neural networks; methods for training of artificial neural networks using Visual Studio software; deep learning framework Caffe for implementation of neural network algorithms. Results: The authors made a review of methods and algorithms which allow carrying out semantic segmentation of images. Based on the analysis, it was concluded that neural network algorithms provide more efficient results. The authors developed the convolutional neural network with the original architecture consisting of six layers. Software implementation of the described algorithms is implemented. It allows building a map of segmented buildings, roads and background based on input data. The paper introduces the comparison of results of using different learning algorithms for the developed neural network.

KW - Image processing

KW - Neural networks

KW - Pattern classification

KW - Remote scanning of the Earth

KW - Semantic segmentation

UR - http://www.scopus.com/inward/record.url?scp=85041407286&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041407286&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:85041407286

VL - 329

SP - 59

EP - 68

JO - Bulletin of the Tomsk Polytechnic University, Geo Assets Engineering

JF - Bulletin of the Tomsk Polytechnic University, Geo Assets Engineering

SN - 2500-1019

IS - 1

ER -