Журнал

About Editorial Board Information for authors and reviewers Publication ethics Contacts User Account: send / review a manuscript
Archive
Volume 21, 2024
Number 1 Number 2 Number 3 Number 4 Number 5
Volume 20, 2023
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 19, 2022
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 18, 2021
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 17, 2020
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 16, 2019
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 15, 2018
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 14, 2017
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6 Number 7
Volume 13, 2016
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 12, 2015
Number 1 Number 2 Number 3 Number 4 Number 5 Number 6
Volume 11, 2014
Number 1 Number 2 Number 3 Number 4
Volume 10, 2013
Number 1 Number 2 Number 3 Number 4
Volume 9, 2012
Number 1 Number 2 Number 3 Number 4 Number 5
Volume 8, 2011
Number 1 Number 2 Number 3 Number 4
Volume 7, 2010
Number 1 Number 2 Number 3 Number 4
Issue 6, 2009
Volume 1 Volume 2
Issue 5, 2008
Volume 1 Volume 2
Issue 4, 2007
Volume 1 Volume 2
Issue 3, 2006
Volume 1 Volume 2
Issue 2, 2005
Volume 1 Volume 2
Issue 1, 2004
Volume 1
Search
Find:
русский
ISSN 2070-7401 (Print), ISSN 2411-0280 (Online)
Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa
CURRENT PROBLEMS IN REMOTE SENSING OF THE EARTH FROM SPACE

  

Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2019, Vol. 16, No. 1, pp. 25-34

Multispectral image segmentation using convolutional neural network

E.S. Ivanov 1 , I.P. Tishchenko 1 , A.N. Vinogradov 1 
1 Program Systems Institute RAS, Pereslavl-Zalessky, Russia
Accepted: 25.12.2018
DOI: 10.21046/2070-7401-2019-16-1-25-34
The paper is devoted to a processing of remote sensing aerospace multispectral images, namely, segmentation. In computer vision, image segmentation is a difficult task. The results of segmentation can be influenced by many factors: the noise of the image, texture, etc. Images obtained from the Terra satellite, with the use of the ASTER tool, were used as the initial data set for the operation of the neural network. The method of image processing, proposed in the article, makes it possible to avoid the disappearance of objects, their false appearance (redundant segmentation), and inaccuracies in determining the boundaries of the results of segmentation. Furthermore, the paper describes the methods of preliminary processing, data preparation, and the advantage of using multichannel images as compared to RGB image segmentation. Examples of segmentation of multispectral remote sensing images are given and the advantages of using neural networks in place of common segmentation algorithms are described. Lastly, the results of image segmentation can be used for subsequent analysis with less expensive resources.
Keywords: image segmentation, remote sensing, computer vision, image processing, multispectral images, convolutional neural networks
Full text

References:

  1. Bartalev S. A., Khovratovich T. S., Analiz vozmozhnostei primeneniya metodov segmentatsii sputnikovykh izobrazhenii dlya vyyavleniya izmenenii v lesakh (Analysis of the possibilities of applying satellite image segmentation techniques to detect changes in forests), Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2011, Vol. 8, No. 1, pp. 44–62, URL: http://d33.infospace.ru/d33_conf/2011v8n1/044-062.pdf.
  2. Dorogoi Ya. Yu., Arkhitektura obobshchennykh svertochnykh neironnykh setei (The architecture of generalized convolutional neural networks), Vestnik NTUU KPII, 2011, No. 54, pp. 229–234, URL: http://www.it-visnyk.kpi.ua/wp-content/uploads/2012/08/54_36.pdf.
  3. Pestunov I. A., Rylov S. A., Algoritmy spektral’no-teksturnoi segmentatsii sputnikovykh izobrazhenii vysokogo prostranstvennogo razresheniya (Spectral-textural segmentation algorithms for satellite images with high spatial resolution), Vestnik Kemerovskogo gosudarstvennogo universiteta, 2012, No. 4(52), Vol. 2, pp. 104–109.
  4. Romanov A. A., Svertochnye neironnye seti (Convolutional neural networks), 1-ya Mezhdunarodnaya nauchno-prakticheskaya konferentsiya “Nauchnye issledovaniya: klyuchevye problemy III tysyacheletiya” (1st Intern. Science-Practical Conf. “Scientific Research: Key Problems of the III Millennium”), Proc., 2018, pp. 5–9, URL: https://scientificresearch.ru/images/PDF/2018/21/svertochnye.pdf.
  5. Solov’ev R. A., Telpukhov D. V., Kustov A. G., Avtomaticheskaya segmentatsiya sputnikovykh snimkov na baze modifitsirovannoi svertochnoi neironnoi seti UNET (Automatic segmentation of satellite images based on the modified UNET convolutional neural network), Inzhenernyi vestnik Dona, 2017, Vol. 47, No. 4(47), URL: http://ivdon.ru/uploads/article/pdf/IVD_56_soloviev_N.pdf_116222c2f5.pdf.
  6. Khlopkov Yu. I., Primenenie iskusstvennykh neironnykh setei v giperzvukovoi aerodinamike (Application of artificial neural networks in hypersonic aerodynamics), Mezhdunarodnyi zhurnal prikladnykh i fundamental’nykh issledovanii, 2015, No. 4-1, pp. 45–49.
  7. Chaban L. N., Vecheruk G. V., Gavrilova T. S., Issledovanie vozmozhnostei klassifikatsii rastitel’nogo pokrova po giperspektral’nym izobrazheniyam v paketakh tematicheskoi obrabotki dannykh distantsionnogo zondirovaniya (Investigation of the possibilities of vegetation cover classification by hyperspectral images in packages of thematic processing of remote sensing data), Trudy Moskovskogo fiziko-tekhnicheskogo instituta, 2009, Vol. 1, No. 3, pp. 171–180, URL: https://mipt.ru/za-nauku/upload/7ce/f_eduu-arphcxl1tgs.pdf.
  8. Ciresan D., Giusti A., Gambardella L., Schmodbuber J., Deep neural networks segment neuronal membranes in electron microscopy images, Advances in Neural Information Processing Systems, 2012, pp. 2843–2851, URL: http://people.idsia.ch/~juergen/nips2012.pdf.
  9. Kriesel D., A Brief introduction to Neural Networks, Version ZETA2-EN, 2007, 226 p., URL: http://www.dkriesel.com/_media/science/neuronalenetze-en-zeta2-2col-dkrieselcom.pdf.
  10. Li Y., Zhang H., Shen Q., Spectral-spatial classification of hyperspectral imagery with 3D convolutional neural network, Remote Sensing, 2017, Vol. 9, No. 1, p. 67.
  11. Ronneberger O., Fischer P., Brox T., U-net: Convolutional networks for biomedical image segmentation, Intern. Conf. Medical Image Computing and Computer-Assisted Intervention, 2015, pp. 234–241.
  12. Sarangi N., Sekhar C., Tensor Deep Stacking Networks and Kernel Deep Convex Networks, 4th Intern. Conf. Pattern Recognition: Applications and Methods (ICPRAM), 2015, pp. 267–281.
  13. Schmidhube J., Deep learning in neural networks: An overview, Neural Networks, 2015, Vol. 61, pp. 85–117.