Application of Methods of Fractal Images Analysis in Solving Environmental Assessment and Object Recognition Problems
https://doi.org/10.17586/0021-3454-2022-65-9-630-639
Abstract
An approach to improving the efficiency of the image pattern recognition system in monitoring and sensing complexes, and in unmanned vehicles based on the use of an additional classification feature is proposed. Tasks to be solved in sensing complexes when constructing an object recognition system are listed. To form an additional characteristic of the object, the value of the fractal dimension (fractal signature) of its contour image is used. Results of fractal analysis of traffic objects images are presented. Fractal analysis of images of territories affected by natural disasters is demonstrated. To construct a dimension map and a fractal dimension histogram, the application of the Minkowski dimension is proposed. The results of experimental verification of the proposed methods and algorithms operability are presented.
About the Authors
O. V. Esikov
Central Design Bureau of Instrument Engineering
Russian Federation
Russian Federation
Oleg V. Esikov - Dr. Sci., Professor; Chief Specialist
Tula
D. V. Titov
Southwest State University
Russian Federation
Russian Federation
Dmitry V. Titov - Dr. Sci., Associate Professor, Department of Computer Engineering
Kursk
References
1. Baklanov A.I. Sistemy nablyudeniya, monitoringa i distantsionnogo zondirovaniya Zemli (Systems of Observation, Monitoring and Remote Sensing of the Earth), Materials of the XV Scientific and Technical Conference, Alushta, 2018, рр. 43-62. (in Russ.)
2. Baklanov A.I. Sistemy nablyudeniya, monitoringa i distantsionnogo zondirovaniya Zemli (Systems of Observation, Monitoring and Remote Sensing of the Earth), Materials of the XIV Scientific and Technical Conference, Sochi, 2017, рр. 32-49. (in Russ.)
3. Danilov A.S. Ekologiya i promyshlennost' Rossii (Ecology and Industry of Russia), 2013, no. 9, pp. 4-7. (in Russ.)
4. Korshunov N.A., Kotel'nikov R.V. Pozharnaya bezopasnost', 2008, no. 1, pp. 125-129. (in Russ.)
5. Schowengerdt R.A. Remote Sensing: Models and Methods for Image Processing, Elsevier, 2006, 560 р.
6. Fedorov A.M. Reports of the Belarusian State University of Informatics and Radioelectronics, 2015, no. 7(93), pp. 129-130. (in Russ.)
7. Esikov O.V., Sukharev E.M., Altukhov A.V., Tarasov E.A. Naukoyemkiye tekhnologii (High Technologies), 2011, no. 4, pp. 54-61. (in Russ.)
8. Potapov A.A. Zarubezhnaya radioelektronika. Uspekhi sovremennoy radioelektroniki, 2000, no. 6, pp. 3-65. (in Russ.) 9. Potapov A.A. Noveyshiye metody obrabotki izobrazheniy (The Latest Image Processing Techniques), Moscow, 2008, 496 р. (in Russ.)
9. Gonzalez R.C., Woods R.E. Digital Image Processing, Prentice Hall, 2008, 954 р.
10. Crownover R.M. Introduction to Fractals and Chaos, Jones and Bartlett Books in Mathematics, 1995, 350 p.
11. Akinshin N.S., Potapov A.A., Bystrov R.P., Esikov O.V., Chernyshkov A.I. Journal of Communications Technology and Electronics, 2020, no. 7(65), pp. 835-842.
12. Esikov O.V., Denisova N.A., Romanyuta A.E. News of the Tula State University. Technical Sciences, 2021, no. 2, pp. 139-145. (in Russ.)
13. Charu С. Aggarwal, Neural Networks and Deep Learning А Textbook, Springer, 2018.
14. Simonyan K., Zisserman A. Very deep convolutional networks for large-scale image recognition, arxiv preprint arxiv:1409.1556, 2014, URL: https://arxiv.org/abs/1409.1556.
15. He K., Zhang X., Ren S., Sun J. Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, рр. 770-778.
16. Rutkowska D., Pilinski M., Rutkowski L. Sieci neuronowe, algorytmy genetyczne i systemy rozmyte, Warszawa, Łodż, Wydawnictwo Naukowe PWN, 2004.
17. Akinshin N.S., Esikov O.V., Potapov A.A., Akinshin R.N., Kuleshov A.V. EPJ Web of Conferences, MNPS-2019, 2019, no. 224, pp. 04008.
18. Akinshin N.S., Esikov O.V., Chernyshkov A.I., Savchuk K.V. News of the Tula State University. Technical Sciences, 2019, no. 10, pp. 44-52. (in Russ.)
19. https://trinixy.ru/52197-do-i-posle-navodneniya-40-foto.html. (in Russ.)
20. https://trinixy.ru/167549-fotografii-malibu-so-sputnika-do-i-posle-pozharov-9-foto.html. (in Russ.)
21. Certificate on the state registration of the computer programs 2019665064, Programma fraktal'nogo analiza izobrazheniy dlya otsenki ekologicheskoy obstanovki (Fractal Image Analysis Program for Environmental Assessment), Esikov O.V., Peteshov A.V., Kuleshov A.V., Savchuk K.V., Ivutin A.N., Priority 11.11.2019, Published 18.11.2019. (in Russ.)
Review
For citations:
Esikov O.V., Titov D.V. Application of Methods of Fractal Images Analysis in Solving Environmental Assessment and Object Recognition Problems. Journal of Instrument Engineering. 2022;65(9):630-639. (In Russ.) https://doi.org/10.17586/0021-3454-2022-65-9-630-639
Views:
11
Email this article 