Abstract
The purpose of the study is to increase the recognition efficiency of irregular-shaped objects in a given location by developing a method and algorithms for recognizing irregular-shaped objects obtained using an unmanned aerial vehicle. The object of the study is the system of production control over the state of the territory, buildings and structures at hazardous production facilities of a metallurgical enterprise. The subject of the research is a mathematical representation of images, algorithms and methods for recognizing objects of irregular shape in a given location based on visual information. The study is carried out as part of research and development work at one of the leading ferrous metallurgy enterprises of the Russian Federation. This article presents the advantages and disadvantages of modern methods for recognizing objects in an image for the recognizing objects problem of irregular shape with a random location; the image structure, that comes for processing when examining the territory of a large industrial enterprise; based on the results of studying the image, a structural unit of information was built and new terms were introduced to formalize the recognition problem; the task of processing graphic information was formulated, when objects of irregular shape were detected in a given location on the territory of a large industrial enterprise, and a technology for solving it based on convolutional artificial neural networks for forward and reverse search of objects was chosen. The results of the study are the basis for the creation of an automated system for monitoring the state of the metallurgical enterprise territory, the use of which provides real-time and on an ongoing basis for the receipt of information on the current parameters of the control object safe operation into the industrial safety management system and informs the personnel about quantitative changes in previously identified objects, as well as the emergence of new ones.
Keywords
graphic information, object recognition, location and territory, task formalization, structural unit of information
1. Dorzhieva V.V. Digitization of industry: the role of artificial intelligence and opportunities for Russia. Voprosy inno-vatsionnoy ekonomiki [Russian Journal of Innovation Eco-nomics], 2022, vol. 12, no. 4, pp. 2383-2394. doi: 10.18334/vinec.12.4.116599 (In Russian)
2. Sotnikov G.A., Frolova A.V. Problems and prospects of industry digitalization in Russia. Vestnik rossiyskogo khimiko-tekhnologicheskogo universiteta imeni D.I. Mendeleeva: Gumanitarnye i sotsialno-ekonomicheskie issledovaniya [Bulletin of the Russian University of Chemical Technology named after D. I. Mendeleev: Humanitarian and socio-economic research], 2021, no. 12-2, pp. 29-39. (In Russian)
3. Aleksandrova A.V., Sabre D.M., Sabre M.M. Analysis of the state of industrial safety and working conditions at industrial facilities of the oil and gas complex of the Syrian Arab Republic. Nauchnye trudy KubGTU [Scientific Works of the Kuban State Technological University], 2019, no. 7, pp. 260-269. (In Russian)
4. Burmistrov A.V., Ilyichev V.Yu. Object recognition in images using the basic tools of the Python language and the open cv library. Nauchnoe obozrenie. Tekhnicheskie nauki. [Scientific Review. Technical science], 2021, no. 5, pp. 15-19. (In Russian)
5. Vorozhtsova N.A., Vologdin S.V. Application of machine learning to automate the process of recognizing information on photographic images of electricity metering devices. Sis-temy kompyuternoy matematiki i ikh prilozheniya [Systems of Computer Mathematics and Their Applications], 2021, no. 22, pp. 51-56. (In Russian)
6. Anirudha B Shetty, Bhoomika, Deeksha, Jeevan Rebeiro, Ramyashree, Facial recognition using Haar cascade and LBP classifiers. Global Transitions Proceedings. 2021, vol. 2(2), pp. 330-335. doi: 10.1016/j.gltp.2021.08.044
7. Chukhraev I.V., Ilyichev V.Yu. Recognition of characteristic objects in the image using computer vision technologies. E-Scio [E-Scio], 2021, no. 8(59), pp. 122-131. (In Russian)
8. Voloboy A.G., Novotortsev L.V. Comparison of regions on aerial photographs in the problem of building recognition. Novye informatsionnye tekhnologii v avtomatizirovannykh sistemakh [New information technologies in automated sys-tems], 2018, no. 21, pp. 17-23. (In Russian)
9. Sukhanov S.I., Krupochkin E.P., Kumarbekuly S., Oskorb-in N.M. Algorithm for classifying objects in an image using a correlation matrix. Trudy seminara po geometrii i ma-tematicheskomu modelirovaniyu [Proceedings of the Seminar on Geometry and Mathematical Modeling], 2020, no. 6, pp. 74-77. (In Russian)
10. Kuchuganov A.V., Kasimov D.R., Kuchuganov V.N. Model-ing reasoning when searching for objects in images. Vestnik Udmurtskogo universiteta. Matematika. Mekhanika. Kompyutermye nauki. [Bulletin of the Udmurt University. Mathematics. Mechanics. Computer science], 2020, vol. 30, no. 3, pp. 497-512. doi: 10.35634/vm200310. (In Russian)
11. Liu X., Zhang Y.n, Zou H., Wang F., Cheng X., Wu W., Liu X., Li Y. Multi-source knowledge graph reasoning for ocean oil spill detection from satellite SAR images. International Journal of Applied Earth Observation and Geoinformation. 2023, vol. 116, p. 103153. doi: 10.1016/j.jag.2022.103153
12. Sirota A.A., Mitrofanova E.Yu., Milovanova A.I. Analysis of algorithms for searching objects in images using various modifications of convolutional neural networks. Vestnik Voronezhskogo gosudarstvennogo universiteta. Seriya: Sis-temnyi analiz i informatsionnye tekhnologii [Proceedings of Voronezh State University. Series: Systems Analysis and Information Technologies], 2019, no. 3, pp. 123-137. (In Russian)
13. Nguyen T.K., Syryamkin V.I., Nguyen Ch.Kh.T. Model of the method of object recognition in images using "convolu-tional neural network - CNN". Sovremennye naukoemkie tekhnologii [Modern high technologies], 2020, no. 12-2, pp. 269-280. doi: 10.17513/snt.38445 (In Russian)
14. Amudhan A.N., Sudheer A.P. Lightweight and computation-ally faster Hypermetropic Convolutional Neural Network for small size object detection. Image and Vision Computing. 2022, vol. 119. doi:10.1016/j.imavis.2022.104396
15. Wang X., He N., Hong C., Wang Q., Chen M. Improved YOLOX-X based UAV aerial photography object detection algorithm. Image and Vision Computing. 2023, vol. 135, 104697. doi: 10.1016/j.imavis.2023.104697
16. Godunov A.I., Balanyan S.T., Egorov P.S. Image segmenta-tion and object recognition based on the technology of con-volutional neural networks. Nadezhnost i kachestvo slozhnykh sistem [Reliability and quality of complex systems], 2021, no. 3 (35), pp. 62-73. doi: 10.21685/2307-4205-2021-3-8 (In Russian)
17. Emaletdinova L.Yu., Nazarov M.A. Neural network algo-rithm for recognizing an object in an image based on a refer-ence contour. Matematicheskie metody v tekhnike i tekhnologiyakh – MMTT. ММТТ [Mathematical methods in engineering and technology – MMTT], 2020, vol. 4, pp. 137-141. (In Russian)
18. Logunova O.S., Devyatov D.Kh., Nurov Kh.Kh. Evaluation of the quality of a continuously cast billet by statistical methods using software. Izvestiya vysshikh uchebnykh zavedeniy. Chernaya metallurgiya. [Izvestiya. Ferrous Met-allurgy], 2005, no. 9, pp. 54-58. (In Russian)
19. Logunova O.S. Stochastic model of the quality of a continu-ously cast billet. Stal [Steel], 2005, no. 12, pp. 21-23. (In Russian)
20. Soynikova E.S., Batishchev D.S., Mikhelev V.M. On the recognition of uniform blood objects based on medical images. Nauchnyi rezultat. Informatsionnye tekhnologii. [Research result. Information technologies], 2018, vol. 3, no. 3, pp. 54-65. doi: 10.18413/2518-1092-2018-3-3-0-7 (In Russian)
21. Druki A.A. Application of convolutional neural networks for the extraction and recognition of license plates in images with a complex background. Izvestiya Tomskogo politekhnicheskogo universiteta [Bulletin of the Tomsk Poly-technic University], 2014, vol. 324, no. 5, pp. 85-92. (In Russian)
22. Logunova O.S., Garbar E.A., Nikolaev A.A. Interval estima-tion of signs of defects on the image of flat rolled product surface. Sovremennye dostizheniya universitetskikh nauch-nykh shkol [Modern achievements of university scientific schools], Magnitogorsk, 2021, Iss. 6, pp. 53-60. (In Russian)
23. Narkevich M.Yu., Logunova O.S., Kornienko V.D., Kali-taev A.N., Surovtsov M.M., Luganskaya D.A., Cher-nyshev A.S. Intelligent decision-making system in assessing the quality of buildings and structures at hazardous production facilities: determining the trajectory of an unmanned aerial vehicle. Vestnik Magnitogorskogo gosudarstvennogo tekhnicheskogo universiteta im. G.I. Nosova [Vestnik of No-sov Magnitogorsk State Technical University], 2022, vol. 20, no. 1, pp. 50-60. (In Russian)
24. Kabanova V.V., Klimov S.S., Logunova O.S. Collection of information and its preliminary processing during continuous monitoring of the atmosphere over an industrial enterprise. AV OVO … (S SAMOGO NACHALA…) [AB OVO... (FROM THE VERY BEGINNING...)], 2021, pp. 23-31. (In Russian)
25. Kornienko V.D., Ezhov G.A., Narkevich M.Yu., Logunova O.S. Classification of initial data for an intelligent system of expert evaluation of visually determined defects and damages. Vestnik Cherepovetskogo gosudarstvennogo universiteta [Cherepovets State University Bulletin], 2022, no. 6 (111), pp. 53-64. doi: 10.23859/1994-0637-2022-6-111-4 (In Russian)
26. Kazakov O.D., Azarenko N.Yu. Intelligent system for de-tecting and accounting for garbage on the territory of the municipality. XXI vek: itogi proshlogo i problem nastiyash-chego plus [XXI Century: Resumes of the Past and Chal-lenges of the Present plus], 2021, vol. 10, no. 2(54), pp. 59-66. (In Russian)
27. Lyapin A.A., Shulzhenko M.V. The use of convolutional neural networks in the processes of sorting solid household waste. Voprosy ustoichivogo razvitiya obshchestva [Issues of sustainable development of society], 2022, no. 8, pp. 772-776. (In Russian)
28. Skripachev V.O., Guida M.V., Guida N.V., Zhukov A.O. Study of convolutional neural networks for object detection on aerospace images. [International Journal of Open Infor-mation Technologies], 2022, vol. 10, no. 7, pp. 54-64. (In Russian)
29. Akinina N.V., Nikiforov M.B. Algorithm for detecting unau-thorized garbage dumps based on the analysis of remote sensing data. Izvestiya Tulskogo gosudarstvennogo universi-teta [Izvestiya Tula State University], 2019, no. 10, pp. 321-329. (In Russian)
30. Arkhipov A.E., Fomin I.S. Investigation of convolutional neural networks in the problem of classification of images of radioactive waste. Mashinostroenie: setevoy elektronnyi nauchnyi zhurnal [Russian Internet Journal of Industrial En-gineering], 2022, vol. 9, no. 2, pp. 39-44. doi: 10.24892/RIJIE/20220207 (In Russian)
31. Gorbachev R.A., Zaripov M.N., Shishkov D.L. Intelligent vision system for detecting obstacles and predicting the be-havior of moving objects on railway tracks. Izvestiya YuFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering sciences], 2022, no. 1 (225), pp. 256-268. doi: 10.18522/2311-3103-2022-1-256-268 (In Russian)
32. On Amendments to the Federal Norms and Rules in the Field of Industrial Safety "Rules for Conducting an Expertise of In-dustrial Safety". Available at: https://www.consultant.ru/document/cons_doc_LAW_418589/ (accessed 21 July 2023)
33. Kolkk A.A., Kolkk V.A., Shiryaev V.I. Improving algorithms for recognizing object types in control systems using fuzzy logic under uncertainty. Vestnik Yuzhno-Uralskogo gosudarstvennogo universiteta. Seriya: Kompyuternye tekhnologii, upravlenie, radioelektronika [Bulletin of South Ural State University. Series "Computer Technologies, Au-tomatic Control, Radioelectronics"], 2020, vol. 20, no. 1, pp. 39-50. doi: 10.14529/ctcr200104 (In Russian)
34. Hedayati A., Vahidnia M.H., Behzadi S. Paddy lands detec-tion using Landsat-8 satellite images and object-based classi-fication in Rasht city, Iran. The Egyptian Journal of Remote Sensing and Space Science. 2022, vol. 25(1), pp. 73-84. doi: 10.1016/j.ejrs.2021.12.008
Okhotnichenko A.V., Logunova O.S., Narkevich M.Yu. Irregular Shape Object Recognition in a Given Location: Formalization And Problem Statement of Graphic Infor-mation Processing. Elektrotekhnicheskie sistemy i kom-pleksy [Electrotechnical Systems and Complexes], 2023, no. 3(60), pp. 34-41. (In Russian). https://doi.org/10.18503/2311-8318-2023-3(60)-34-41