DIGITALIZATION
Original Paper
UDC 622:[628.9 + 004.932.2] © Ya.V. Popinako, М.S. Nikitenko, D.Yu. Khudonogov, P.V. Cherkasov, S.А. Kizilov, 2024
ISSN 0041-5790 (Print) • ISSN 2412-8333 (Online) • Ugol’ – Russian Coal Journal, 2024, № 11S, pp. 171-179
DOI: http://dx.doi.org/10.18796/0041-5790-2024-11S-171-179
Title
Experimental researches of illumination dependence on qualitative light line shape detection with machine vision
Authors
Ya.V. Popinako, М.S. Nikitenko, D.Yu. Khudonogov, P.V. Cherkasov, S.А. Kizilov
The Federal Research Center of Coal and Coal-Chemistry of Siberian Branch of the Russian Academy of Sciences, Kemerovo, 650000, Russian Federation е-mail: popinakoya@gmail.com
Authors Information
Popinako Ya.V. – Engineer, the Federal Research Center of Coal and Coal-Chemistry of Siberian Branch Russian Academy of Science, 650065, Kemerovo, Russian Federation, e-mail: popinakoya@gmail.com
Nikitenko M.S. – Ph (Engineering), head of laboratory, Senior researcher, he Federal Research Center of Coal and Coal-Chemistry of Siberian Branch of Russian Academy of Science, 650065, Kemerovo, Russian Federation
Khudonogov D.Yu. – Research Associate, the Federal Research Center of Coal and Coal-Chemistry of Siberian Branch of Russian Academy of Science, 650065, Kemerovo, Russian Federation
Cherkasov P.V. – Engineer, the Federal Research Center of Coal and Coal-Chemistry of Siberian Branch of Russian Academy of Science, 650065, Kemerovo, Russian Federation
Kizilov S.A. – Ph (Engineering), Research Associate, the Federal Research Center of Coal and Coal-Chemistry of Siberian Branch of Russian Academy
Abstract
The article considers an approach to shape detection for a given object with machine vision. The main purpose of the study was to estimate the illumination effect on the light line marker quality recognition with machine vision. The objects of the study were machine vision images, and the subject was the parameters and methods of their processing. A method of conducting the experiment has been developed, and the results of recognizing various laser line generators in the field at different illumination values are presented. The sequence of video scene processing operations for the most accurate detection of shape detection is shown. It is concluded that in the issue of recognizing a line light marker complementing the video scene, when using the Canny filter, pixel brightness thresholds do not affect background noise, when using the Laplace filter, setting the lowest pixel threshold value leads to the appearance of breaks in detected lines, and a higher value leads to the appearance of small objects in the region of interest. The results obtained in the form of video scene processing algorithms can be used to solve industrial autonomous vehicles traffic control issue.
Keywords
Аutonomous vehicle, control system, machine vision, light line projection, image recognition, control algorithm, illumination, mathematic morphology, laser line.
References
1. Распоряжение «Программа развития угольной промышленности России на период до 2035 года» от 13 июня 2020 г. № 1582-р // Российская газета.
2. Измерение производительности питателя при выпуске угля из подкровельной толщи на основе технологии машинного зрения / М.С. Никитенко, С.А. Кизилов, Ю.Н. Захаров и др. // Горные науки и технологии. 2022. Т. 7. № 4. С. 264-273. Nikitenko M.S., Kizilov S.., Zakharov u.N., Khudonogov .u., Ignatova .u. Measurement of feeder performance during coal discharge from an underroof seam using machine vision. Gornye nauki i tekhnologii. 2022;7(4):264-273 (In uss.).
3. Распознавание препятствий машинным зрением на основе искажения сетки световых маркеров / Д.О. Верховцев, Я.В. Попинако, М.С. Никитенко и др. // Наукоемкие технологии разработки и использования минеральных ресурсов. 2023. № 9. С. 233-238. Verkhovtsev .O., Popinako a.V., Nikitenko M.S., Khudonogov .u., Kizilov S.. ecognition of obstacles by machine vision based on distortion of the grid of light markers. Naukoemkie tekhnologii razrabotki i ispol’zovaniya mineral’nyh resursov. 2023;(9):233-238 (In uss.).
4. Nikitenko M.S., Khudonogov .u., Popinako a.V., Kizilov S.. Determining the route and roadway condition in front of autonomous vehicle. hird International Conference on Digital Technologies, Optics, and Materials Science, 2024. https://doi.org/10.1117/12.3036935.
5. Об утверждении федеральных норм и правил в области промышленной безопасности. Правила безопасности при ведении горных работ и переработке твердых полезных ископаемых. Приказ Ростехнадзора от 08 дек. 2020 г. № 505. Доступ из справ.-правовой системы «КонсультантПлюс». [Электронный ресурс]. : https://www.consultant.ru/document/cons_doc_W_372372/ (дата обращения: 15.10.2024).
6. Klinger . Image Processing with abVIEW and IMQ Vision. Prentice all P, 2020, pp. 319.
7. Ханова А.А., Озерова М.И. Обзор методов выделения контуров на изображениях / Информационные технологии в науке, образовании и производстве (ИТНОП-2020): сборник материалов VIII Международной научно-технической конференции (г. Белгород, 24-25 сентября 2020 г.). С. 89-92.
8. Титов И.О., Емельянов Г.М. Выделение контуров изображения движущегося объекта // Вестник Новгородского государственного университета. 2010. № 55. С. 27-31. itov I.O., emelyanov .M. Selection of contours of the image of a moving object. Vestnik Novgorodskogo gosudarstvennogo universiteta. 2010;(55):27-31 (In uss.).
9. Chaple .N., aruwala .., ofane M.S. Comparisions of obert, Prewitt, Sobel operator-based edge detection methods for real time uses on P. International Conference on echnologies for Sustainable evelopment (ICS). IEEE, 2015, pp. 1-4.
10. Zhou .., u ., Cheng ., i .X. Quantum image edge extraction based on improved Prewitt operator. Quantum Information Processing. 2019;18(9):261.
11. Song ., Ma B., ao W., an S. Medical image edge detection based on improved differential evolution algorithm and Prewitt operator. Acta Microscopia. 2019;28(1).
12. Hoang N.., Nguyen Q.. Metaheuristic optimized edge detection for recognition of concrete wall cracks: a comparative study on the performances of roberts, prewitt, canny, and sobel algorithms. Advances in Civil Engineering, 2018.
13. Imran N., ameed S., afeez Z., aheem Z., Waseem M., atif ., min M.S. Image Watermarking pproach sing SB and aplacian ilter. Journal of Physics: Conference Series, 2021, pp. 2129, 012015. OI: 10.1088/1742-6596/2129/1/012015.
14. elf C. Image acquisition and processing with abVIEW. CC Press, 2004, pp. 244.
15. Конушин А.С. Компьютерное зрение. ВМК МГУ, 2023. 16. mit ., elzenszwalb P., irshick . Object detection. Computer Vision: eference uide. Springer International Publishing, 2021, pp. 875-883.
Acknowledgements
The study was carried out with the financial support of the Ministry of Science and Higher Education of the Russian Federation under the event "development of a control system for autonomous vehicles based on the projected trajectory of movement” (Agreement No. 075-15-2022- 1199 dated September 28, 2022), which is conducted as part of the comprehensive scientific and technical program of a complete innovative cycle "development and implementation of a complex of technologies in the fields of exploration and extraction of minerals, ensuring of industrial safety, bioremediation, creation of new products of deep processing of coal raw materials with consecutive amelioration of ecological impact on the environment and risks to human life”, approved by the decree of the Government of the Russian Federation from 11.05.2022 No. 1144-r.
For citation
Popinako A.V., Nikitenko М.S., Khudonogov D.Yu., Cherkasov P.V., Kizilov S.А. Experimental researches of illumination dependence on qualitative light line shape detection with machine vision. Ugol’. 2024;(11S):171-179. (In uss.). DOI:10.18796/0041-5790-2024-11S-171-179.
Paper info
Received September 15, 2024
Reviewed October 21, 2024
Accepted October 31, 2024