DIGITIZATION
Original Paper
UDC 622.272:620.179.16:004.8 © V.P. Potapov1, 2, M.V. Lysenko3, S.E. Popov1, E.S. Kudrin3, 2024
ISSN 0041-5790 (Print) • ISSN 2412-8333 (Online) • Ugol’ – Russian Coal Journal, 2024, № 9, pp. 109-114
DOI: http://dx.doi.org/10.18796/0041-5790-2024-9-109-114
Title
MINING VIDEO ENDOSCOPY – BASICS OF APPLICATION AND DATA PROCESSING BY ARTIFICIAL INTELLIGENCE METHODS
Authors
V.P. Potapov1,2, M.V. Lysenko3, S.E. Popov1, E.S. Kudrin3
1 Federal Research Center of information and calculated technologies, Novosibirsk, 690003, Russian Federation
2 Chinakal Institute of Mining of the Siberian Branch of the RAS, Novosibirsk, 690005, Russian Federation
3 LTD NIC IPGP «RANK», Kemerovo 650000, Russian Federation, e-mail: vadimptpv@gmail.com
Authors Information
Potapov V.P. – Doctor of Engineering Sciences, Professor, Аcademician of the Academy of Mining Sciences,
Academician of the Academy of Natural Sciences, Chief Researcher, Federal Research Center of Information
and Calculated Technologies, Novosibirsk, 690003, Russian Federation, Chief Researcher, Chinakal Institute of Mining of the Siberian Branch of the RA S, Novosibirsk, 690005, Russian Federation, e-mail: vadimptpv@gmail.com
Lysenko M.V. – Technical Director, LTD NIC IPGP «RANK», Kemerovo 650000, Russian Federation,
e-mail: nits.info@yandex.ru
Popov S.E. – PhD (Engineering), Senior Researcher, Federal Research Center of Information and Calculated technologies, Novosibirsk, 690003, Russian Federation, e-mail: ogidog@yandex.ru
Kudrin E.S. – Geophysical Engineer, LTD NIC IPGP «RANK», Kemerovo 650000, Russian Federation, e-mail: nits.info@yandex.ru
Abstract
Telemetric control systems, realized for example as video endoscopes, find more and more application for solving the problems of assessing the state of the rock massif subjected to anthropogenic loads. However, the processing of data obtained in the measurement processes is rather labor-intensive and is complicated by a large amount of geo-information coming in the form of video images. It is necessary to pay special attention to the decoding of each frame, highlighting the features specific to the place of measurements. The paper considers a new approach to endoscopic data processing based on one of the artificial intelligence technologies-machine vision. A certain sequence of work of the created algorithm is described and examples of concrete data processing are given. The question of further processing of the obtained geometric material and further approaches for transition to obtaining physical and mechanical properties of the array is considered.
Keywords
Mining video endoscopy, telemetry systems, artificial intelligence methods, machine vision, fracture recognition, contour massif, mining and geological conditions, neural networks, fractured massif, image markup.
References
1. Khang a., hajimahmud V.a., Misra a., litvinova E. Machine Vision and Industrial robotics in Manufacturing: approaches, technologies, and applications. CrC Press, 2025.
2. umbaugh Scott E. digital Image Processing and analysis: Computer Vision and Image analysis. 4th Edition. CrC Press, 2023.
3. Esfandiari K., abdollahi f. Neural Network-Based adaptive Control of uncertain Nonlinear Systems. New york, Springer Publ., 2022.
4. Коул А., Ганджу С., Казам М. Искусственный интеллект и компьютерное зрение. Реальныепроектына Python, Keras и tensorflow. СПб.: Питер, 2023.
5. Shinde S.V., Medhane d.V., Castillo O. applied Computer Vision and Soft Computing with Interpretable aI. Boca raton: CrC Press, 2023.
6. Mugesh S. hands-on Ml Projects with OpenCV: Master computer vision and Machine learning using OpenCV and Python. Orange Education Pvt ltd, aVa, 2023.
7. ddhich a. Practical Computer Vision: Extract insightful information from images using tensorflow, Keras, and OpenCV. Packt Publishing, 2018.
8. ayed Ismail Ben. high-Order Models in Semantic Image Segmentation. academic Press/Elsevier, 2023.
9. davies E.r. Computer Vision: Principles, algorithms, applications, learning. 5th Edition. academic Press, 2018.
10. Martinez Jes?s. tensorflow 2.0 Computer Vision Cookbook: Implement machine learning solutions to overcome various computer vision challenges.
11. Planche Benjamin, andres Eliot. hands-On Computer Vision with tensorflow 2: leverage deep learning to create powerful image processing apps with tensor flow 2.0 and Keras. Packt Publishing, 2019.
12. Pardo-Ig?zquiza E. et al. Mathematics of Planet Earth. lecture Notes in Earth System Sciences. Proceedings of the 15th annual Confer? ence of the International association for Mathematical geosciences. Springer, 2014.
13. Zhang K., Cheng h.-d. deep learning for Crack-like Object detec? tion. CrC Press, 2023.
14. ralte Z., Kar I. learn Python generative aI: Journey from autoencod? ers to transformers to large language models. BPB Publications, 2024.
15. Chambers d. digital Image Correlation: advanced Methods and applications. New york, Nova Science Publ., 2017, 125 p. 16. Masrour t., ramchoun h., hajji t., hosni M. artificial Intelligence and Industrial applications: algorithms, techniques, and Engineering applications. Springer, 2023.
Acknowledgment
The research was supported by the Russian Science Foundation grant No. 23-17-00148, https://rscf.ru/ project/23-17-00148/.
For citation
Potapov V.P., Lysenko M.V., Popov S.E., Kudrin E.S. Mining video endoscopy – basics of application and data processing by artificial intelligence methods // Ugol. 2024;(9):109-114. (In Russ.). DOI: 10.18796/0041-5790-2024-9-109-114.
Paper info
Received July 22, 2024
Reviewed August 15, 2024
Accepted August 26, 2024
