Open pit mine integrating YOLO optimization model and triangulation network stope data extraction method

• Autorzy: Li Tianwen

Identyfikatory

DOI

10.24425/ams.2025.154659

• Języki publikacji: EN

Abstrakty

EN

To achieve the automatic, rapid, and precise extraction of stope data from open-pit mines, this paper introduces a novel stope data extraction method based on an enhanced Mine-YOLO model integrated with a triangulated network. An attention mechanism is incorporated to improve the capture of channel, spatial, and global multi-scale features, enabling the model to effectively consider both global context and boundary details of open-pit stopes while enhancing its ability to distinguish positive samples through an optimized loss function. Following dataset training and validation, the average accuracy for stope identification and segmentation using the Mine-YOLO model has improved by 0.15 and 0.079 respectively compared to the baseline model. The Mine-YOLO framework is employed to extract stope areas from DEM data; subsequently, indices such as stope area, volume, and mining depth are automatically calculated via a constructed triangulation network. The average errors in extracted stope area, volume, and mining depth are found to be 0.058, 0.047, and 0.002 respectively – demonstrating that the proposed methodology possesses high accuracy and significant practical application value.

Słowa kluczowe

EN

improved YOLOv8; spatial attention mechanism; extraction from open pit mine; TIN triangle network; image segmentation Subject classification codes

PL

kopalnia odkrywkowa; sieć triangulacyjna; ekstrakcja danych

• Wydawca: Instytut Mechaniki Górotworu PAN
• Czasopismo: Archives of Mining Sciences
• Rocznik: 2025
• Tom: Vol. 70, no. 2
• Strony: 205--222
• Opis fizyczny: Bibliogr. 23 poz., rys., tab., wykr.

Twórcy

autor

Li Tianwen

• Yangtze University , School of Geosciences, Wuhan 430074, China

• https://orcid.org/0009-0001-0951-3975

Bibliografia

• [1] Z h. Zhang, Y. Li, G. Nan, Exploration and practice of horizontal stratified mining in non-metallic open-pit minein Hebei Province [J]. China Mining Industry 33 (06), 203-209 (2024).DOI: https://doi.org/10.12075/j.issn.1004-4051.20240222.
• [2] R . Tombe, S. Viriri, Remote sensing image scene classification: Advances and open challenges [J]. Geomatics 3(1), 137-155(2023). DOI: https://doi.org/10.3390/geomatics3010007.
• [3] H. Ji, X. Luo, Implementation of Ensemble Deep Learning Coupled with Remote Sensing for the Quantitative Analysis of Changes in Arable Land Use in a Mining Area [J]. Indian Soc Remote Sens. 49, 2875-2890 (2021).DOI: https://doi.org/10.1007/s12524-021-01430-6.
• [4] J. Xiang, J. Chen, G. Sofia, et al., Open-pit mine geomorphic changes analysis using multi-temporal UAV survey[J]. Environmental Earth Sciences 77, 1-18 (2018). DOI: https://doi.org/10.1007/s12665-018-7383-9.
• [5] C .H. Lin, T.Y. Wang, A novel convolutional neural network architecture of multispectral remote sensing images for automatic material classification [J]. Signal Processing Image Communication 97 (105), 116329 (2021).DOI: https://doi.org/10.1016/j.image.2021.116329.
• [6] W . Zhang, P. Tang, L. Zhao, Remote Sensing Image Scene Classification Using CNN-CapsNet [J]. Remote Sensing11 (5), 494 (2019). DOI: https://doi.org/10.3390/rs11050494.
• [7] Y. Liu, Y. Zhong, F. Fei, et al., Scene semantic classification based on random-scale stretched convolutional neural network for high-spatial resolution remote sensing imagery [C]. 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS). IEEE 2016, 763-766 (2016). DOI: https://doi.org/10.1109/igarss.2016.7729192.
• [8] R . Balaniuk, O. Isupova, S. Reece, Mining and tailings dam detection in satellite imagery using deep learning [J].Sensors 20 (23), 6936 (2020). DOI: https://doi.org/10.3390/s20236936.
• [9] H. Xie, Y. Pan, J. Luan, et al., Semantic segmentation of open pit mining area based on remote sensing shallow features and deep learning [C]. Big Data Analytics for Cyber-Physical System in Smart City: BDCPS 2020, 28-29 December 2020, Shanghai, China. Springer Singapore 2021, 52-59 (2021).DOI: https://doi.org/10.1007/978-981-33-4572-0_8.
• [10] T. Chen, X. Zheng, R. Niu, et al., Open-pit mine area map with Gaofen-2 satellite images using U-Net+ [J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 15, 3589-3599 (2022).DOI: https://doi.org/10.1109/jstars.2022.3171290.
• [11] H. Xie, Y. Pan, J. Luan, et al., Open-pit mining area segmentation of remote sensing images based on DUSegNet [J].Journal of the Indian Society of Remote Sensing 49 (6), 1257-1270 (2021).DOI: https://doi.org/10.1007/s12524-021-01312-x.
• [12] Y Liu, C Li, J Huang, et al. MineSDS: A Unified Framework for Small Object Detection and Drivable Area Segmentation for Open-Pit Mining Scenario [J]. Sensors 23 (13), 5977 (2023).DOI: https://doi.org/10.3390/s23135977.
• [13] X. Meng, D. Zhang, S. Dong, C. Yao, Open-Pit Granite Mining Area Extraction Using UAV Aerial Images and the Novel GIPNet. Remote Sensing 16 (5), 789 (2024). DOI: https://doi.org/10.3390/rs16050789.
• [14] D. Guo, Y. Zhang, Image detection of coal gangue based on light weight PAM-M-YOLO model [J]. Mining Researchand Development 44 (5), 220-227 (2018).
• [15] Sh. Ruan, Sh. Yan, Q. Gu, et al., Road negative obstacle detection in open pit mining area based on multi-feature fusion [J]. Journal of China Coal Society 49 (5), 2561-2572 (2019).DOI: https://doi.org/10.13225/j.cnki.jccs.2023.0539.
• [16] Y. Liu, Z. Shao, N. Hoffmann, Global attention mechanism: Retain information to enhance channel-spatial interactions[J]. arXiv preprint arXiv: 2112, 05561 (2021). DOI: https://doi.org/10.48550/arXiv.2112.05561.
• [17] W . Hao, C. Ren, M. Han, et al., Cattle body detection based on YOLOv5-EMA for precision livestock farming [J].Animals 13 (22) 3535 (2023). DOI: https://doi.org/10.3390/ani13223535.
• [18] Z . Ren, L. Wang, Z. He, Open-Pit Mining Area Extraction from High-Resolution Remote Sensing Images Basedon EMANet and FC-CRF. Remote Sensing 15 (15), 3829 (2023). DOI: https://doi.org/10.3390/rs15153829.
• [19] H. Zhang, S. Zhang, Focaler-IoU: More Focused Intersection over Union Loss [J]. arXiv preprint arXiv: 2401,10525 (2024). DOI: https://doi.org/10.48550/arXiv.2401.10525.
• [20] H. Jiale, Zh. Min, Sh. Fei, RTDETR improvement for unmanned aerial vehicle (uav) small target detection algorithm[J/OL]. Computer Engineering and Application 1-11 (2024).http://kns.cnki.net/kcms/detail/11.2127.TP.20240624.1520.010.html. DOI: 10.3778/j.issn.1002-8331.2404-0114.
• [21] L. Yi, Z. Huang, Y. Yi, Improved YOLOv8 foreign body detection method of transmission lines [J/OL]. Electronic Measurement Technology, 1-11 (2024). http://kns.cnki.net/kcms/detail/11.2175.TN.20240927.1427.138.html.
• [22] D. Li, G. Wang, Y. Guo, et al., Image recognition method of coal waste in complex working environment based on CFS-YOLO algorithm [J]. Coal Science and Technology 52 (6), 226-237 (2018).DOI: https://doi.org/10.12438/cst.2023-1967.
• [23] X. Tan, B. Zhu, J. Wang, et al., An efficient improved TIN growth algorithm for discrete elevation points [J].Journal of Naval University of Engineering 35 (02), 25-30 (2023).

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025)