Optimized YOLO Model for Accurate and Real-Time Detection of Machinery Around Shovels in Copper Mining

Document Type : Research Article

Authors

Dept. of Electrical Engineering, Yazd University, Yazd, Iran

Abstract

Shovels are among the most important equipment in open-pit mining operations, widely used for loading minerals. These heavy machines play a crucial role in operational efficiency, but due to the operator's visibility limitations, particularly in the shovel's blind spots, they pose significant safety risks. In these situations, operators may face challenges in detecting vehicles around the shovel, increasing the likelihood of accidents and incidents. This study proposes an enhanced version of the YOLO model for the precise and rapid detection of vehicles around the shovel in copper mining environments. The proposed model, using real-time processing, is capable of detecting vehicles in four directions around the shovel and preventing collisions. To evaluate this model, real-world data collected from four cameras installed around the shovel in a copper mine under various lighting conditions, including day and night, were used. The proposed method was evaluated on a new dataset of shovels under real working conditions. The results, with an average accuracy of 94.2% and a rate of 159 fps, demonstrate a significant improvement in detection accuracy and an increase in the speed of the recognition process, meeting the requirements for accurate and real-time detection of vehicles around the shovel. The findings show that the proposed model can act as an effective collision avoidance system, preventing collisions between the shovel and surrounding vehicles, which directly enhances the safety of the work environment and personnel. Furthermore, this system can help reduce accidents and injuries caused by collisions between shovels and surrounding vehicles, thereby improving the overall productivity of mining operations in copper mines.

Keywords

Main Subjects

References

[1]       Kusi-Sarpong, S., Bai, C., Sarkis, J., and Wang, X. (2015). Green supply chain practices evaluation in the mining industry using a joint rough sets and fuzzy TOPSIS methodology. Resources Policy, 46, 86–100.
[2]       Holmberg, K., Kivikytö-Reponen, P., Härkisaari, P., Valtonen, K., and Erdemir, A. (2017). Global energy consumption due to friction and wear in the mining industry. Tribology International, 115, 116–139.
[3]       Ranängen, H., and Lindman, Å. (2017). A path towards sustainability for the Nordic mining industry. Journal of Cleaner Production, 151, 43–52.
[4]       Sanmiquel, L., and Rossell, J. M., and Vintró, C. (2015). Study of spanish mining accidents using data mining techniques. Safety Science, 75, 49–55.
[5]       Permana, H. (2012). Risk assessment as a strategy to prevent mine accidents in Indonesian mining. Revista de Minería. 18(4): 43–49.
[6]       Kizil, M. (2003). Virtual reality applications in the Australian minerals industry. Application of computers and operations research in the minerals industries, South African. 569-574.
[7]       Kazan, E., and Usmen, M. A. (2018). Worker safety and injury severity analysis of earthmoving equipment accidents. Journal of safety research, 65, 73-81.
[8]       Squelch, A. P. (2001). Virtual reality for mine safety training in South Africa. Journal of the Southern African Institute of Mining and Metallurgy, 101(4): 209-216.
[9]       Kia, K., Fitch, S. M., Newsom, S. A., and Kim, J. H. (2020). Effect of whole-body vibration exposures on physiological stresses: Mining heavy equipment applications. Applied ergonomics, 85, 103065.
[10]    Domingues, M. S., Baptista, A. L., and Diogo, M. T. (2017). Engineering complex systems applied to risk management in the mining industry. International journal of mining science and technology, 27(4): 611-616.
[11]    Tichon, J., and Burgess-Limerick, R. (2011). A review of virtual reality as a medium for safety related training in mining. Journal of Health and Safety Research and Practice, 3(1): 33-40.
[12]    Shahmoradi, J., Talebi, E., Roghanchi, P., andHassanalian, M. (2020). A comprehensive review of applications of drone technology in the mining industry. Drones, 4(3): 34.
[13]    Patrucco, M., Pira, E., Pentimalli, S., Nebbia, R., and Sorlini, A. (2021). Anti-collision systems in tunneling to improve effectiveness and safety in a system-quality approach: A review of the state of the art. Infrastructures, 6(3): 42.
[14]    Kim, H., and Choi, Y. (2021). Autonomous driving robot that drives and returns along a planned route in underground mines by recognizing road signs. Applied Sciences, 11(21): 10235.
[15]    Backman, S., Lindmark, D., Bodin, K., Servin, M., Mörk, J., and Löfgren, H. (2021). Continuous control of an underground loader using deep reinforcement learning. Machines, 9(10): 216.
[16]    Kim, H., and Choi, Y. (2020). Comparison of three location estimation methods of an autonomous driving robot for underground mines. Applied Sciences, 10(14): 4831.
[17]    Lööw, J., Abrahamsson, L., and Johansson, J. (2019). Mining 4.0—The impact of new technology from a work place perspective. Mining, Metallurgy and Exploration, 36, 701-707.
[18]    Sishi, M., andTelukdarie, A. (2020). Implementation of Industry 4.0 technologies in the mining industry-a case study. International Journal of Mining and Mineral Engineering, 11(1): 1-22.
[19]    Sánchez, F., and Hartlieb, P. (2020). Innovation in the mining industry: Technological trends and a case study of the challenges of disruptive innovation. Mining, Metallurgy and Exploration, 37(5): 1385-1399.
[20]    Groves, W. A., Kecojevic, V. J., andKomljenovic, D. (2007). Analysis of fatalities and injuries involving mining equipment. Journal of safety research. 38(4): 461-470.
[21]    Amponsah-Tawiah, K., Jain, A., Leka, S., Hollis, D., and Cox, T. (2013). Examining psychosocial and physical hazards in the Ghanaian mining industry and their implications for employees’ safety experience. Journal of safety research. 45: 75-84.
[22]    Ruff, T., Coleman, P., and Martini, L. (2011). Machine-related injuries in the US mining industry and priorities for safety research. International journal of injury control and safety promotion. 18(1): 11-20.
[23]    Imam, M., Baïna, K., Tabii, Y., Ressami, E. M., Adlaoui, Y., Benzakour, I., and Abdelwahed, E. H. (2023). The future of mine safety: a comprehensive review of anti-collision systems based on computer vision in underground mines. Sensors. 23(9): 4294.
[24]    Ali, D., and Frimpong, S. (2020). Artificial intelligence, machine learning and process automation: Existing knowledge frontier and way forward for mining sector. Artificial Intelligence Review. 53(8): 6025-6042.
[25]    Hyder, Z., Siau, K., and Nah, F. (2019). Artificial intelligence, machine learning, and autonomous technologies in mining industry. Journal of Database Management (JDM). 30(2): 67-79.
[26]    Viola, P., and Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. In Proceedings of the 2001 IEEE computer society conference on computer vision and pattern recognition. CVPR 2001, Vol. 1, pp. I-I.
[27]    Dalal, N., and Triggs, B. (2005). Histograms of oriented gradients for human detection. In 2005 IEEE computer society conference on computer vision and pattern recognition. CVPR'05, Vol. 1, pp. 886-893.
[28]    Felzenszwalb, P., McAllester, D., and Ramanan, D. (2008). A discriminatively trained, multiscale, deformable part model. In 2008 IEEE conference on computer vision and pattern recognition. pp. 1-8.
[29]    Ren, S., He, K., Girshick, R., and Sun, J. (2016). Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE transactions on pattern analysis and machine intelligence. 39(6): 1137-1149.
[30]    Zou, Z., Chen, K., Shi, Z., Guo, Y., and Ye, J. (2023). Object detection in 20 years: A survey. Proceedings of the IEEE. 111(3): 257-276.
[31]    Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C. Y., and Berg, A. C. (2016). Ssd: Single shot multibox detector. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14, Springer International Publishing. pp. 21-37.
[32]    Redmon, J. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 779-788.
[33]    Lin, T., Goyal, P., Girshick, R., He, K., andDollár, P. (2017). Focal loss for dense object detection. In Proceedings of the IEEE International Conference on Computer Vision. pp. 2980–2988.
[34]    Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., and Tian, Q. (2019). Centernet: Keypoint triplets for object detection. In Proceedings of the IEEE/CVF international conference on computer vision. pp. 6569-6578.
[35]    Redmon, J., and Farhadi, A. (2017). YOLO9000: better,  faster, stronger. In Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 7263-7271.
[36]    Redmon, J. (2018). Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767.
[37]    Bochkovskiy, A., Wang, C. Y., and Liao, H. Y. M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934.
[38]    Jocher, G., Chaurasia, A., Stoken, A., Borovec, J., Kwon, Y., Fang, J., Michael, K., Montes, D., Nadar, J.  and Skalski, P. (2022). ultralytics/yolov5: v6. 1-tensorrt, tensorflow edge tpu and openvino export and inference. Zenodo.
[39]    Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L. and ;Desmaison, A. (2019). Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32.
[40]    Elfwing, S., Uchibe, E., andDoya, K. (2018). Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural networks, 107, 3-11.
[41]    Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., Nie, W. and Li, Y. (2022). YOLOv6: A single-stage object detection framework for industrial applications. arXiv preprint arXiv:2209.02976.
[42]    Wang, C. Y., Bochkovskiy, A., and Liao, H. Y. M. (2023). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 7464-7475.
[43]    Jocher, G., Chaurasia, A., and Qiu, J. (2023). Ultralytics YOLOv8 (version 8.0. 0).
[44]    Zhang, S., Yang, H., Yang, C., Yuan, W., Li, X., Wang, X., Zhang, Y., Cai, X., Sheng, Y., Deng, X. and Huang, W. (2023). Edge device detection of tea leaves with one bud and two leaves based on shuffleNetv2-YOLOv5-lite-E. Agronomy, 13(2), 577.
[45]    Powers, D. M. (2020). Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation. arXiv preprint arXiv:2010.16061.

Files

History

  • Receive Date: 12 January 2025
  • Revise Date: 27 April 2025
  • Accept Date: 27 May 2025

Share

How to cite

Statistics