Robust Miner Detection in Challenging Underground Environments: An Improved YOLOv11 Approach
Source abstract
Abstract
To address the issue of low detection accuracy caused by low illumination and occlusion in underground coal mines, this study proposes an innovative miner detection method. A large dataset encompassing complex environments, such as low-light conditions, partial strong light interference, and occlusion, was constructed. The Efficient Channel Attention (ECA) mechanism was integrated into the YOLOv11 model to enhance the model’s ability to focus on key features, thereby significantly improving detection accuracy. Additionally, a new weighted Complete Intersection over Union (CIoU) and adaptive confidence loss function were proposed to enhance the model’s robustness in low-light and occlusion scenarios. Experimental results demonstrate that the proposed method outperforms various improved algorithms and state-of-the-art detection models in both detection performance and robustness, providing important technical support and reference for coal miner safety assurance and intelligent mine management.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Infrastructure Maintenance and Monitoring · Visual Attention and Saliency Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, China
School of Intelligent Engineering, Jiangsu Vocational College of Information Technology, Wuxi 214000, China
School of Information Engineering, Xuzhou University of Technology, Xuzhou 221116, China
Funding
Natural Science Foundation of the Jiangsu Higher Education Institutions of China · Xuzhou Science and Technology Plan Project
References (34)
Show source-provided references
1. Analysis of the causes and safety countermeasures of coal mine accidents: A case study of coal mine accidents in China from 2018 to 202210.1016/j.psep.2024.04.137 ↗
2. Research on target detection in underground coal mines based on improved YOLOv5
3. Deep learning algorithms for object detection in low-visibility environments: A case study in coal mines
4. Intelligent emergency response system in coal mines using deep learning and IoT technologies
5. AI-Powered Personnel Tracking for Emergency Response in Coal Mines
6. Real-time deep learning-based personnel detection in coal mines with improved YOLOv4 model
7. Enhancing safety in coal mines with automated personnel detection using convolutional neural networks
8. A real-time surveillance system for underground coal mines using deep learning object detection
9. Enhanced YOLO-based detection for personnel identification in coal mines with adverse lighting conditions
10. Personnel positioning and tracking in coal mines using RFID and deep learning
11. Enhancing the generalization capability of object detection models in underground coal mining environments
12. Real-time object detection and recognition for safety monitoring in coal mines based on deep learning
13. Addressing occlusion and dust interference in deep learning-based detection models for coal mines
14. A Real-Time Personnel Detection System in Underground Coal Mines Using Deep Learning
15. Infrared and Thermal Imaging Combined System for Coal Mine Safety Monitoring and Personnel Detection
16. YOLOv11-based improved object detection model for autonomous driving in urban environments
17. Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., and Hu, Q. (2020, January 14–19). ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.01155 ↗
18. A dataset of drilling site object detection in underground coal mines
19. Advances in YOLOv11 for real-time object detection and tracking in industrial applications
20. YOLOv11-based pose estimation for sports and fitness applications
21. An Improved ECA-Net for Real-Time Object Detection in Embedded Systems
22. A Lightweight Network for Human Pose Estimation Using Attention Mechanisms
23. YOLOv11: Enhancements in Real-Time Object Detection with Improved Feature Representation
24. Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017, January 21–26). Feature Pyramid Networks for Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.106 ↗
25. A Comprehensive Review on Loss Functions in Object Detection
26. Adaptive Confidence Loss for Object Detection with Uncertainty Estimation
27. Focal Loss for Dense Object Detection
28. Kong, Y., Shang, X., and Jia, S. (2024). Drone-DETR: Efficient Small Object Detection for Remote Sensing Image Using Enhanced RT-DETR Model. Sensors, 24.10.3390/s24175496 ↗
29. Bui, T., Liu, J., and Cao, J. (2024). Elderly fall detection in complex environment based on improved YOLOv5s and LSTM. Appl. Sci., 14.10.3390/app14199028 ↗
30. A Real-Time Object Detection System Based on YOLOv5 for Smart Surveillance
31. Object Detection in Large-Scale Remote Sensing Images with a Distributed Deep Learning Framework
32. Real-Time Object Detection in Aerial Images Using YOLO with Attention Mechanism
33. A Review of Deep Learning Approaches for Object Detection in Remote Sensing Images
34. Tang, L., Li, T., and Xu, C. (2024). Stratigraphic division method based on the improved YOLOv8. Appl. Sci., 14.10.3390/app14209485 ↗