Downhole Coal–Rock Recognition Based on Joint Migration and Enhanced Multidimensional Full-Scale Visual Features
Source abstract
Abstract
The accurate identification of coal and rock at the mining face is often hindered by adverse underground imaging conditions, including poor lighting and strong reflectivity. To tackle these issues, this work introduces a recognition framework specifically designed for underground environments, leveraging joint migration and enhancement of multidimensional and full-scale visual representations. A Transformer-based architecture is employed to capture global dependencies within the image and perform reflectance component denoising. Additionally, a multi-scale luminance adjustment module is integrated to merge features across perceptual ranges, mitigating localized brightness anomalies such as overexposure. The model is structured around an encoder–decoder backbone, enhanced by a full-scale connectivity mechanism, a residual attention block with dilated convolution, Res2Block elements, and a composite loss function. These components collectively support precise pixel-level segmentation of coal–rock imagery. Experimental evaluations reveal that the proposed luminance module achieves a PSNR of 21.288 and an SSIM of 0.783, outperforming standard enhancement methods like RetinexNet and RRDNet. The segmentation framework achieves a MIoU of 97.99% and an MPA of 99.28%, surpassing U-Net by 2.21 and 1.53 percentage points, respectively.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Mineral Processing and Grinding · Coal Properties and Utilization · Rock Mechanics and Modeling
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Electrical and Control Engineering, North University of China, Taiyuan 030051, China
State Key Laboratory of Extreme Environment Optoelectronic Dynamic Measurement Technology and Instrument, Taiyuan 030051, China
School of Mechanical and Electrical Engineering, Beijing Institute of Technology, Beijing 100081, China
State Key Laboratory of Coal Mine Disaster Dynamics and Control, Chongqing University, Chongqing 400044, China
Funding
Fund for the National Key Research and Development Program of China · Fund for the Fundamental Research Programs of Shanxi Province · State Key Laboratory of Coal Mine Disaster Dynamics and Control, Chongqing University, Chongqing 400044, China
References (27)
Show source-provided references
1. Coal-rock interface real-time recognition based on the improved YOLO detection and bilateral segmentation network
2. Li, X., Wang, X., Chen, J., and Zhao, H. (2023, January 16–18). The semantic segmentation method of coal rock image based on resnest. Proceedings of the 2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT), Qingdao, China.10.1109/AINIT59027.2023.10212983 ↗
3. Automatic Coal and Rock Interface Recognition Based on Dual-Branch Fusion Network
4. Fusion of Vibration and Image Signals for Coal-Rock Interface Recognition10.1109/JSEN.2023.3333322 ↗
5. Song, C., Xu, C., Tian, M., and Chen, R. (2023, January 22–24). Coal-rock interface image segmentation based on u 2 net model with coordinate attention. Proceedings of the 2023 6th International Conference on Intelligent Autonomous Systems (ICoIAS), Shanghai, China.10.1109/ICoIAS61634.2023.00012 ↗
6. Recognition of coal rock and positioning measurement of coal seam based on faster r-cnn
7. Application of yolov2 in intelligent recognition and location of coal and rock
8. Coal-rock recognition method of fully-mechanized coal mining face based on improved u-net network model
9. A deep convolutional neural network model for intelligent discrimination between coal and rocks in coal mining face10.1155/2020/2616510 ↗
10. Generative adversarial networks based sample generation of coal and rock images
11. Coalrock image recognition method for mining and heading face based on spatial pyramid pooling structure
12. Coal-rock interface image recognition method based on improved deeplabv3+ and transfer learning
13. Coal-rock interface identification method based on improved yolov3 and cubic spline interpolation
14. Coal-rock image recognition method for complex and harsh environment in coal mine using deep learning models10.1109/ACCESS.2023.3300243 ↗
15. Coal rock image recognition method based on improved clbp and receptive field theory10.1002/dug2.12023 ↗
16. Wang, C. (2022). Low-Light Coal-Rock Image Enhancement Based on Hybrid Algorithm and Human-Simulated Intelligent Control of Shearer Mining Height. [Master’s Thesis, North University of China].
17. Wang, Y. (2021). Coal-Rock Boundary Identification Based on Improved Yolov3 and Research on Human-Simulating Intelligentcontrol of Mining Height. [Master’s Thesis, North University of China].
18. Coal-rock interface recognition based on CNN with attention mechanism
19. Intelligent deployment solution for tabling adapting deep learning10.1109/ACCESS.2023.3234075 ↗
20. Feature detection of mineral zoning in spiral slope flow under complex conditions based on improved yolov5 algorithm
21. Research on Coal-Rock Interface Recognition in Intelligent Shearer
22. Zhao, H., Shi, J., Qi, X., Wang, X., and Jia, J. (2017, January 21–26). Pyramid scene parsing network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.660 ↗
23. Wei, C., Wang, W., Yang, W., and Liu, J. (2018). Deep retinex decomposition for low-light enhancement. arXiv.
24. Zhu, A., Zhang, L., Shen, Y., Ma, Y., Zhao, S., and Zhou, Y. (2020, January 6–10). Zero-shot restoration of underexposed images via robust retinex decomposition. Proceedings of the 2020 IEEE International Conference on Multimedia and Expo (ICME), London, UK.10.1109/ICME46284.2020.9102962 ↗
25. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs10.1109/TPAMI.2017.2699184 ↗
26. Segnet: A deep convolutional encoder-decoder architecture for image segmentation10.1109/TPAMI.2016.2644615 ↗
27. Research on intelligent implementation of the beneficiation process of shaking table10.1016/j.mineng.2023.108108 ↗