Mine Water Hazard Video Recognition Based on Residual Preprocessing and Temporal–Spatial Descriptors
Source abstract
Abstract
Traditional water hazard monitoring often relies on manual inspection and water level sensors, typically lacking in accuracy and real-time capabilities. However, the method of using video surveillance for monitoring water hazard characteristics can compensate for these shortcomings. Therefore, this study proposes a method to detect water hazards in mines using video recognition technology, combining temporal and spatial descriptors to enhance recognition accuracy. This study employs residual preprocessing technology to effectively eliminate complex underground static backgrounds, focusing solely on dynamic water flow features, thereby addressing the issue of the absence of water inrush samples. The method involves analyzing dynamic water flow pixels and applying an iterative denoising algorithm to successfully remove discrete noise points while preserving connected water flow areas. Experimental results show that this method achieves a detection accuracy of 90.68% for gushing water, significantly surpassing methods that rely solely on temporal or spatial descriptors. Moreover, this method not only focuses on the temporal characteristics of water flow but also addresses the challenge of detection difficulties due to the lack of historical gushing water samples. This research provides an effective technical solution and new insights for future water gushing monitoring in mines.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Rock Mechanics and Modeling · Geophysical Methods and Applications · Geoscience and Mining Technology
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Inner Mongolia Research Institute, China University of Mining and Technology, Beijing 221008, China
Shandong Institute of Geophysical & Geochemical Exploration, Jinan 250013, China
National Engineering Research Center of Coal Mine Water Hazard Controlling, China University of Mining and Technology, Beijing 100083, China
Key Laboratory of Mine Water Control and Resources Utilization, National Mine Safety Administration, China University of Mining and Technology, Beijing 100083, China
School of Science, China University of Mining and Technology, Beijing 100083, China
College of Geoscience and Surveying Engineering, China University of Mining and Technology, Beijing 100083, China
Funding
Major Research Instrument Development Project of the National Natural Science Foundation of China · Shandong Province Postdoctoral Innovation Seed Cultivation Program · Scientific and technological research project of Shandong Bureau of Geology and Mineral Resources Exploration and Development · Coal-Major Project · China National Scientific and Technical Support Program · China National Natural Science Foundation · New Patten Research and Development Institutions of ordos
References (31)
Show source-provided references
1. Damage characteristics and mechanism of a strong water inrush disaster at the Wangjialing coal mine, Shanxi province, China
2. Potentially toxic elements (PTEs) associated with asbestos chrysotile, tremolite and actinolite in the Calabria region (Italy)10.1016/j.chemgeo.2020.119896 ↗
3. A cloud-based service for emergency evacuation of mine water inrush accidents10.1002/cpe.6125 ↗
4. Optimal location of water level sensors for monitoring mine water inrush based on the set covering model10.1038/s41598-021-82121-7 ↗
5. Image recognition of mine water inrush based on bilinear convolutional neural network with few-shot learning10.1021/acsomega.3c09735 ↗
6. Quantification of water inflow in rock tunnel faces via convolutional neural network approach10.1016/j.autcon.2020.103526 ↗
7. Source Discrimination of Mine Water Inrush Based on Spectral Data and EGA–PNN Model: A Case Study of Huangyuchuan mine10.1007/s10230-021-00840-9 ↗
8. Visualization Analysis and Progress of Mine Water Inrush Disaster-Related Research10.1007/s10230-022-00876-5 ↗
9. Coal-rock image recognition method for complex and harsh environment in coal mine using deep learning models10.1109/ACCESS.2023.3300243 ↗
10. Neural texture synthesis and style transfer of coal-rock images in coal mine heading faces using very deep convolutional networks10.1016/j.tust.2024.106342 ↗
11. Liu, X., Jing, W., Zhou, M., and Li, Y. (2019). Multi-Scale Feature Fusion for Coal-Rock Recognition Based on Completed Local Binary Pattern and Convolution Neural Network. Entropy, 21.10.3390/e21060622 ↗
12. Coal gangue image recognition model based on improved U−Net and top coal caving control
13. Coal/gangue recognition using convolutional neural networks and thermal images10.1109/ACCESS.2020.2990200 ↗
14. Detection of coal content in gangue via image analysis and particle swarm optimization–support vector machine10.1080/19392699.2021.1932842 ↗
15. Liang, Y., Liu, Y., Lu, C., Cui, D., Yang, J., and Zhou, R. (2024). Research on Intelligent Monitoring and Protection Equipment of Vital Signs of Underground Personnel in Coal Mines. Sensors, 25.10.3390/s25010063 ↗
16. Inspection routing problem for coal mine safety personnel in underground mines10.1016/j.cie.2019.03.003 ↗
17. Hazard identification, risk assessment and management of industrial system: Process safety in mining industry10.1016/j.ssci.2022.105863 ↗
18. Deep learning in mining biological data10.1007/s12559-020-09773-x ↗
19. Predicting mine water inrush accidents based on water level anomalies of borehole groups using long short-term memory and isolation forest10.1016/j.jhydrol.2022.128813 ↗
20. A study on a water-inrush incident at Laohutai coalmine10.1016/j.ijrmms.2012.12.002 ↗
21. Meng, S., Zeng, Y., Wu, Q., Wang, L., Yang, L., Bao, H., Zhang, Y., Yang, G., Du, X., and Pang, K. (2023). Exploration of Coal-Water Dual Resource Synergistic Mining System under the Derived Hydrodynamic Water Inrush Mode. Res. Sq.10.21203/rs.3.rs-2941646/v1 ↗
22. Water leakage image recognition of shield tunnel via learning deep feature representation10.1016/j.jvcir.2019.102708 ↗
23. Water detection through spatio-temporal invariant descriptors10.1016/j.cviu.2016.04.003 ↗
24. Face recognition using local binary patterns (LBP)
25. A global geometric framework for nonlinear dimensionality reduction10.1126/science.290.5500.2319 ↗
26. Fourier transform-based scalable image quality measure10.1109/TIP.2012.2197010 ↗
27. Automatic recognition of SEM microstructure and phases of steel using LBP and random decision forest operator10.1016/j.measurement.2019.107224 ↗
28. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision10.1109/TPAMI.2004.60 ↗
29. Type classification and main characteristics of mine water disasters
30. Episode-constrained cross-validation in video concept retrieval10.1109/TMM.2009.2017619 ↗
31. Rens, E.G., and Edelstein-Keshet, L. (2019). From energy to cellular forces in the Cellular Potts Model: An algorithmic approach. PLoS Comput. Biol., 15.10.1101/601781 ↗