Ore Rock Fragmentation Calculation Based on Multi-Modal Fusion of Point Clouds and Images
Source abstract
Abstract
The accurate calculation of ore rock fragmentation is important for achieving the autonomous mining operation of mine excavators. However, a single mode cannot accurately calculate the ore rock fragmentation due to the low resolution of the point cloud mode and the lack of spatial position information of the image mode. To solve this problem, we propose an ore rock fragmentation calculation method (ORFCM) based on the multi-modal fusion of point clouds and images. The ORFCM makes full use of the advantages of multi-modal data, including the fine-grained object segmentation of images and spatial location information of point clouds. To solve the problem of image under-segmentation, we propose a multiscale adaptive edge-detection method based on an innovative standard deviation map to enhance the weak edges. Furthermore, an improved marked watershed segmentation algorithm is proposed to solve the problem of low segmentation accuracy caused by excessive noise of the gradient map and weak edges submerged. Experiments demonstrate that ORFCM can accurately calculate ore rock fragmentation in the local excavation area without relying on external markers for pixel calibration. The average error of the equivalent diameter of ore rock blocks is 0.66 cm, the average error of the elliptical long diameter is 1.42 cm, and the average error of the elliptical short diameter is 1.06 cm, which can effectively meet practical engineering needs.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Mineral Processing and Grinding · 3D Surveying and Cultural Heritage · Image and Object Detection Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Mechanical and Electrical Engineering, Henan University of Science and Technology, Luoyang 471023, China
School of Control Science and Engineering, Dalian University of Technology, Dalian 116024, China
Funding
National Natural Science Foundation of China · Major Science and Technology Project of Henan Province · Joint Fund of Science and Technology Research and Development Plan of Henan Province · Key Research Projects of Higher Education Institutions of Henan Province · Natural Science Foundation of Liaoning Province · Science and Technology Major Project of Shanxi Province
References (28)
Show source-provided references
1. Measurement of size distribution of blasted rock using digital image processing
2. A Novel Coal-Rock Recognition Method for Coal Mining Working Face Based on Laser Point Cloud Data10.1109/TIM.2021.3108228 ↗
3. Amankwah, A., and Aldrich, C. (2011, January 19–20). Automatic ore image segmentation using mean shift and watershed transform. Proceedings of the 21st International Conference Radioelektronika 2011, Brno, Czech Republic.10.1109/RADIOELEK.2011.5936391 ↗
4. Zhang, G., Li, M., and Zhan, Y. (2017, January 29–31). Ore image thresholding segmentation using double windows with fisher discrimination. Proceedings of the 2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD), Guilin, China.10.1109/FSKD.2017.8393208 ↗
5. Wang, R., Zhang, W., and Shao, L. (2018). Research of Ore Particle Size Detection Based on Image Processing, Springer.10.1007/978-981-10-6499-9_48 ↗
6. A method of blasted rock image segmentation based on improved watershed algorithm10.1038/s41598-022-11351-0 ↗
7. Distribution characteristics of fragments size and optimization of blasting parameters under blasting impact load in open-pit mine10.1109/ACCESS.2019.2942968 ↗
8. Fragment size estimation without image segmentation10.1179/174313108X268312 ↗
9. Liu, Y., Sun, J.H., Yu, H.Y., Wang, Y.Y., and Zhou, X.K. (2020). An Improved Grey Wolf Optimizer Based on Differential Evolution and OTSU Algorithm. Appl. Sci., 10.10.3390/app10186343 ↗
10. Ore image thresholding using bi-neighbourhood Otsu’s approach10.1049/el.2010.2962 ↗
11. Determining the fragmented rock size distribution using textural feature extraction of images10.1016/j.powtec.2018.10.006 ↗
12. Predicting rock size distribution in mine blasting using various novel soft computing models based on meta-heuristics and machine learning algorithms10.1016/j.gsf.2020.11.005 ↗
13. Yuan, L., and Duan, Y. (2018). A Method of Ore Image Segmentation Based on Deep Learning, Springer.10.1007/978-3-319-95957-3_53 ↗
14. A neural network-based soft sensor for particle size distribution using image analysis10.1016/j.powtec.2011.06.013 ↗
15. Prediction of particle size distribution curves of dump materials using convolutional neural networks
16. He, K., Gkioxari, G., and Dollár, P. (2017, January 22–29). Mask r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.322 ↗
17. Xiao, D., Liu, X., and Le, B. (2020). An ore image segmentation method based on RDU-Net model. Sensors, 17.10.3390/s20174979 ↗
18. DUNet: A deformable network for retinal vessel segmentation10.1016/j.knosys.2019.04.025 ↗
19. Matthew, J. (2013, January 26–28). Automated image segmentation and analysis of rock piles in an open-pit mine. Proceedings of the 2013 International Conference on Digital Image Computing: Techniques and Applications (DICTA), Hobart, TAS, Australia.
20. Measuring blast fragmentation at Esperanza mine using 3D laser scanning10.1179/1743286314Y.0000000076 ↗
21. Application of laser scanning to measure fragmentation in underground mines
22. Practical measurement of size distribution of blasted rocks using LiDAR scan data10.1007/s00603-020-02181-5 ↗
23. Multiscale adaptive edge detector for images based on a novel standard deviation map10.1109/TIM.2021.3083888 ↗
24. A flexible new technique for camera calibration10.1109/34.888718 ↗
25. Calibration of a 3D laser rangefinder and a camera based on optimization solution10.3934/jimo.2019119 ↗
26. A computational approach to edge detection10.1109/TPAMI.1986.4767851 ↗
27. Edge drawing: A combined real-time edge and segment detector10.1016/j.jvcir.2012.05.004 ↗
28. Zhang, H., Wu, C., and Zhang, L. (2020, January 25–28). A novel centroid update approach for clustering-based superpixel methods and superpixel-based edge detection. Proceedings of the 2020 IEEE International Conference on Image Processing (ICIP), Abu Dhabi, United Arab Emirates.10.1109/ICIP40778.2020.9191282 ↗