ORIGINAL PAPER
Ore crushing position study method based on stacked ore point cloud instance segmentation
1
Jiangxi Mining and Metallurgical Engineering Research Center, China
2
School of Mechanical and Electrical Engineering, Jiangxi University of Science and Technology
Submission date: 2025-04-06
Final revision date: 2025-05-25
Acceptance date: 2025-05-29
Publication date: 2026-03-31
Corresponding author
Gospodarka Surowcami Mineralnymi – Mineral Resources Management 2026;42(1):45-68
KEYWORDS
TOPICS
ABSTRACT
To address the technical challenges in industrial applications involving stacked ores – particularly the difficulties in distinguishing individual particles resulting from mutual occlusion and geometric irregularities, and the limitations of conventional approaches in precisely determining optimal crushing positions – this study develops a multimodal feature fusion framework integrating ore segmentation with intelligent crushing position determination. Instance Segmentation Level: a hierarchical segmentation framework is constructed by integrating super-voxel clustering with 3D point cloud surface concavity-convexity analysis. To address edge segmentation optimization, a curvature-constrained region growing algorithm is introduced. Furthermore, an adhesion-aware concavity-convexity evaluation function is established to achieve precise separation of adherent ores, effectively mitigating the over-segmentation issues inherent in traditional Euclidean clustering methods when handling complex stacked scenarios. Positional Decision-Making Level: we propose a crushing point localization method incorporating multi-scale geometric feature fusion. Poisson surface reconstruction is employed to construct a continuous geometric model of the ore surface. This is combined with an enhanced RANSAC plane detection algorithm to identify optimal crushing planes, followed by a comprehensive analysis to determine crushing direction vectors. Experimental results demonstrate that the method can effectively segment individual ores in complex stacking scenarios and optimize crushing position determination based on geometric features, providing reliable technical support for automated crushing operations.
CONFLICT OF INTEREST
The Authors have no conflict of interest to declare.
METADATA IN OTHER LANGUAGES:
Polish
Metoda badania położenia kruszenia rudy oparta na segmentacji instancji chmury punktów ułożonych w stosy
ułożone rudy, segmentacja instancji, klasteryzacja hiperwokseli, pozycja kruszenia
Aby sprostać wyzwaniom technicznym w zastosowaniach przemysłowych z rudami ułożonymi w stosy – w szczególności trudnościom w rozróżnianiu poszczególnych cząstek, wynikającym ze wzajemnej okluzji i nieregularności geometrycznych, a także ograniczeniom konwencjonalnych metod w precyzyjnym określaniu optymalnych pozycji kruszenia – w niniejszym badaniu opracowano multimodalny model łączenia cech, integrujący segmentację rudy z inteligentnym określaniem pozycji kruszenia. Poziom segmentacji instancji: hierarchiczny model segmentacji został skonstruowany poprzez integrację klastrowania superwokseli z analizą wklęsłości i wypukłości powierzchni chmury punktów 3D. Aby zoptymalizować segmentację krawędzi, wprowadzono algorytm wzrostu regionu z ograniczeniami krzywizny. Ponadto opracowano funkcję oceny wklęsłości i wypukłości uwzględniającą adhezję, aby uzyskać precyzyjną separację przylegających rud, skutecznie łagodząc problemy z nadsegmentacją, nieodłącznie związane z tradycyjnymi euklidesowymi metodami klasteryzacji podczas obsługi złożonych scenariuszy ułożenia warstw. Poziom podejmowania decyzji pozycyjnych: proponujemy metodę lokalizacji punktu kruszenia, wykorzystującą wieloskalową fuzję cech geometrycznych. Rekonstrukcja powierzchni Poissona została wykorzystana do zbudowania ciągłego modelu geometrycznego powierzchni rudy. Jest ona połączona z ulepszonym algorytmem detekcji płaszczyzn RANSAC w celu identyfikacji optymalnych płaszczyzn kruszenia. Następnie przeprowadzana jest kompleksowa analiza w celu określenia wektorów kierunku kruszenia. Wyniki eksperymentalne pokazują, że metoda ta może skutecznie segmentować poszczególne rudy w złożonych scenariuszach ułożenia warstw i optymalizować określanie pozycji kruszenia w oparciu o cechy geometryczne, zapewniając niezawodne wsparcie techniczne dla zautomatyzowanych operacji kruszenia.
REFERENCES (27)
1.
Cheng et al. 2024 – Cheng, X., Liu, S., Zhou, J. et al. 2024. FDG-PointNet: fusion of dense connectivity and Gaussian distance for 3D target detection. Journal of Jilin University (Engineering Edition).
2.
Dreier et al. 2025 – Dreier, A.,Tobies, A., Kuhlmann, H., Klingbeil, L. 2025. Stone instance segmentation of rubble masonry based on laser scanning point clouds. Measurement 242(PB), https://doi.org/10.1016/j.meas....
3.
Daif, H. and Marzouk, M., 2025. Point cloud classification and part segmentation of steel structure elements. Neural Computing and Applications 37(6), https://doi.org/10.1007/s00521....
4.
Du et al. 2025 – Du, J., Cai, G., Wang, Z., Jinhe, S., Huang, M., Zelek, J., Marcato Junior, J. and Li, J. 2025. 2025. MTCloud: Multi-type convolutional linkage network for point cloud instance segmentation. Expert Systems With Applications 270(2), https://doi.org/10.1016/j.eswa....
5.
Fang et al. 2025 – Fang, Z., Zhuang, C., Lu, Z., Wang, Y., Liu, L. and Xiao, J. 2025. BGPSeg: Boundary-Guided Primitive Instance Segmentation of Point Clouds. IEEE Trans Image Process, https://doi.org/10.1109/tip.20....
6.
Ghahremani et al. 2021 – Ghahremani M., Williams, K., Corke, F.M.K., Tiddeman, B., Liu, Y. and Doonan, J.H. 2021. Deep Segmentation of Point Clouds of Wheat. Frontiers in plant science 12, https://doi.org/10.3389/fpls.2....
7.
Guo et al. 2024 – Guo, L., He, Y., Du, X. et al. 2024. Lidar volume measurement method based on visual correction. Journal of Instrumentation 1–12.
8.
Huang et al. 2018 – Huang, Q., Wang, W. and Neumann, U. 2018. Recurrent slice networks for 3d segmentation of point clouds. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), https://doi.org/10.1109/CVPR.2....
9.
Huang et al. 2023 – Huang H., Wen, X., Yang, L., Wang, H.F., Gao, T. and Ru, F. 2023. K-mean complementary iterative clustering optimization based on the crazy hunting vulture algorithm. Journal of Zhejiang University (Engineering Edition) 57(11), https://doi.org/10.3785/j.issn....
10.
Huang et al. 2025 – Huang, H., Bu, Y., Xu, H. and Wang, X. 2025. Point Cloud Segmentation Algorithm Based on Contrastive Learning and Label Mining. Journal of Computer Research and Development 62(1), https://dx.doi.org/10.7544/iss....
11.
Hugues et al. 2019 – Hugues T., Qi, C.R., Deschaud, J.E., Marcotegui, B., Goulette, F. and Guibas, L.J. 2019. KPConv: Flexible and deformable convolution for point clouds. IEEE/CVF International Conference on Computer Vision (ICCV), https://doi.org/10.48550/arXiv....
12.
Jiang et al. 2018 – Jiang, M., Wu, Y., Zhao, T., Zhao, Z. and Lu, C. 2018. Pointsift: A sift-like network module for 3d point cloud semantic segmentation. Computer Vision and Pattern Recognition (cs.CV), https://doi.org/10.48550/arXiv....
13.
Ma et al. 2020 – Ma, X., Xue, H., Zhou, Y. et al. 2020. Point cloud segmentation of sheep body and measurement of body size parameters based on improved regional growth method. Journal of China Agricultural University 25(03), pp. 99–105 (in Chinese with English abstract).
14.
Li et al. 2025 – Li, Y., Zhang, Z., Li, H. and Zhang, W. 2025. DPPCN: density and position-based point convolution network for point cloud segmentation. Pattern Analysis and Applications 28(2), https://doi.org/10.1007/s10044....
15.
Qi et al. 2017a – Qi, C.R., Su, H., Kaichun, M. and Guibas, L.J. 2017a. Pointnet: Deep learning on point sets for 3d classification and segmentation. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 652–660, https://doi.org/10.1109/CVPR.2....
16.
Qi et al. 2017b – Qi, C.R., Yi, L., Su, H. and Guibas, L. 2017b. Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems 30, https://doi.org/10.48550/arXiv....
17.
Shahraki et al. 2025 – Shahraki, M., Elamin, A. and El-Rabbany, A. 2025. SAMNet++: A Segment Anything Model forSupervised 3D Point Cloud SemanticSegmentation. Remote Sensing 17(7), https://doi.org/10.3390/rs1707....
18.
Wang et al. 2019 – Wang, Y., Sun, Y., Liu, Z., Sarma, S.E., Bronstein, M.M. and Solomon, J.M. 2019. Dynamic graph cnn for learning on point clouds. ACM Transactions on Graphics (TOG) 38(5), https://doi.org/10.1145/332636....
19.
Wang et al. 2023 – Wang, J., Jiang, Y. and Wang, L. 2023. Segmentation of building roof surfaces in airborne LiDAR point clouds based on voxel growth. Journal of Geo-Information Science 25(12), pp. 2468–2486.
20.
Wu et al. 2020 – Wu, W., Qi, Z. and Li, F. 2020. PointConv: Deep convolutional networks on 3D Point Clouds. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), https://doi.org/10.1109/CVPR.2....
21.
Wu et al. 2023 – Wu, W.G., Tian, S.Y., Zhang, Z.Y. and Zhang B. 2023. Research on semantic segmentation method for uneven features of unpaved roads. Automotive Engineering 45(8), https://doi.org/10.19562/j.chi....
22.
Yang et al. 2024 – Yang, W., Pei, S., Liu, Y. et al. 2024. Research on semantic segmentation of point cloud at critical parts of transmission lines based on improved PointNet++. High Voltage Technology 1–14.
23.
Zhao, Z.B. 2023. Construction of point cloud dataset for typical mechanical parts. University of Electronic Science and Technology.
24.
Zhao et al. 2025 – Zhao, F., Huang, H., Xiao, N., Yu, J. and Geng, G. 2025. A point cloud segmentation algorithm based on multi-feature training and weighted random forest. Measurement Science and Technology 36(1), https://doi.org/10.1088/1361-6....
25.
Zhu et al. 2023 – Zhu, J., Bian, Y., Han, F. et al. 2023. Research on binocular active vision point cloud target detection based on improved Euclidean clustering algorithm. Optoelectronics (Laser) 34(12), pp. 1288–1297.
26.
Zhu et al. 2024 – Zhu, A., Fei-Peng Da, F.P. and Gai, S.Y. 2024. Three-dimensional point cloud recognition and segmentation sensitive to fused features. Journal of Xi’an Jiaotong University 5.
27.
Zolotarev et al. 2025 – Zolotarev, F., Eerola, T. and Kauppi, T. 2025. Deep Unsupervised Segmentation of Log Point Clouds. Computer Vision and Pattern Recognition (cs.CV), https://doi.org/10.48550/arXiv....
| eISSN: | 2299-2324 |
| ISSN: | 0860-0953 |
© 2006-2026 Journal hosting platform by Bentus
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
