ORIGINAL PAPER
Adaptive ore point cloud filtering algorithm based on the K-nearest neighbor
1
Jiangxi Mining and Metallurgical Engineering Research Center
2
School of Mechanical and Electrical Engineering, Jiangxi University of Science and Technology Ganzhou, Jiangxi Province
These authors had equal contribution to this work
Submission date: 2024-10-30
Final revision date: 2025-01-17
Acceptance date: 2025-05-13
Publication date: 2025-06-11
Gospodarka Surowcami Mineralnymi – Mineral Resources Management 2025;41(2):197-211
KEYWORDS
TOPICS
Rational and efficient development and utilization of mineral resourcesEffective mineral deposits exploitationPreparation and processing of mineral raw materialsRational use of mineral raw materials
ABSTRACT
A robotic arm can determine the crushing center of ore using point clouds reconstructed by a binocular camera. However, noise in the original point cloud creates ambiguity, complicating the determination process. To address this, an efficient noise filtering and smoothing algorithm for point clouds is proposed. First, the topological relationships among the point clouds are established using a K-D tree, enabling neighborhood selection and query for each point. The density and density variance for each neighborhood are then calculated via the K-nearest neighbor density filtering method. Clustering is applied to determine the average density, and the optimal K value is adaptively obtained based on both the density variance and cluster densities with assigned weights. The local outlier factor is subsequently calculated using this K value, and noise points are filtered out by setting an outlier factor threshold. Based on the enhanced K-nearest neighbor density filtering algorithm, the experimental results demonstrate that this method achieves a denoising precision of 95.68%, representing an improvement of 55.06% over the traditional Radius filtering method and 27.5% over the statistical filtering method. Additionally, the noise recall rate reaches 99.92%, and the original retention rate is 94.17%, showcasing superior filtering performance while preserving data integrity. These advancements provide a reliable technical foundation for subsequent ore crushing and point cloud data processing tasks.
FUNDING
This work was supported by the General Projects of R&D Program of Ganzhou (No. 202101124911).
CONFLICT OF INTEREST
The Authors have no conflict of interest to declare.
METADATA IN OTHER LANGUAGES:
Polish
Adaptacyjny algorytm filtrowania chmury punktów rudy oparty na najbliższych sąsiadach K
widzenie stereoskopowe, chmura punktów rudy, filtrowanie, K najbliższych sąsiadów
Manipulator może określić środek kruszenia rudy za pomocą chmur punktów rekonstruowanych przez kamerę binokularną. Jednak szumy w oryginalnej chmurze punktów powodują niejednoznaczność, co komplikuje proces określania środka kruszenia. Aby temu zaradzić, zaproponowano wydajny algorytm filtrowania i wygładzania szumów w chmurach punktów. Najpierw za pomocą drzewa K-D ustalane są relacje topologiczne między punktami chmury, co umożliwia wybór i zapytania dotyczące sąsiedztwa każdego punktu. Następnie dla każdego sąsiedztwa obliczana jest gęstość i wariancja gęstości za pomocą metody filtrowania gęstości najbliższych sąsiadów K. Zastosowano klasteryzację w celu określenia średniej gęstości, a optymalna wartość K jest adaptacyjnie uzyskiwana na podstawie zarówno wariancji gęstości, jak i gęstości klastrów z przypisanymi wagami. Następnie obliczany jest lokalny współczynnik odstępstwa przy użyciu tej wartości K, a punkty szumów są odfiltrowywane poprzez ustawienie progu współczynnika odstępstwa. Na podstawie udoskonalonego algorytmu filtrowania gęstości najbliższych sąsiadów K wyniki eksperymentów wykazują, że metoda ta osiąga precyzję odszumiania na poziomie 95,68%, co stanowi poprawę o 55,06% w porównaniu z tradycyjną metodą filtrowania promienia oraz o 27,5% w porównaniu z metodą filtrowania statystycznego. Ponadto wskaźnik odzyskiwania szumów osiąga 99,92%, a wskaźnik zachowania oryginalnych danych wynosi 94,17%, co pokazuje doskonałą wydajność filtrowania przy jednoczesnym zachowaniu integralności danych. Te osiągnięcia stanowią niezawodną podstawę techniczną do dalszych zadań związanych z kruszeniem rudy oraz przetwarzaniem danych chmury punktów.
REFERENCES (19)
1.
Axelsson, P. 2000. DEM generation from laser scanner data using adaptive TIN models. International Archives of Photogrammetry and Remote Sensing 33(4), pp. 110–117.
2.
Cai et al. 2021 – Cai, M., Li, P., Tan, W. and Ren, F. 2021. Key engineering technologies to achieve green, intelligent, and sustainable development of deep metal mines in China. Engineering 7(11), pp. 1513–1517, DOI: 10.1016/j.eng.2021.07.010.
3.
Chae et al. 2017 – Chae, D.K., Lee, S.C., Lee, S.Y. and Kim, S.W. 2017. On identifying k-nearest neighbors in neighborhood models for efficient and effective collaborative filtering. Neurocomputing, 278, pp. 134–143, DOI: 10.1016/j.neucom.2017.06.081.
4.
Chen et al. 2021 – Chen, C., Guo, J., Wu, H., Li, Y. and Shi, B. 2021. Performance comparison of filtering algorithms for high-density airborne LiDAR point clouds over complex LandScapes. Remote Sensing 13(14), DOI: 10.3390/rs13142663.
5.
Chen et al. 2023 – Chen, S., Wang, J., Pan, W., Gao, S., Wang, M. and Lu, X. 2023. Towards uniform point distribution in feature-preserving point cloud filtering. Computational Visual Media 9(2), pp. 249–263, DOI: 10.1007/s41095-022-0278-4.
6.
Han et al. 2017 – Han, X.F., Jin, J.S., Wang, M.J., Jiang, W., Gao, L. and Xiao, L. 2017. A review of algorithms for filtering the 3D point cloud. Signal Processing Image Communication 57, pp. 103–112, DOI: 10.1016/j.image.2017.05.009.
7.
Han et al. 2018 – Han, X.F., Jin, J.S., Wang, M.J. and Jiang, W. 2018. Guided 3D point cloud filtering. Multimedia Tools and Applications 77, pp. 17397–17411, DOI: 10.1007/s11042-017-5310-9.
8.
Jia et al. 2019 – Jia, C.C., Wang, C.J., Yang, T., Fan, B.H. and He, F.G. 2019. A 3D point cloud filtering algorithm based on surface variation factor classification. Procedia Computer Science 154, pp. 54–61, DOI: 10.1016/j.procs.2019.06.010.
9.
Li et al. 2019 – Li, X., Chen, Z., Chen, J. and Zhu, H. 2019. Automatic characterization of rock mass discontinuities using 3D point clouds. Engineering Geology 259, DOI: 10.1016/j.enggeo.2019.05.008.
10.
Li et al. 2023 – Li, Y., Peng, P., Li, H., Xie, J., Liu, L. and Xiao, J. 2023. Drilling Path Planning of Rock-Drilling Jumbo Using a Vehicle-Mounted 3D Scanner. Sustainability 15(12), DOI: 10.3390/su15129737.
11.
Lu et al. 2020 – Lu, D., Lu, X., Sun, Y. and Wang, J. 2020. Deep feature-preserving normal estimation for point cloud filtering. Computer-Aided Design 125, DOI: 10.1016/j.cad.2020.102860.
12.
Moreno, C. and Li, M. 2016. A comparative study of filtering methods for point clouds in real-time video streaming. Proceedings of the World Congress on Engineering and Computer Science 1, pp. 388–393).
13.
Pingel et al. 2013 – Pingel, T.J., Clarke, K.C. and McBride, W.A. 2013. An improved simple morphological filter for the terrain classification of airborne LIDAR data. ISPRS Journal of Photogrammetry and Remote Sensing 77, pp. 21–30, DOI: 10.1016/j.isprsjprs.2012.12.002.
14.
Wang et al. 2022 – Wang, J., Jiang, J., Lu, X. and Wang, M. 2022. Rethinking point cloud filtering: A non-local position based approach. Computer-Aided Design, 144, DOI: 10.1016/j.cad.2021.103162.
15.
Weales, D. 2018. Design of a Bin-picking System for Large Objects with High Clutter and Occlusion (Doctoral dissertation, University of Guelph).
16.
Yang et al. 2024 – Yang, L., Yang, H., Liu, Y. and Cao, C. 2024. Stereo matching algorithm for mineral images based on improved BT-Census. Minerals Engineering 216, DOI: 10.1016/j.mineng.2024.108905.
17.
Zeng et al. 2023 – Zeng, N., Li, J., Zhang, Y., Gao, X. and Luo, L. 2023. Scattered Train Bolt Point Cloud Segmentation Based on Hierarchical Multi-Scale Feature Learning. Sensors 23(4), DOI: 10.3390/s23042019.
18.
Zeybek, M. and Şanlıoğlu, İ. 2019. Point cloud filtering on UAV based point cloud. Measurement 133, pp. 99–111, DOI: 10.1016/j.measurement.2018.10.013.
19.
Zhang et al. 2016 – Zhang, W., Qi, J., Wan, P., Wang, H., Xie, D., Wang, X. and Yan, G. 2016. An easy-to-use airborne LiDAR data filtering method based on cloth simulation. Remote sensing 8(6), DOI: 10.3390/rs8060501.
| eISSN: | 2299-2324 |
| ISSN: | 0860-0953 |
© 2006-2025 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.
