3D POINT CLOUD DENOISING USING OPTIMISED K-MEANS CLUSTERING AND GRAVITATIONAL FEATURE FUNCTIONS

Fei Xia,∗ Jiale Chen,∗ Yu Pan,∗ Wei Zhang,∗∗ Wantao Zhuo,∗ and Jianliang Mao∗

References

  1. [1] A. Xiao, J. Huang, D. Guan, X. Zhang, S. Lu, and L. Shao,Unsupervised point cloud representation learning with deepneural networks: A survey, IEEE Transactions on PatternAnalysis and Machine Intelligence, 45(9), 2023, 11321–11339.
  2. [2] A.K. Aggarwal, On the use of artificial intelligence techniquesin transportation systems, International Journal of SoftComputing and Engineering 5(5), 2015, 21–24.
  3. [3] A. Kumar, Geo-tagged 3D geometric modeling of urbanstructures by mitigating reflected GPS signals using a laserrange sensor, in Proceeding of the SAI Internatrionl ConferenceIntelligent Computing, Science and Information Conference,Cham, 2024, 396–414.
  4. [4] A.K. Aggarwal, A hybrid approach to GPS improvement inurban canyons, International Journal of Engineering Scienceand Research Technology, 4(10), 2015, 358–363.
  5. [5] C.A. Mueller and A. Birk, Visual object categorization basedon hierarchical shape motifs learned from noisy point clouddecompositions, Journal of Intelligent & Robotic Systems 97(2),2020, 313–338.
  6. [6] T. Zhao, P. Gao, T. Tian, J. Ma, and J. Tian, From noiseaddition to denoising: A self-variation capture network forpoint cloud optimization, IEEE Transactions on Visualizationand Computer Graphics, 30(7), 2024, 3413–3426.
  7. [7] K. Li, Y. Dong, B. Park, T. Koch, and Z. Wan,POE-Net: Expand-Laplacian attention network for large-scale place recognition in point cloud, InternationalJournal of Robotics and Automation, 40(6), 2025, DOI:http://dx.doi.org/10.2316/J.2025.206-1142.
  8. [8] T.D. Dung and G. Capi, Application of neural networks forrobot 3D mapping and annotation using depth image camera,International Journal of Robotics and Automation 37(6), 2022,529–536.
  9. [9] F. Gou, Y. Li, C. Hou, and H. Wang, 3D point cloud globaldenoising algorithm based on different noise characteristics,Measurement Science and Technology, 35(1), 2023, 15032.
  10. [10] F. Zhao, Point cloud denoising algorithm with geometric featurepreserving, Multimedia Systems, 28(5), 2022, 1679–1687.
  11. [11] E. Barnefske and H. Sternberg, Evaluating the quality ofsemantic segmented 3D point clouds, Remote Sensing, 14(3),2022, 446.
  12. [12] X. Hu, X. Wei, and J. Sun, A noising-denoising frameworkfor point cloud upsampling via normalizing flows, PatternRecognition 140, 2023, 109569.
  13. [13] R. Gao, J. Park, X. Hu, S. Yang, and K. Cho, Reflective noisefiltering of large-scale point cloud using multi-position LiDARsensing data, Remote Sensing, 13(16), 2021, 3058.
  14. [14] D. Ma, T. Fu, Y. Yang, K. Cao, J. Fan, D. Xiao, H. Song,Y. Gu, and J. Yang, Fusion-competition framework of localtopology and global texture for head pose estimation, PatternRecognition, 149, 2024, 110285.
  15. [15] D. Chen, Q. Yan, J. Zhou, and Y. Du, An adaptivelocalisation method based on dbscan algorithm in mobile robot,International Journal of Robotics and Automation, 38(4), 2023,323–333.
  16. [16] D.C. Hoang, J.A. Stork, and T. Stoyanov, Voting and attention-based pose relation learning for object pose estimation from3D point clouds, IEEE Robotics and Automation Letters, 7(4),2022, 8980–8987.
  17. [17] A. Ten Pas, M. Gualtieri, K. Saenko, and R. Platt, Grasppose detection in point clouds, The International Journal ofRobotics Research, 36(13–14), 2017, 1455–1473.
  18. [18] P. Song, F. Jin, M. Ji, T. Liang, and Q. Li, Denoising algorithmfor inclined tunnel point cloud data based on irregular contourfeatures, Measurement Science and Technology, 35(9), 2024,95203.
  19. [19] X. Wang, W. Cui, R. Xiong, X. Fan, and D. Zhao, FCNet:Learning noise-free features for point cloud denoising, IEEETransactions on Circuits and Systems for Video Technology,33(11), 2023, 6288–6301.
  20. [20] J. MacQueen, Classification and analysis of multivari-ate observations, in Proceeding of the 5th BerkeleySymposium Mathematics Statistics Probability, 1967,281–297.
  21. [21] Z. Yang and D. Xiao, A systemic point-cloud de-noising andsmoothing method for 3D shape reuse, in Proceeding of the12th Int. Conference Control Automation Robotics & Vision(ICARCV), 2012, 1722–1727.
  22. [22] X. Duan, L. Feng, and X. Zhao, Point cloud denoising algorithmvia geometric metrics on the statistical manifold, AppliedSciences, 13(14), 2023, 8264.
  23. [23] B. Su, J. Ma, Y. Peng, and S. Min, Algorithm for RGBD pointcloud denoising and simplification based on K-means clustering,Journal of System Simulation, 28(10), 2020, 2329–2335.
  24. [24] Y. Li and L. Wei, An outlier removal method from UAV pointcloud data for transmission lines, in Proceeding Computing,Communications and IoT Applications (ComComAp), 2021,238–241.
  25. [25] C. Chen, B. Yang, S. Song, X. Peng, and R Huang, Automaticclearance anomaly detection for transmission line corridorsutilizing UAV-Borne LIDAR data, Remote Sensing, 10(4),2018, 613.
  26. [26] C. Tang, H. Wang, Z. Wang, X. Zeng, H. Yan, and Y. Xiao, Animproved OPTICS clustering algorithm for discovering clusterswith uneven densities, Intelligent Data Analysis, 25(6), 2021,1453–1471.
  27. [27] W. Lian, S. Li, G. Zhang, X. Chen, and Z. Li, Denoisingalgorithm based on local distance weighted statistics for photoncounting LiDAR point data, in Proceeding IGARSS IEEEInternational Geoscience and Remote Sensing Symposium,2019, 8988–8991.
  28. [28] C. Shi, C. Wang, X. Liu, S. Sun, B. Xiao, X. Li, and G. Li,Three-dimensional point cloud denoising via a gravitationalfeature function, Applied Optics, 61(6), 2022, 1331–1343.
  29. [29] H. Chen, Z. Wei, X. Li, Y. Xu, M. Wei, and J. Wang,RePCD-Net: Feature-aware recurrent point cloud denoisingnetwork, International Journal of Computer Vision, 130(3),2022, 615–629.
  30. [30] X. Xu, G. Geng, X. Cao, K. Li, and M. Zhou, TDNet:Transformer-based network for point cloud denoising, AppliedOptics, 61(6), 2022, C80–C88.
  31. [31] M.J. Rakotosaona, V. La Barbera, P. Guerrero, N.J. Mitra,and M. Ovsjanikov, Pointcleannet: Learning to denoise andremove outliers from dense point clouds, Computer GraphicsForum, 39(1), 2020, 185–203.

Important Links:

Go Back