Point Cloud Simplification Algorithm Based on Improved Bald Eagle Search and K-Means Clustering Iteration

NIU Hongxia; LI Fuli

doi:10.7652/xjtuxb202402018

您当前的位置：

首页 >

文章列表页 >

Point Cloud Simplification Algorithm Based on Improved Bald Eagle Search and K-Means Clustering Iteration

更新时间：2025-05-13

- Point Cloud Simplification Algorithm Based on Improved Bald Eagle Search and K-Means Clustering Iteration
- Vol. 58, Issue 2, Pages: 172-183(2024)
- 作者机构：
  
  1. 兰州交通大学自动化与电气工程学院,兰州,730070
  2. 兰州交通大学甘肃省高原交通信息工程及控制重点实验室,兰州,730070
  3. 兰州交通大学光电技术与智能控制教育部重点实验室,兰州,730070
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb202402018
  CLC： TP391
- Online First：10 February 2024，
  
  Published：2024
- 稿件说明：
移动端阅览
NIU Hongxia, LI Fuli. Point Cloud Simplification Algorithm Based on Improved Bald Eagle Search and K-Means Clustering Iteration[J]. 2024, 58(2): 172-183.
DOI：

NIU Hongxia, LI Fuli. Point Cloud Simplification Algorithm Based on Improved Bald Eagle Search and K-Means Clustering Iteration[J]. 2024, 58(2): 172-183. DOI： 10.7652/xjtuxb202402018.

摘要

针对激光雷达的固有特性和复杂环境易造成点云噪声和冗余点云

以及传统点云简化算法忽略了点云固有特征等问题

提出了一种基于改进秃鹰搜索和K均值聚类(KMC)混合迭代的点云简化算法(IBESSA)。首先

通过秃鹰搜索(BES)算法迭代阶段的竞争融合(CFBES)

提高其收敛速度和优化精度; 其次

通过CFBES和KMC算法的混合迭代

实现了点云数据的聚类; 然后

在k近邻(k-NN)实现点云簇密度估计的基础上

结合香农熵实现点云信息量化; 最后

删除信息量化值小于阈值的聚类簇

完成点云数据简化。使用UCI国际标准数据集和斯坦福点云数据集分别对CFBES-KMC算法的聚类效果及点云的简化效果进行验证

结果表明:与改进飞蛾扑火的K均值交叉迭代、K-means++、模糊C均值聚类算法的聚类效果相比

CFBES-KMC算法的聚类准确率分别提高了1.02%、12.31%、14.72%; 在斯坦福点云数据集上

IBESSA算法在有效滤除冗余点云的基础上保留了原本点云的细节和形状特征

不失为一种高效的点云简化算法。

Abstract

Aiming at the inherent characteristics of lidar and the point cloud noise and redundant point cloud that are easily caused in complex environment

as well as the problem that the inherent features of point cloud are often ignored in conventional point cloud simplification algorithms

a point cloud simplification algorithm based on improved bald eagle search and K-means clustering(KMC)hybrid iteration(IBESSA)is proposed. Firstly

the convergence is accelerated and optimization accuracy is upgraded through the competitive fusion in the BES iteration stage(CFBES). Secondly

the point cloud data is clustered by the hybrid iteration of CFBES and KMC algorithm. Then

based on the implementation of point cloud density estimation with k-nearest neighbors(k-NN)

point cloud information quantization is achieved combined Shannon entropy. Finally

the cluster with the information quantization value less than the threshold is deleted to complete the simplification of point cloud data. UCI international standard dataset and Stanford point cloud dataset are used to verify the clustering effect and point cloud simplification effect of CFBES-KMC. The results show that compared with hybrid iterative K-means clustering with improved moth-flame optimization

K-means++ and fuzzy C-means clustering algorithm

the clustering accuracy of CFBES-KMC is improved by 1.02%

12.31%

14.72% respectively. On the Stanford point cloud dataset

the IBESSA algorithm effectively filters out redundant point clouds while preserving the details and shape features of the original point cloud

which means it is an efficient point cloud simplification algorithm.

关键词

Keywords

references

YUAN Hui, ZHANG Dexiang, WANG Weiwei,et al. A sampling-based 3D point cloud compression algorithm for immersivecommunication [J]. Mobile Networks and Applications, 2020, 25(5): 1863-1872.

陈辉, 黄晓铭, 刘万泉. 基于动态网格k邻域搜索的激光点云精简算法 [J]. 控制与决策, 2020, 35(12): 2986-2992.

CHEN Hui, HUANG Xiaoming, LIU Wanquan.Laser point cloud simplification algorithm based on dynamic grid k-nearestneighbors searching [J]. Control and Decision, 2020, 35(12): 2986-2992.

王建强, 樊彦国, 李国胜, 等. 基于多参数k-means聚类的自适应点云精简 [J]. 激光与光电子学进展, 2021, 58(6): 167-175.

WANG Jianqiang, FAN Yanguo, LI Guosheng, etal. Adaptive point cloud reduction based on multi parameter k-means clustering[J]. Laser Optoelectronics Progress, 2021, 58(6): 167-175.

DING Xiaoying, LIN Weisi, CHENZhenzhong, et al. Point cloud saliency detection by local and global featurefusion [J]. IEEE Transactions on Image Processing, 2019, 28(11): 5379-5393.

PAULY M, GROSS M, KOBBELT L P.Efficient simplification of point-sampled surfaces [C]//2002 Proceedings of theIEEE Visualization(VIS). Boston, MA, USA: IEEE, 2002: 163-170.

XUAN Wei, HUA Xianghong, CHEN Xijiang,et al. A new progressive simplification method for point cloud using localentropy of normal angle [J]. Journal of the Indian Society of Remote Sensing,2018, 46(4): 581-589.

MAHDAOUI A, SBAI E H. 3D point cloudsimplification based on k-nearest neighbor and clustering [J]. Advances inMultimedia, 2020, 2020: 8825205.

MA Tong, SHEN Wei. Notice of removal:research on a hybrid k-means clustering algorithm based on improved geneticalgorithm [C]//2018 International Computers, Signals and SystemsConference(ICOMSSC). Piscataway, NJ, USA: IEEE, 2018: 228-233.

HUA Chun. A quantum-inspired particleswarm optimization k-means++ clustering algorithm [C]//2021 IEEE SymposiumSeries on Computational Intelligence(SSCI). Piscataway, NJ, USA: IEEE, 2021:1-6.

ALSATTAR H A, ZAIDAN A A, ZAIDAN B B.Novel meta-heuristic bald eagle search optimisation algorithm [J]. ArtificialIntelligence Review, 2020, 53(3): 2237-2264.

蒋宇飞, 许贤泽, 徐逢秋, 等. 多策略融合改进的自适应蜉蝣算法 [J/OL]. 北京航空航天大学学报, 2022: 1-14[2022-11-23]. https://doi.org/10.13700/j.bh.1001-5965.2022.0492.

JIANG Yufei, XU Xianze, XU Fengqiu, et al.Adaptive ephemera algorithm with improved multi-strategy fusion [J/OL]. Journalof Beijing University of Aeronautics and Astronautics, 2022: 1-14[2022-11-23].https://doi.org/10.13700/j.bh.1001-5965.2022.0492.

MAHDAOUI A, BOUAZI A, HSAINI A M, etal. Comparison of k-means and fuzzy c-means algorithms on simplification of 3Dpoint cloud based on entropy estimation [J]. Advances in Science, Technologyand Engineering Systems Journal, 2017, 2(5): 38-44.

DING Xinghao, HE Fujin, LIN Zhirui, etal. Crowd density estimation using fusion of multi-layer features [J]. IEEETransactions on Intelligent Transportation Systems, 2021, 22(8): 4776-4787.

ZHOU Zhou, SI Gangquan, SUN Haodong,et al. A robust clustering algorithm based on the identification of core pointsand KNN kernel density estimation [J]. Expert Systems with Applications, 2022,195: 116573.

GONDELACH D J, LINARES R. Real-timethermospheric density estimation via radar and GPS tracking data assimilation[J]. Space Weather, 2021, 19(4): e2020SW002620.

THARWAT A. Parameter investigation ofsupport vector machine classifier with kernel functions [J]. Knowledge andInformation Systems, 2019, 61(3): 1269-1302.

CINCOTTA P M, GIORDANO C M, ALVESSILVA R, et al. The Shannon entropy: an efficient indicator of dynamicalstability [J]. Physica: D Nonlinear Phenomena, 2021, 417: 132816.

TOLEDO F J, GALIANO V, BLANES J M, etal. Photovoltaic single-diode model parametrization: an application to thecalculus of the Euclidean distance to an Ⅰ-Ⅴ curve[J/OL]. Mathematics and Computers in Simulation, 2023: 1-26[2023-03-10].https://doi.org/10.1016/j.matcom.2023.01.005.

杨清夙, 游志胜, 张先玉. 基于豪斯多夫距离的快速多人脸检测算法 [J]. 电子科技大学学报, 2004, 33(4): 407-409.

YANG Qingsu, YOU Zhisheng, ZHANG Xianyu.Fast multi-face detection algorithm based on Hausdorff distance [J]. Journal ofUniversity of Electronic Science and Technology of China, 2004, 33(4): 407-409.

郭云川, 张长胜, 段青娜, 等. 融合多策略的改进秃鹰搜索算法 [J]. 控制与决策, 2024, 39(1): 69-77.

GUO Yunchuan, ZHANG Changsheng, DUANQingna, et al. Improved bald eagle search algorithm fused with multiplestrategies [J]. Control and Decision, 2024, 39(1): 69-77.

刘卫明, 崔瑜, 毛伊敏, 等. 基于MapReduce和MSSA的并行k-means算法 [J]. 计算机应用研究,2022, 39(11): 3244-3251, 3257.

LIU Weiming, CUI Yu, MAO Yimin, et al.Parallel k-means algorithm based on MapReduce and MSSA [J]. ApplicationResearch of Computers, 2022, 39(11): 3244-3251, 3257.

黄鹤, 李昕芮, 吴琨, 等. 引入改进飞蛾扑火的K均值交叉迭代聚类算法 [J]. 西安交通大学学报, 2020, 54(9): 32-39.

HUANG He, LI Xinrui, WU Kun, et al. Hybriditerative K-means clustering with improved moth-flame optimization [J]. Journalof Xi'an Jiaotong University, 2020, 54(9): 32-39.

NIU Lede, XIONG Liran. Optimisationand application research of ant colony algorithm in vehicle routing problem[J]. International Journal of Computing Science and Mathematics, 2021, 13(2):177-193.

TIAN Hui. Research on robot optimalpath planning method based on improved ant colony algorithm [J]. InternationalJournal of Computing Science and Mathematics, 2021, 13(1): 80-92.

YU Jin, YOU Xiaoming, LIU Sheng.Dynamic reproductive ant colony algorithm based on piecewise clustering [J].Applied Intelligence, 2021, 51(12): 8680-8700.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on Point Cloud Simplification with Preserved Features

A Method to Detect Network Attacks Using Entropy in the Intrusion Detection System

Fuzzy C-means Clustering Information Entropy Point Cloud Simplification Using Mixed Strategy Joint Optimization

Mechanism and Optimal Control Strategy for Hysteresis in Rapid Dehumidification Response of Indirect Thermal Systems in Electric Vehicles

Windage Loss and Flow Characteristics in Impeller Back Gaps of sCO2 Radial Inflow Turbines

Related Author

史宝全

梁晋

张晓强

舒挽

夏秦

王志文

卢柯

HUANG He

Related Institution

School of Mechanical Engineering, Xi'an Jiaotong University

School of Electronics and Information Engineering, Xi'an Jiaotong University

Xi'an Key Laboratory of Intelligent Expressway Information Fusion and Control, Chang'an University

School of Electronic and Control Engineering, Chang'an University

Institute of Data Science and Artificial Intelligence, Chang'an University

⁰