基于自适应八叉树区域生长的螺旋桨点云模型提取

王焱爽, 程东

doi:10.16411/j.cnki.issn1006-7736.2024.04.007

大连海事大学学报 >

2024 , Vol. 50 >Issue 4: 59 - 66

DOI: https://doi.org/10.16411/j.cnki.issn1006-7736.2024.04.007

基于自适应八叉树区域生长的螺旋桨点云模型提取

展开

(大连海事大学轮机工程学院，辽宁大连 116026)

王焱爽（1999 — ），男，研究生，研究方向：船用螺旋桨参数的三维测量。程东*（1972 — ），男，博士，教授，E-mail：chengdmu@dlmu.edu.cn。

程东*（1972 — ），男，博士，教授， E-mail：chengdmu@dlmu.edu.cn。

网络出版日期: 2024-07-09

基金资助

中央高校基本科研业务费专项资金资助项目（3132023515）

收起

Extraction of propeller point cloud model based on adaptive octree region growth

Expand

(Marine Engineering College, Dalian Maritime University, Dalian 116026, China)

Online published: 2024-07-09

Fold

摘要

为实现螺旋桨几何参数的非接触式测量，提出一种基于自适应八叉树的区域生长算法提取螺旋桨点云模型。首先，采用自适应八叉树将点云数据划分为若干非均匀体素。其次，结合体素的空间连通性和平滑性设置区域生长判据，利用体素的特征属性进行区域生长，实现对螺旋桨点云模型的提取。然后，利用正交试验法进行算法参数的优选。最后，将本文算法与基于传统八叉树的区域生长算法和基于点的区域生长算法进行对比实验。结果表明：本文算法可以实现对螺旋桨点云模型的精确提取，分割精度达99.5%，相比其他两种算法精度分别提高了1.8%和1.3%；执行时间为1045 ms，分别为其他两种算法耗时的4.1%和5.6%，点云分割的效率得到明显提高。

关键词： 螺旋桨; 点云; 自适应八叉树; 区域生长

本文引用格式

王焱爽, 程东 . 基于自适应八叉树区域生长的螺旋桨点云模型提取[J]. 大连海事大学学报, 2024 , 50(4) : 59 -66 . DOI: 10.16411/j.cnki.issn1006-7736.2024.04.007

Abstract

To realize the non-contact measurement of propeller geometric parameters, a region growing algorithm based on adaptive octree was proposed to extract the point cloud model of an propeller. Firstly, the adaptive octree was utilized to partition the point cloud data into non-uniform voxels. Secondly, by combining with the spatial connectivity and smoothness of voxels, the region growth criteria were set, such the feature attributes of voxels were utilized for region growth to extract the propeller point cloud model. Then, the orthogonal experimental method was used to optimize the algorithm parameters. Finally, a comparative experiment was conducted between the proposed algorithm and the traditional octree based region growing algorithm as well as the point based region growing algorithm. Results show that the algorithm can achieve accurate extraction of the propeller point cloud model, while the segmentation accuracy can reach 99.5%, which is 1.8% and 1.3% higher than the other two algorithms. The execution time is 1045 ms, which is 4.1% and 5.6% of the other two algorithms. The efficiency of point cloud segmentation can be significantly improved.

Key words： propeller; point cloud; adaptive octree; regional growth

参考文献

［1］CHOURASIYA S, MOHAPATRA P K, TRIPATHI S. Non-intrusive underwater measurement of mobile bottom surface［J］. Advances in Water Resources, 2017, 104: 76-88.
［2］KRZESZOWSKI T, DZIADEK B, FRANCA C, et al. System for estimation of human anthropometric parameters based on data from kinect v2 depth camera［J］. Sensors, 2023, 23(7): 3459.
［3］苏云龙,平雪良,李楠.基于RANSAC三维点云的平面提取算法［J］.激光与红外, 2019,49(6):780-784.
SU Y L, PING X L, LI N. A planar extraction algorithm based on RANSAC 3D point cloud［J］. Laser & Infrared, 2019,49(6):780-784. (in Chinese)
［4］SEVGENS C, KARSLI F. An improved RANSAC algorithm for extracting roof planes from airborne lidar data［J］. The Photogrammetric Record, 2020, 35(169): 40-57.
［5］刘亚坤,李永强,刘会云,等.基于改进RANSAC算法的复杂建筑物屋顶点云分割［J］.地球信息科学学报,2021,23(8):1497-1507.
LIU Y K, LI Y Q, LIU H Y, et al. An improved RANSAC algorithm for point cloud segmentation of complex building roofs［J］. Journal of Geo-information Science, 2021,23(8):1497-1507. (in Chinese)
［6］WANG B X, LAN J, GAO J J. LiDAR filtering in 3D object detection based on improved RANSAC［J］. Remote Sensing, 2022, 14(9): 2110.
［7］KUAK R A. The feature extraction from point clouds using geometric features and RANSAC algorithm［J］. Advanced LiDAR, 2022, 2(1): 15-20.
［8］DU X G, LU Y C, CHEN Q J. A fast multiplane segmentation algorithm for sparse 3D LiDAR point clouds by line segment grouping［J］. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 1-15.
［9］LI L, YAO J, TU J M, et al. Roof plane segmentation from airborne LiDAR data using hierarchical clustering and boundary relabeling［J］. Remote Sensing, 2020, 12(9): 1363.
［10］SUN Z, LI Z Y, LIU Y C. An improved lidar data segmentation algorithm based on Euclidean clustering［C］//Proceedings of the 11th International Conference on Modelling, Identification and Control (ICMIC2019). Singapore：Springer , 2020: 1119-1130.
［11］ZHAO Y P, ZHOU X L. K-means clustering algorithm and its improvement research［J］. Journal of Physics: Conference Series, 2021, 1873(1): 012074.
［12］史红霞,王建民.基于法向量区域聚类分割的点云特征线提取［J］.中国机械工程,2021,32(21):2552-2561.
SHI H X, WANG J M. Feature line extraction for point cloud based on normal vector region clustering segmentation［J］. China Mechanical Engineering, 2021,32(21):2552-2561. (in Chinese)
［13］LEE H R, JUNG J Y. Clustering-based plane segmentation neural network for urban scene modeling［J］. Sensors, 2021, 21(24): 8382.
［14］HARJANTI T W, SETIYANI H, TRIANTO J, et al. Classification of mint leaf types based on the image using Euclidean distance and K-means clustering with shape and texture feature extraction［J］. Tech-E, 2022, 5(2):115-124.
［15］XIE Y X, TIAN J J, ZHU X X. Linking points with labels in 3D: a review of point cloud semantic segmentation［J］. IEEE Geoscience and Remote Sensing Magazine, 2020, 8(4): 38-59.
［16］李仁忠,刘阳阳,杨曼,等.基于改进的区域生长三维点云分割［J］.激光与光电子学进展, 2018,55(5):325-331.
LI R Z, LIU Y Y, YANG M, et al. Three-dimensional point cloud segmentation algorithm based on improved region growing［J］. Laser & Optoelectronics Progress, 2018,55(5):325-331. (in Chinese)
［17］汪文琪,李宗春,付永健,等.基于改进多规则区域生长的点云多要素分割［J］.光学学报, 2021,41(5):198-212.
WANG W Q, LI Z C, FU Y J, et al. Multi-factor segmentation of point cloud based on improved multi-rule region growing［J］. Acta Optica Sinica, 2021,41(5):198-212. (in Chinese)
［18］赵传,郭海涛,卢俊,等.结合区域增长与RANSAC的机载LiDAR点云屋顶面分割［J］.测绘学报, 2021,50(5):621-633.
ZHAO C, GUO H T, LU J, et al. Roof segmentation from airborne LiDAR by combining region growing with random sample consensus［J］.Acta Geodaetica et Cartographica Sinica, 2021，50(5):621-633. (in Chinese)
［19］李文,刘德儿,王有毅,等.基于超体素的区域聚类的复杂场景分割［J］.激光与红外, 2021,51(11):1425-1432.
LI W, LIU D E, WANG Y Y, et al. Complex scene segmentation based on super voxel region clustering［J］. Laser & Infrared, 2021,51(11):1425-1432. (in Chinese)
［20］WANG M, TSENG Y H. Automatic segmentation of LiDAR data into coplanar point clusters using an octree-based split and merge algorithm［J］. Photogrammetric Engineering & Remote Sensing, 2010, 76(4): 407-420.
［21］VO A V, TRUONG-HONG L, LAEFER D F, et al. Octree-based region growing for point cloud segmentation［J］. ISPRS Journal of Photogrammetry and Remote Sensing, 2015, 104: 88-100.
［22］李明磊,李广云,王力,等.采用八叉树体素生长的点云平面提取［J］.光学精密工程, 2018,26(1):172-183.
LI M L, LI G Y, WANG L, et al. Planar feature extraction from unorganized point clouds using octree voxel based region growing［J］. Optics and Precision Engineering, 2018,26(1):172-183. (in Chinese)
［23］SU Y T, BETHEL J, HU S W. Octree-based segmentation for terrestrial LiDAR point cloud data in industrial applications［J］. ISPRS Journal of Photogrammetry & Remote Sensing, 2016, 113:59-74.
［24］ZENG J H，WANG D C，CHEN P. Improved color region growing point cloud segmentation algorithm based on Octree［C］// 2022 3rd International Conference on Information Science, Parallel and Distributed Systems(ISPDS).New York:IEEE,2022:424-429.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献