基于改进欧氏聚类的锥桶检测方法与试验  

Detection Method and Experiment of the Cone Based on Improved Euclidean Clustering

作　　者：黄瑞钦 梁洪波 李强 杨爱喜 张新闻 Huang Ruiqin;Liang Hongbo;Li Qiang;Yang Aixi;Zhang Xinwen(School of Mechanical and Energy Engineering,Zhejiang University of Science&Technology,Hangzhou,Zhejiang 310023,China;Department of Automobile and Engineering,Anhui Communications Vocational&Technical College,Hefei,Anhui230051,China;Pol ytechnic Institute of Zhejiang University,Hangzhou,Zhejiang 310015,China)

机构地区：[1]浙江科技学院机械与能源工程学院,浙江杭州310023 [2]安徽交通职业技术学院汽车与机械工程系,安徽合肥230051 [3]浙江大学工程师学院,浙江杭州310015

出　　处：《应用激光》2022年第10期126-134,共9页Applied Laser

基　　金：安徽省教育厅2020年度高校科学研究重大项目(KJ2020ZD78);浙江省自然科学基金项目(LY21E050001);汽车新技术安徽省工程技术研究中心开放基金(QCKJ202105)。

摘　　要：针对赛道环境下欧氏聚类算法检测锥桶不准确的问题,提出了一种基于改进欧氏聚类算法的锥桶检测方法。首先,通过机器人操作系统(ROS)采集点云;再对点云预处理,找到感兴趣区域(ROI)后,利用随机采样算法分离地面和锥桶的点云;然后,将距离和阈值模型化;接着,设计出面向赛道环境的区域划分方法来改进欧氏聚类算法,利用动态阈值聚类分割出锥桶点云;最后,通过Matlab平台验证算法。在两种赛道环境下进行实车试验,聚类分割的准确率分别达到93.98%和99%。试验结果表明,所提方法能够准确地检测赛道中的锥桶。Aiming at the inaccurate detection of cone buckets by Euclidean clustering algorithm in the race track environment, a cone bucket detection method based on improved Euclidean clustering algorithm is proposed. Firstly, the point clouds are collected through the robot operating system(ROS);then the point clouds are preprocessed to find the region of interest(ROI) and then the ground and cone bucket point clouds are separated using a random sampling algorithm;then the distances and thresholds are modeled;then a region partitioning method is designed for the track environment to improve Euclidean clustering algorithm, and the cone bucket point clouds are segmented using dynamic threshold clustering;finally the algorithm is validated through the Matlab platform. The accuracy of clustering segmentation reached 93.98% and 99% in real-world tests under two track environments, respectively. The test results show that the proposed method can accurately detect the cone bucket in the track.

关 键 词：激光雷达 锥桶检测 欧氏聚类 区域划分 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]