基于真实三维人体点云的特征参数提取  

Feature Parameter Extraction Based onReal 3D Human Body Point Cloud

作　　者：李静[1] 尹伟石[1] 孟品超[1] LI Jing;YIN Weishi;MENG Pinchao(School of Mathematics and Statistics,Changchun University of Science and Technology,Changchun 130022)

机构地区：[1]长春理工大学数学与统计学院,长春130022

出　　处：《长春理工大学学报（自然科学版）》2024年第1期131-136,共6页Journal of Changchun University of Science and Technology(Natural Science Edition)

基　　金：吉林省自然科学基金(20220101040JC)。

摘　　要：针对真实三维人体点云数据,提出一种快速提取人体特征参数的方法。首先对点云数据进行预处理,并将人体中心点转化为坐标原点,然后利用人体几何形状以及特征参数的定义,通过分层探索法来定位人体特征点,最后利用人体特征点得到相应的特征截面信息,使用边缘识别法提取特征轮廓边界点,对于不同人体体型,基于人体几何形状分析法自动识别正常和肥胖人体体型,有效地计算不同体型的真实特征参数信息。数值实验说明了该方法的有效性。Aiming at the real three-dimensional human body point cloud data,this paper proposes a method to quickly extract human feature parameters.Firstly,the point cloud data is preprocessed and the center point of the human body is transformed into the coordinate origin.Then,by using the definition of human body geometry and characteristic parameters,the human body feature points are located by hierarchical exploration method.Finally,the corresponding feature section information is obtained by using the human body feature points,and the feature contour boundary points are extracted by using the edge recognition method.For different body shapes,the normal and obese body shapes are automatically identified based on the human body geometry analysis method,and the real feature parameter information of different body shapes is effectively calculated.Numerical experiments show the effectiveness of the proposed method.

关 键 词：真实三维人体点云 点云数据 特征点 特征提取 

分 类 号：O242.1[理学—计算数学]