基于模板匹配的三维人体语义特征提取算法

doi:10.3969/j.issn.1006-2475.2020.04.016

计算机与现代化

基于模板匹配的三维人体语义特征提取算法

(1.河海大学物联网工程学院,江苏常州213022;
2.常州市图形图像与骨科植入物数字化技术重点实验室,江苏常州213022)

收稿日期:2020-01-08 出版日期:2020-04-22 发布日期:2020-04-24
作者简介:李灵杰(1994-),女,山东济南人,硕士研究生,研究方向:计算机图形学,人体特征提取,E-mail: lilingjie2020@outlook.com; 童晶(1981-),男,副教授,博士,研究方向:计算机图形学,虚拟现实,三维打印,E-mail: tongjing.cn@gmail.com; 步文瑜(1997-),女,山东济南人,硕士研究生,研究方向:计算机图形学,三维网格变形,E-mail: wenyu.bu@qq.com; 孙海舟(1998-),男,浙江杭州人,硕士研究生,研究方向:计算机图形学,Unity3D建模与应用,E-mail: 874302225@qq.com; 陈正鸣(1965-),男,教授,博士生导师,博士,研究方向:CAD，CG,E-mail: zmchen@hhuc.edu.cn。
基金资助:
国家自然科学基金资助项目(61772172)

Semantic Feature Extraction Algorithm for 3D Human Body Based on Template Matching

(1. College of Internet of Things Engineering, Hohai University, Changzhou 213022, China;
2. Changzhou Key Laboratory of Graphics, Images and Orthopedic Implants Digital Technology, Changzhou 213022, China)

Received:2020-01-08 Online:2020-04-22 Published:2020-04-24

摘要/Abstract

摘要： 随着社会经济发展，生活水平的提高，人们对定制产品的需求越来越多，例如服装高级定制、健身计划定制等。为更好地满足这些需求并提供精准的数据支撑，需提取精确的人体语义特征，即人体的身高、胸围、腰围等一系列参数。对现有特征提取算法进行分析研究，设计一种基于模板匹配的三维人体语义特征提取算法。通过模板模型逼近输入模型，将模板模型上的语义特征采样点拓展到输入模型上，使用NURBS曲线拟合采样点，计算曲线长度。实验结果表明本文所提算法综合性能好，能够为服装定制、人体动画、人体工程学设计等提供精确广泛的数据支持。

关键词: 三维人体模型, 特征提取, 模板匹配

Abstract: With the development of society and economy and the improvement of living standards, people’s demand for customized products is increasing, such as advanced customization of clothing and customization of fitness programs. In order to better meet these needs and provide accurate data support, it is necessary to extract precise human body semantic features, that is, a series of parameters such as height, chest size, and waist size of the human body. The existing feature extraction algorithms are analyzed and researched, and a semantic feature extraction algorithm for 3D human body based on template matching is designed. The template model is used to approximate the input model, and the semantic feature sampling points on the template model are extended to the input model. The NURBS curve is used to fit the sampling points to calculate the curve length. The experimental results show that the proposed algorithm has good comprehensive performance and can provide accurate and extensive data support for clothing customization, human body animation, and ergonomic design.

Key words: 3D human model, feature extraction, template matching

中图分类号:

TP391.41

李灵杰1,童晶1,2,步文瑜1,孙海舟1,陈正鸣1,2. 基于模板匹配的三维人体语义特征提取算法[J]. 计算机与现代化, doi: 10.3969/j.issn.1006-2475.2020.04.016.

LI Ling-jie1, TONG Jing1,2, BU Wen-yu1, SUN Hai-zhou1, CHEN Zheng-ming1,2. Semantic Feature Extraction Algorithm for 3D Human Body Based on Template Matching[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2020.04.016.

参考文献

［1］陈光. 基于多态统计的三维人体重建及其在虚拟试衣中的应用［D］. 杭州:浙江大学, 2017.
［2］朱江涛. 基于Kinect的人体三维重建与尺寸测量［D］. 杭州:杭州电子科技大学, 2015.
［3］张文斌,肖平,杨子田,等. 人体测量高新技术——三维人体扫描技术的应用和发展［C］// 2006/2007中国纺织工业技术进步研究报告. 2006.
［4］程宵琼. 非接触式三维人体测量与传统人体测量的比较研究［J］. 西部皮革, 2016,38(6):52.
［5］夏鹏泽,曾长松,姜志华. “中国军人服装用人体尺寸数据库”样本组成特点［J］. 中国个体防护装备, 2001(1):20-22.
［6］ CHI-YUANG Y U, LIANG M H. The development of real 3D human digital model for design［J］. Asian Journal of Applied Sciences, 2012,5(6):404-413.
［7］ WANG C C L, CHANG T K K, YUEN M M F. From laser-scanned data to feature human model: A system based on fuzzy logic concept［J］. Compute-Aided Design, 2003,35(3):241-253.
［8］ WANG C C L. Parameterization and parametric design of mannequins［J］. Computer-Aided Design, 2005,37(1):83-98.
［9］ AZOUZ Z B, SHU C, MANTEL A. Automatic locating of anthropometric landmarks on 3D human models［C］// The 3rd International Symposium on 3D Data Processing, Visualization, and Transmission. 2006:750-757.
［10］LEONG L F, FANG J J, TSAI M J. Automatic body feature extraction from a marker-less scanned human body［J］. Computer-Aided Design, 2007,39(7):568-582.
［11］PROBST T, FOSSATI A, SALZMANN M, et al. Efficient model-free anthropometry from depth data［C］// 2017 International Conference on 3D Vision. 2017:486-495.
［12］SONG D, TONG R, CHANG J, et al. Clothes size prediction from dressed-human silhouettes［C］// International Workshop on Next Generation Computer Animation Techniques. 2017:86-98.
［13］XU H H, YU Y, ZHOU Y, et al. Measuring accurate body parameters of dressed humans with large-scale motion using a kinect sensor［J］. Sensors, 2013,13(9):11362-11384.
［14］NEOPHYTOU A, YU Q Z, HILTON A. ShapeMate: A virtual tape measure［C］// The 4th International Conference on 3D Body Scanning Technologies. 2013:127-133.
［15］HASLER N, STOLL C, SUNKEL M, et al. A statistical model of human pose and body shape［J］. Computer Graphics Forum, 2009,28(2):337-346.
［16］SCHOELER M, PAPON J, WORGOTTER F. Constrained planar cuts-object partitioning for point clouds［C］// Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. 2015:5207-5215.
［17］BEYER K, GOLDSTEIN J, RAMAKRISHNAN R, et al. When is “nearest neighbor” meaningful?［C］// International Conference on Database Theory. 1999:217-235.
［18］ALLEN B, CURLESS B, CURLESS B, et al. The space of human body shapes: Reconstruction and parameterization from range scans［J］. ACM Transactions on Graphics, 2003,22(3):587-594.
［19］FU X M, LIU Y, SNYDER J, et al. Anisotropic simplicial meshing using local convex functions［J］. ACM Transactions on Graphics, 2014,33(6):95-106.
［20］KWOK T H, ZHANG Y,WANG C C. Efficient optimization of common base domains for cross parameterization［J］. IEEE Transactions on Visualization & Computer Graphics, 2012,18(10):1678-1692.
［21］兰浩. NURBS曲线整体光顺逼近算法研究与应用［D］. 西安:西安理工大学, 2008.

[1]	王秋忆, 周浩, 郑婷婷. 改进RetinaNet的电力设备目标检测方法[J]. 计算机与现代化, 2024, 0(01): 47-52.
[2]	杨柳青, 王冲. 基于极大熵的Web服务资源个性化推荐方法[J]. 计算机与现代化, 2023, 0(09): 32-37.
[3]	胡睿杰, 车逗. 红外小目标检测方法综述[J]. 计算机与现代化, 2023, 0(08): 79-86.
[4]	王欣怡, 尹四清, 洪军. 融合注意力机制的非对称深度监督哈希[J]. 计算机与现代化, 2023, 0(05): 26-31.
[5]	潘凤, 王杰, 张艳莎, 谭棉, 何兴, 王林, . 基于双分支特征拼接的行人重识别[J]. 计算机与现代化, 2023, 0(05): 93-99.
[6]	张晓东, 王栩颖, 秦子轩. 基于特征融合的抽油机井检泵周期预测[J]. 计算机与现代化, 2022, 0(12): 60-66.
[7]	李春生, 冯阳宵, 富宇, 张可佳, 吴润桐. 基于均值聚类的员工行为分析方法[J]. 计算机与现代化, 2022, 0(09): 19-24.
[8]	王梦, 张鸿鑫, 刘庆华, 张东. 基于改进YOLOv5的幽门螺杆菌免疫印迹图像识别[J]. 计算机与现代化, 2022, 0(09): 78-84.
[9]	陈钢. 融合RoBERTa和特征提取的政务热线工单分类[J]. 计算机与现代化, 2022, 0(06): 21-26.
[10]	贺璇, 刘怡欣, 何小海, 卿粼波, 陈洪刚. 基于改进残差网络的联合损失步态特征识别[J]. 计算机与现代化, 2022, 0(04): 27-32.
[11]	赵聪慧, 冯庆胜. 基于DT-CWT和SVM的踏面旋转不变纹理提取算法[J]. 计算机与现代化, 2021, 0(12): 85-90.
[12]	李龙, 张重阳. 基于改进YOLOv3的车辆尾灯检测方法[J]. 计算机与现代化, 2021, 0(07): 89-94.
[13]	刘亚东, 罗印升, 曹阳阳, 宋伟. 深度学习在手机数据接口缺陷检测中的应用[J]. 计算机与现代化, 2021, 0(06): 35-40.
[14]	林智伟, 朱文章, 陈浩. 基于神经网络空时特征提取的动态手势识别[J]. 计算机与现代化, 2021, 0(06): 41-47.
[15]	黄旭彬, 张金霜. 基于运动想象脑电控制的智能家居系统[J]. 计算机与现代化, 2021, 0(02): 68-72.

基于模板匹配的三维人体语义特征提取算法

Semantic Feature Extraction Algorithm for 3D Human Body Based on Template Matching

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价