光学技术, 2017, 43 (6): 528, 网络出版: 2017-12-25  

基于点云模型的人体尺寸提取算法

Extraction of human body measures based on 3D point clouds
方群 1,*尚媛园 1,2,3郭国栋 2,4邵珠宏 1,2,5
作者单位
1 首都师范大学 信息工程学院, 北京 100048
2 成像技术北京市高精尖创新中心, 北京 100048
3 首都师范大学 电子系统可靠性技术北京市重点实验室, 北京 100048
4 美国西弗吉尼亚大学
5 首都师范大学 高可靠嵌入式系统技术北京市工程技术研究中心, 北京 100048
摘要
针对人体尺寸自动提取的问题, 提出一种基于PCL点云库的交互式算法。通过单台Microsoft Kinect 采集人体点云数据, 使用邻域平均法进行去噪预处理; 通过人机交互的方式选取特征点得到所对应的点云轮廓; 采用改进的凸包算法估算人体胸围、腰围、脖围尺寸。实现了全面的非接触式人机交互, 具有操作便捷、速度快的特点。实验结果表明交互式人体尺寸提取方法能够适用于不同人群, 改进的凸包算法能够有效地提高尺寸精度; 提取的人体尺寸满足GB/T 23698-2009的精度要求。
Abstract
For the automatic extraction of human body measures, an interactive algorithm based on PCL point clouds is proposed. The human body information is captured by a single Microsoft Kinect to obtain the point cloud data, and the neighborhood average method is used for denoising. The algorithm is adopted to estimate the human body measures. The method achieves a complete non-contact human-computer interaction, which has the characteristics of convenient operation and fast speed. The experimental results show that not only the algorithm can be applied to different groups of people, but also it improves the dimensional accuracy. The algorithm satisfies the accuracy requirements of GB/T 23698-2009.
参考文献

[1] 席焕久.人体测量方法[M].北京:科学出版社, 2010: 1-10.

    XI Huanjiu.Anthropometric methods[M].Beijing:Science Press, 2010: 1-10.

[2] 吴壮志, 廖爽爽, 聂磊.基于图像的人体参数测量系统的设计与实现[J].湖南大学学报:自然科学版, 2010, 37(9): 88-92.

    WU Zhuangzhi, LIAO Shuangshuang, NIE Lei. Design and implementation of human size measurement system based on images[J]. Journal of Hunan University(Natural Sciences),2010,37(9): 88-92.

[3] 林德静, 孙晓东. 基于三维扫描的人体尺寸提取技术[J].北京服装学院学报:自然科学版,2005, 25(3):36-41.

    LIN Dejing, SUN Xiaodong. Technique of measurement extraction based on 3D human body scanning data[J]. Journal of Beijing Institute of Clothing Technology(Natural Science Edition), 2005, 25(3):36-41.

[4] 甘应进, 陈东生, 孟爽.非接触式三维人体计测现状[J].纺织学报,2005, 26(3):145-146.

    GAN Yingjing, CHEN Dongsheng, MENG Shuang. Recent development of non-touch 3D body measurement[J]. Journal of Textile Research, 2005, 26(3):145-146.

[5] LEWARK E A, NURRE J H. Automated fudicial labeling on human body data[C]∥Proceedings of SPIE the International Society for Optical Engineering, San Jose, USA: 1998, 3313:82-89.

[6] WANG C, CHANG T, YUEN M, et al. From laser-scanned data to feature human model: a system based on fuzzy logic concept [J].Computer-Aided Design,2003, 35(3):241-253.

[7] 陆国栋, 许鹏, 徐文鹏. 人体扫描模型的特征提取方法研究 [J].工程设计学报,2005, 12(4): 247-251.

    LU Guodong, XU Peng, XU Wenpeng. Research on feature extraction method of scanned body model[J]. Chinese Journal of Engineering Design,2005, 12(4): 247-251.

[8] 陈国安, 刘飞, 李丽. 采用模糊规则的人体点云特征尺寸识别与提取[J].计算机辅助设计与图形学学,2011,23(8): 1393-1400.

    CHEN Guoan, LIU Fei, LI L. Recognition and extraction of human body's feature dimensions using fuzzy rules[J]. Journal of Computer-Aided Design & Computer Graphics, 2011, 23(8): 1393-1400.

[9] 3-d Scanning Methodologies For Internationally Compatible Anthropometric Databases[S]. Swiss: Swiss Standards, 2006.

[10] 中国国家标准化管理委员会. GB/T23698-2009三维扫描人体测量方法的一般要求[S]. 北京: 中国标准出版社, 2009.

    Standardization Administration of the People's Republic of China. GB/T 23698-2009 General requirements 3-Dscanning anthropometric methodologies[S]. BeiJing: Standards Press of China, 2009.

[11] IZADI S, NEWCOMBE R A, KIM D, et al. KinectFusion: real-time dynamic 3D surface reconstruction and interaction.[C]∥ACM SIGGRAPH,New York, USA: ACM, 2011, 3: 1175-1184.

[12] CURLESS B, LEVOY M, A volumetric method for building complex models from range images.[C]∥Proceedings of The 23rd Annual Conference on Computer Graphics and Interactive Techniques, New York, USA:1996, ACM,3: 303-312.

[13] WHELAN T, KAESS M, FALLON M, et al. Kintinuous: Spatially Extended KinectFusion [J]. Robotics & Autonomous Systems, 2012, 69(C):3-14.

[14] 孙金虎, 周来水, 安鲁陵. 点云模型法矢调整优化算法[J]. 中国图象图形学报, 2013, 18(7):844-851.

    SUN Jinhu, ZHOU Laishui, AN Luling. Optimal algorithm for normal adjustment of point clouds[J]. Journal of Image and Graphics, 2013, 18(7):844-851.

[15] 周晓飞, 杨静宇, 姜文瀚. 核最近邻凸包分类算法[J]. 中国图象图形学报, 2007, 12(7): 1209-1213.

    ZHOU Xiaofei, YANG Jingyu, JIANG Wenhan. Kernel nearest neighbor convex hull classification algorithm[J]. Journal of Image and Graphics, 2007, 12(7): 1209-1213.

[16] 朱德海. 点云库PCL学习教程[M]. 北京: 北京航空航天大学出版社, 2012: 1-4.

    ZHU Dehai. Point cloud library PCL[M]. Beijing: Beihang University Press, 2012: 1-4.

方群, 尚媛园, 郭国栋, 邵珠宏. 基于点云模型的人体尺寸提取算法[J]. 光学技术, 2017, 43(6): 528. FANG Qun, SHANG Yuanyuan, GUO Guodong, SHAO Zhuhong. Extraction of human body measures based on 3D point clouds[J]. Optical Technique, 2017, 43(6): 528.

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!