基于图像的人体颈肩部三维模型构建

doi:10.13475/j.fzxb.20200707808

纺织学报 ›› 2021, Vol. 42 ›› Issue (01): 125-132.doi: 10.13475/j.fzxb.20200707808

基于图像的人体颈肩部三维模型构建

王婷¹, 顾冰菲¹^,²^,³()

1.浙江理工大学服装学院, 浙江杭州 310018
2.浙江省服装工程技术研究中心, 浙江杭州 310018
3.丝绸文化传承与产品设计数字化技术文化和旅游部重点实验室, 浙江杭州 310018

收稿日期:2020-07-30 修回日期:2020-10-14 出版日期:2021-01-15 发布日期:2021-01-21
通讯作者: 顾冰菲
作者简介:王婷(1995—),女,硕士生。主要研究方向为数字化服装技术。
基金资助:
国家自然科学基金项目(61702461);国家自然科学基金项目(61702460);中国纺织工业联合会科技指导性项目(2018079);2020年“纺织之光”应用基础研究项目(J202007);浙江理工大学科研业务费专项资金资助项目(2020Q051);浙江理工大学服饰文化创新团队项目(11310031282006)

3-D modeling of neck-shoulder part based on human photos

WANG Ting¹, GU Bingfei¹^,²^,³()

1. School of Fashion Design & Engineering, Zhejiang Sci-Tech University, Hangzhou, Zhejiang 310018, China
2. Clothing Engineering Research Center of Zhejiang Province, Hangzhou, Zhejiang 310018, China
3. Key Laboratory of Silk Culture Heritage and Products Design Digital Technology, Ministry of Culture and Tourism, Hangzhou, Zhejiang 310018, China

Received:2020-07-30 Revised:2020-10-14 Online:2021-01-15 Published:2021-01-21
Contact: GU Bingfei

摘要/Abstract

摘要：

为实现个性化服装在线设计和虚拟试衣,提出一种基于人体正侧面照片的尺寸测量及建模方法。首先结合202名青年女性的三维点云数据确定与人体颈肩部形态相关的8个特征截面层,以各截面层中心点为基准点每隔10°测量角度半径并分析其与截面厚度、宽度之间的关系,建立各截面层的曲线形态规则。然后基于人体正侧面照片进行图像分割以提取人体轮廓,通过人体高度比例关系识别颈肩部特征点所在高度区域,结合颈肩部形态规律提取各特征截面层曲线形态规则所需参数。最后根据曲线形态规则和人体测量参数,通过NURBS曲面建模实现基于人体正侧面照片的颈肩部三维模型构建。结果表明:基于人体照片提取的人体基本参数值的误差百分比均小于5%,且使用该方法构建的三维模型与真实值之间的误差绝对值均在1 cm或1°以内。

关键词: 颈肩部形态, 人体照片, 尺寸提取, 曲线规则, 三维建模

Abstract:

In order to facilitate personalized clothing online design and virtual fitting, a method of size extraction and 3-D modeling based on the front and side photographs of human body was proposed. Eight characteristic cross-sectional layers related to the neck-shoulder shape were determined based on 202 young women's 3-D point cloud data. Taking the center point of each cross-section layer as the reference point, the angle radius was measured every 10° and the relationship among the angle radius, the thickness and width of the curves were analyzed to establish the curve shape rules of each sectional layer. Then, the image segmentation technology was used to extract the human contour based on the front and side photos, the height area where the neck-shoulder feature points were located was identified through the height proportion of the human body, and the parameters required for the curve shape rules of each characteristic section were extracted with the neck-shoulder shape rules. Finally, according to the curve shape rules and anthropometric parameters, NURBS surface modeling was used to realize the 3-D model construction of neck and shoulder based on human body photos. The results show that the error percentage of the basic parameters extracted from human body photos is less than 5%, and the absolute error between the 3-D model constructed by this method and the real value is within 1 cm or 1°, which proves the feasibility of this method, and provides technical support for the automatic generation of garment pattern and 3-D virtual fitting.

Key words: neck-shoulder shape, human body photos, size extraction, virtual fitting, 3-D modeling

中图分类号:

TS941.17

王婷, 顾冰菲. 基于图像的人体颈肩部三维模型构建[J]. 纺织学报, 2021, 42(01): 125-132.

WANG Ting, GU Bingfei. 3-D modeling of neck-shoulder part based on human photos[J]. Journal of Textile Research, 2021, 42(01): 125-132.

图/表 18

表1

表2

样本量的确定"

测量项目	样本均值 $x ˉ$ /cm	标准差s/cm	样本量n
身高	161.43	3.93	23
颈围	33.54	2.27	176
肩围	72.76	4.45	144
腋下围	87.08	4.47	101

表2

图1

图2

图3

图4

表3

图5

表4

图6

表5

图7

图8

表6

图9

图10

表7

表8

参考文献 19

[1]	CHENG Z Q, CHEN Y, MARTIN R R, et al. Parametric modeling of 3D human body shape-A survey[J]. Computers & Graphics, 2018,71:88-100.
[2]	PISHCHULIN L, WUHRER S, HELTEN T, et al. Building statistical shape spaces for 3D human modeling[J]. Pattern Recognition, 2017,67:276-286.
[3]	HEEKYUNG J, CHEN J. A study on 3D virtual body formation and deformation by body shape analysis[J]. International Journal of Clothing Science and Technology, 2019,31(6):755-776.
[4]	LI J, YU Q, XU H, et al. Measuring and modeling human bodies with a novel relocatable mechatronic sensor-net[J]. Textile Research Journal, 2019,89(19/20):4131-4147.
[5]	SHIN J Y, Nam Y J. A study on body shape for 3D virtual body shape transformation-focusing on the women with age of forties[J]. Fashion & Textile Research Journal, 2015,17(2):265-277.
[6]	MARKIEWICZ Ł, WITKOWSKI M, SITNIK R, et al. 3D anthropometric algorithms for the estimation of measurements required for specialized garment design[J]. Expert Systems With Application, 2017,85(1):366-385.
[7]	AFFUSO O, PRADHAN L, ZHANG C, et al. A method for measuring human body composition using digital images[J]. PLoS ONE, 2018,13(11):1-13.
[8]	许明星, 李重. 基于图像的人体特征点提取与尺寸测量[J]. 计算机系统应用, 2018,27(6):87-94.
	XU Mingxing, LI Zhong. Image-based feature extraction and dimension measurement for human bodies[J]. Computer Systems & Applications, 2018,27(6):87-94.
[9]	SENANAYAKE M, RAHEJA A, ZHANG Y H. Automated human body measurement extraction[J]. International Journal of Clothing Science & Technology, 2018,30(2):175-194.
[10]	马黎. 基于图像的非接触式人体测量算法的研究与实现[D]. 成都: 电子科技大学, 2017: 36-47.
	MA Li. Research and implementation of non-contacting anthropometric algorithm based on image[D]. Chengdu: University of Electronic Science and Technology of China, 2017: 36-47.
[11]	胡新荣, 刘嘉文, 刘军平, 等. 基于ABSS的着装人体多特征点提取与尺寸测量[EB/OL]. 计算机工程, 2020: 1-10.[2020-01-10]. http://kns.cnki.net/kcms/detail/31.1289.tp.20200110.1329.004.html.
	HU Xinrong, LIU Jiawen, LIU Junping, et al. Multi-features extraction and dimension measurement for dressed human bodies via adaptive body structure segmentation[EB/OL]. Computer Engineering, 2020: 1-10.[2020-01-10]. http://kns.cnki.net/kcms/detail/31.1289.tp.20200110.1329.004.html.
[12]	CHEN G, LI J, ZENG J, et al. Optimizing human model reconstruction from RGB-D images based on skin detection[J]. Virtual Reality, 2016,20(3):159-172.
[13]	董鹏辉, 柯良军. 基于图像的三维重建技术综述[J]. 无线电通信技术, 2019,45(2):115-119.
	DONG Penghui, KE Liangjun. Overview of 3D reconstruction techniques based on images[J]. Radio Communications Technology, 2019,45(2):115-119.
[14]	师乐. 基于二维图像实时个性化人体模型重建算法的研究[D]. 西安: 西安工程大学, 2019: 25-40.
	SHI Le. Research on real-time personalized human body model reconstruction algorithm based on two-dimensional image[D]. Xi'an: Xi'an Polytechnic University, 2019: 25-40.
[15]	王力. 基于图像的非接触式人体测量与建模技术研究[D]. 西安:西安工程大学, 2018: 27-51.
	WANG Li. Research on non-contacting human body measurement and modeling technology based on image[D]. Xi'an: Xi'an Polytechnic University, 2018: 27-51.
[16]	王永波. 基于3D人体测量的江浙地区青年男性腰臀部特征研究[D]. 无锡: 江南大学, 2019: 12-13.
	WANG Yongbo. Study on characteristics of Jiangsu and Zhejiang young male's waist-hip based on 3D Body measurement[D]. Wuxi: Jiangnan University, 2019: 12-13.
[17]	贺莉文. 基于肩截面曲线的弓背型青年男体细分与识别模型[D]. 苏州: 苏州大学, 2018: 38-39.
	HE Liwen. Classification and recognition model of the hunchback young male body based on shoulder section curve[D]. Suzhou: Soochow University, 2018: 38-39.
[18]	余张君. 基于中老年着装人体美评价的旗袍用人台建模研究[D]. 上海: 东华大学, 2018: 40-42.
	YU Zhangjun. Research on cheongsam mannequin modeling based on the evaluation of physical beauty in middle-aged and elderly group[D]. Shanghai: Donghua University, 2018: 40-42.
[19]	王兴晨, 路春光, 赵震, 等. 逆向工程特征点提取与参数化建模方法研究[J]. 机械设计与制造, 2018,323(1):222-225.
	WANG Xingchen, LU Chunguang, ZHAO Zhen, et al. Research on extraction from reverse engineering characteristics section and parameterized modeling method[J]. Machinery Design & Manufacture, 2018,323(1):222-225.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

参数	身高/cm	颈点高/cm	侧颈点高/cm	肩点高/cm	腋下点高/cm	颈围/cm	侧颈围/cm	肩围/cm	腋下围/cm
最小值	154.1	130.7	125.6	124.0	110.0	29.5	33.6	59.3	76.9
最大值	172.4	148.6	145.8	145.6	133.0	40.8	46.9	82.8	99.4
平均值	161.4	137.8	135.4	132.5	122.1	33.5	38.9	72.8	87.1
标准差	3.9	3.8	3.6	4.5	3.9	2.3	2.7	4.5	4.5
变异系数/%	2.4	2.8	2.7	3.4	3.2	6.9	6.9	6.2	5.2

角度半径	肩厚		肩宽
角度半径	r	sig.	r	sig.
R₀	0.970^**	0.000	0.723^**	0.000
R₁₀	0.976^**	0.000	0.743^**	0.000
R₂₀	0.979^**	0.000	0.686^**	0.000
R₃₀	0.972^**	0.000	0.682^**	0.000
R₄₀	0.897^**	0.000	0.808^**	0.000
R₅₀	0.781^**	0.000	0.851^**	0.000
R₆₀	0.631^**	0.000	0.858^**	0.000
R₇₀	0.491^**	0.005	0.855^**	0.000
R₈₀	0.343	0.050	0.843^**	0.000
R₉₀	0.672^**	0.000	0.983^**	0.000

角度/(°)	回归方程	R²
0	R₀=0.491D-0.481	0.941
10	R₁₀=0.472D+3.040	0.953
20	R₂₀=0.490D+3.467	0.959
30	R₃₀=0.541D+0.293	0.944
40	R₄₀=0.390D+0.092W-3.813	0.875
50	R₅₀=0.228D+0.161W+2.987	0.793
60	R₆₀=0.051D+0.287W-4.381	0.739
70	R₇₀=-0.198D+0.475W-17.565	0.746
80	R₈₀=-0.762D+0.830W-23.305	0.808
90	R₉₀=0.501W-2.330	0.966

高度		宽度		厚度
参数	符号	参数	符号	参数	符号
颈点高	H_NP	颈宽	W_NP	颈厚	D_NP
侧颈点高	H_SNP	侧颈宽	W_SNP	侧颈厚	D_SNP
肩点高	H_SP	肩宽	W_SP	肩厚	D_SP
腋点高	H_AP	腋下宽	W_AP	腋下厚	D_AP
身高	H

指标	特征部位	成对差分(提取值-测量值)			T值	显著性	相关系数	平均绝对误差/cm	误差百分比/%
指标	特征部位	均值/cm	标准差/cm	标准误差	T值	显著性	相关系数	平均绝对误差/cm	误差百分比/%
厚度	颈部	-0.086 1	0.367 7	0.058 1	-1.481	0.147	0.868	0.32	3.05
	侧颈部	-0.115 7	0.427 7	0.067 6	-1.710	0.095	0.877	0.37	3.55
	肩部	-0.068 6	0.493 6	0.078 0	-0.879	0.385	0.908	0.43	3.46
	腋下	-0.267 0	0.877 5	0.138 7	-1.924	0.062	0.847	0.75	3.78
宽度	颈部	-0.022 2	0.400 8	0.063 4	-0.351	0.728	0.859	0.34	3.24
	侧颈部	-0.053 2	0.489 0	0.077 3	-0.689	0.495	0.861	0.43	3.20
	肩部	0.059 9	0.788 9	0.124 7	0.480	0.634	0.910	0.66	2.12
	腋下	0.050 4	0.597 8	0.094 5	0.005 3	0.597	0.964	0.51	1.62

基于图像的人体颈肩部三维模型构建

3-D modeling of neck-shoulder part based on human photos

RichHTML

PDF (PC)

摘要/Abstract

引用本文

使用本文

图/表 18

参考文献 19

相关文章 5

Metrics

本文评价

推荐阅读 0

服装类型	误差/cm
服装类型	颈围	肩宽	胸围
西服	±0.6	±0.6	±2.0
衬衫	±0.6	±0.8	±2.0
连衣裙	±0.6	±0.8	±2.0

样本	部位	肩斜角/(°)	背入角/(°)	颈厚/ cm	颈宽/ cm	侧颈厚/ cm	侧颈宽/ cm	肩厚/ cm	肩宽/ cm	腋下厚/ cm	腋下宽/ cm	颈围/ cm	侧颈围/ cm	肩围/ cm	腋下围/ cm
1^#	模型尺寸	23.5	17.8	11.6	12.4	12.0	15.5	12.5	33.8	20.8	33.6	37.7	43.7	76.9	90.9
	三维测量尺寸	22.6	17.9	11.9	12.1	12.0	15.6	12.9	33.8	20.6	33.8	38.2	44.3	77.9	91.6
	误差	-0.9	0.1	0.3	-0.3	0.0	0.1	0.4	0.0	-0.2	0.2	0.5	0.6	1.0	0.7
2^#	模型尺寸	24.2	12.9	10.0	10.6	10.5	13.6	13.3	30.7	20.2	30.1	32.1	38.2	71.3	84.9
	三维测量尺寸	24.9	12.8	10.2	11.0	10.4	13.8	13.5	30.9	20.4	30.2	32.0	38.3	71.7	85.2
	误差	0.7	-0.1	0.2	0.4	-0.1	0.2	0.2	0.2	0.2	0.1	-0.1	0.1	0.4	0.3

[1]	王婷, 顾冰菲. 基于二维图像的青年女性颈肩部形态自动识别[J]. 纺织学报, 2020, 41(12): 111-117.
[2]	王旭, 储长流, 倪庆清, 刘新华. 运用MAXScript语言的单层机织物结构三维建模[J]. 纺织学报, 2019, 40(01): 159-165.
[3]	沈奕君张婷婷柯莹王宏付. 三维参数化技术在构建现代服装新形态中的应用[J]. 纺织学报, 2018, 39(12): 118-123.
[4]	金兰名蒋高明丛洪莲. 三维纬编提花织物的计算机仿真及系统实现[J]. 纺织学报, 2016, 37(07): 155-161.
[5]	金兰名蒋高明丛洪莲. 纬编提花绗缝织物凹凸曲面的测量及三维建模[J]. 纺织学报, 2016, 37(06): 148-154.