浏览全部资源
扫码关注微信
Received：24 March 2021，
Revised：30 June 2021，
Accepted：06 July 2021，
Published：16 October 2022
移动端阅览
目的
2
人体尺寸测量是服装制作中的一个重要环节。非接触式人体测量具有效率高、方便快捷的优点，但存在测量精准度较低、对设备和外界环境要求高等问题。为进一步改进这些问题，本文基于卷积神经网络建立模型，相继提出人体分割和关键点检测的方法、基于Bezier曲线的人体肩宽测量方法和基于双椭圆拟合的人体围度测量方法。
方法
2
通过摄像头获取人体的正面、侧面及背面图像；利用Deeplabv3+算法对人体图像进行分割获得人体轮廓，利用OpenPose算法对人体关键点进行检测及定位，利用肩部端点处的角度特征并结合人体肩部关节点信息确定肩部端点，利用肩部曲线与Bezier曲线的相似性通过计算肩部Bezier曲线的长度得到肩宽，通过关键点信息确定胸围、腰围及臀围的宽度和厚度，并建立围度曲线的双椭圆拟合模型，采用线性回归法训练得到拟合模型中的参数，最后利用双椭圆拟合曲线的周长得到人体围度。
结果
2
根据本文方法对100位被测者进行肩宽计算，对132位被测者进行人体围度计算，平均绝对误差均在3 cm以内，符合国家测量标准，且整套方法操作方便，结果稳定。
结论
2
实验验证了本文方法在人体尺寸测量中的精度，降低了非接触式人体测量法对外界环境和设备的依赖程度，提高了系统的鲁棒性，为非接触式人体测量走向实用化打下了坚实基础。
Objective
2
The human body size measurement is developed in garment making based on contact and non-contact methods. The manual contact measurement mainly uses soft ruler and other tools to measure by hand. This method is time costly and inaccuracy
which is not appropriate for large-scaled human body size collection. The intelligent non-contact human body measurement obtains human body size through some equipment and instruments
which has the features of high efficiency
easy use and quick response. Traditional non-contact human body measurement is constrained of external factors
such as single color background and fixed lighting scenario. In addition
the traditional methods extract less number of human key points
or the position of human key points have some deviation for the human body with particular size. To further address these issues
we construct a convolution neural network model and facilitate the method for segmenting human body and detecting the key points. Meanwhile
we focus on the measurement method of shoulder width based on Bezier curve
as well as the measurement method of body circumference based on double ellipse fitting.
Method
2
Three images of the front
side and back of the human body are captured through the camera. The acquired image is segmented using the Deeplavb3+ algorithm and the human body contour is obtained. Lightweight OpenPose algorithm is employed to detect the 13 human body key points
including shoulder joint
elbow joint
wrist joint
hip joint
knee joint
ankle joint
etc. First
the end point of shoulder is identified by integrated information of human shoulder joints because the angle between the tangent lines at the end of shoulder is less than the angle of its surrounding point. The two endpoints of shoulder curve can be regarded as the starting point and the ending point of the quadratic Bezier curve based on the similarity of shoulder curve and Bezier curve. Next
the intersection of the tangent lines of the two ends of shoulder width curve is used as the control point of the quadratic Bezier curve. The shoulder width is obtained by the calculated length of shoulder Bezier curve. The range of waist is determined by the key points of hip joint and elbow joint in the human contour curve. The average waist width and thickness within the range are taken as the width and thickness of the human waist. The waist curve of human body is as two ellipses with equal long axes and unequal short axes. The double ellipse fitting model is established for human circumference curve. The parameters of the double ellipse fitting model are trained by linear regression method. Finally
the waist length of human body is obtained with the circumference of the double ellipse fitting curves. Similarly
the measurement position of chest and hip circumference is roughly determined in accordance with the results of human segmentation and key detected points. The measurement curve of the whole chest and hip circumference is fitted to obtain the curve length.
Result
2
we compare the human key point detection performance of three algorithms
including Lightweight OpenPose
contour-based detection
and human proportion based detection. Our experimental results show that Lightweight OpenPose can extract human key points more accurately.Additionally
we also compare the network results and computation of OpenPose to Lightweight OpenPose. The results show that Lightweight OpenPose can simplify the computation and guarantee the detection accuracy. We select 100 shoulder categories for data evaluation of the measurement of shoulder width
including flat
wide or narrow
and sliding one. We compare the shoulder width measurement performance of three algorithms
including vanishing point and proportion based algorithm
regression analysis and the proposed algorithm. These experimental results demonstrate that our average absolute error of shoulder width measured is less than 2 cm. For the measurement of human circumference
132 samples are selected for data evaluation. For the measurement of waist circumference
we evaluate four methods related to regression analysis method
support vector machine (SVM)-based waist circumference estimation algorithm
direct ellipse fitting method and the proposed algorithm. For the measurement of chest and hip circumference
we carry out the evaluations of three methods like regression analysis method
direct ellipse fitting method and the proposed algorithm. The comparative results show that the average abstract error of the proposed algorithm is within 3 cm
which is suitable for the national measurement standard.
Conclusion
2
Our algorithm evaluate the accuracy of human body size measurement
which reduces the dependence of the non-contact measurement on the external environment and equipment
improves the robustness of the system
and promotes the non-contact measurement in practice. The future research potentials can be improved through the robustness of human body segmentation method
the elimination of hair or other racial bodies on shoulder width and chest circumference measurement
and the detection accuracy of shoulder endpoint and chest positioning. It is challenged that more integrated human body data like chest
waist or hip contour need to be estimated for potential features of individual-based human body size further.
Cao Z, Hidalgo G, Simon T, Wei S E and Sheikh Y. 2021. OpenPose: realtime multi-person 2D pose estimation using part affinity fields. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(1): 172-186 [DOI: 10.1109/TPAMI.2019.2929257]
Chao H, Luximon A and Yeung K W. 2015. Functional 3D human model design: a pilot study based on surface anthropometry and infrared thermography. Computer-Aided Design and Applications, 12(4): 475-484 [DOI: 10.1080/16864360.2014.997644]
Chen L C, Papandreou G, Kokkinos I, Murphy K and Yuille A L. 2018a. DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(4): 834-848 [DOI: 10.1109/TPAMI.2017.2699184]
Chen L C, Zhu Y K, Papandreou G, Schroff F and Adam H. 2018b. Encoder-decoder with atrous separable convolution for semantic image segmentation//Proceedings of the 15th European Conference on Computer Vision. Munich, Germany: Springer: 833-851 [ DOI:10.1007/978-3-030-01234-2_49 http://dx.doi.org/10.1007/978-3-030-01234-2_49 ]
Crease R P. 2010. Invasion of the full-body scanners. Wall Street Journal Eastern Edition.
Deng W Y. 2008. Research on Method of 3D Personalized Human Body Modeling Based on Photos and Neural Network. Hangzhou: Zhejiang University
邓卫燕. 2008. 基于用户照片和神经网络的三维个性化人体建模方法研究. 杭州: 浙江大学
Deng W Y, Lu G D, Wang J and Chen L. 2010. Extraction of feature parameters of three-dimensional human body based on image. Journal of Zhejiang University (Engineering Science), 44(5): 837-840
邓卫燕, 陆国栋, 王进, 陈龙. 2010. 基于图像的三维人体特征参数提取方法. 浙江大学学报(工学版), 44(5): 837-840 [DOI: 10.3785/j.issn.1008-973X.2010.05.001]
General Administration of Quality Supervision, Inspection and Quarantine of the People's Republic of China and Standardization Administration of the People's Republic of China. 2008. GB/T 16160-2008 Location and method of anthropometric surveys for garments. Beijing: Standards Press of China: 1-5
中华人民共和国国家质量监督检验检疫总局, 中国国家标准化管理委员会. 2008. GB/T 16160-2008服装用人体测量的部位与方法. 北京: 中国标准出版社: 1-5
Gittoes M J R, Bezodis I N and Wilson C. 2009. An image-based approach to obtaining anthropometric measurements for inertia modeling. Journal of Applied Biomechanics, 25(3): 265-270 [DOI: 10.1123/jab.25.3.265]
Huang X L. 2009. Research on Measurement of Young Female's Bodies Based on Digital Images. Suzhou: Soochow University
黄秀丽. 2009. 基于数字图像的青年女体测量系统研究. 苏州: 苏州大学
Jiang L Y, Yao J, Li B P, Fang F, Zhang Q and Meng M Q H. 2012. Automatic body feature extraction from front and side images. Journal of Software Engineering and Applications, 5(12B): 94-100 [DOI: 10.4236/jsea.2012.512B019]
Jones P R M, West G M, Harris D H and Read J B. 1989. The loughborough anthropometric shadow scanner (LASS). Endeavour, 13(4): 162-168 [DOI: 10.1016/S0160-9327(89)80004-3]
Lin Y L and Wang M J J. 2011. Automated body feature extraction from 2D images. Expert Systems with Applications, 38(3): 2585-2591 [DOI: 10.1016/j.eswa.2010.08.048]
Lin Y L and Wang M J J. 2012. Constructing 3D human model from front and side images. Expert Systems with Applications, 39(5): 5012-5018 [DOI: 10.1016/j.eswa.2011.10.011]
Meadows D M, Johnson W O and Allen J B. 1970. Generation of surface contours by moiré patterns. Applied Optics, 9(4): 942-947 [DOI: 10.1364/AO.9.000942]
Osokin D. 2018. Real-time 2D multi-person pose estimation on CPU: lightweight OpenPose//Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods. Prague, Czekh: SciTePress
Pan L, Wang J, Yao T and Yu Z J. 2013. Comparison of contact with non-contact measuring data in garment. Journal of Dalian Polytechnic University, 32(2): 140-142
潘力, 王军, 姚彤, 于佐君. 2013. 接触与非接触式人体测量数据比较. 大连工业大学学报, 32(2): 140-142 [DOI: 1674-1404(2013)02-014003]
Qi X and Ji Z P. 2019. Size measurement and fitting based on 3D human body model. Modern Computer, (7): 74-81
齐啸, 计忠平. 2019. 基于三维人体模型的尺寸测量和拟合. 现代计算机, (7): 74-81 [DOI: 10.3969/j.issn.1007-1423.2019.07.016]
Seo D, Kang E, Kim Y M, Kim S Y, Oh I S and Kim M G. 2020. SVM-based waist circumference estimation using Kinect. Computer Methods and Programs in Biomedicine, 191: #105418 [DOI: 10.1016/j.cmpb.2020.105418]
Wang L. 2018. Research on Non-Contacting Human Body Measurement and Modeling Technology Based on Image. Xi′an: Xi′an Polytechnic University
王力. 2018. 基于图像的非接触式人体测量与建模技术研究. 西安: 西安工程大学
Xu F, Zhang H and Zheng R. 2006. Prediction for bust girth using regression analysis from photographic and anthropometric data. Journal of Textile Research, 27(8): 49-52
徐枫, 张浩, 郑嵘. 2006. 照相测量中胸围拟合的回归分析. 纺织学报, 27(8): 49-52 [DOI: 10.3321/j.issn:0253-9721.2006.08.014]
Xu H M, Xia L K, Yang Q, Liu Y J, Tang S Y and Yang J. 2017. Human featured automatic measurement system. Journal of Image and Graphics, 22(2): 225-231
徐慧明, 夏立坤, 杨琪, 刘宇杰, 唐宋元, 杨健. 2017. 新型人体参数自动测量系统. 中国图象图形学报, 22(2): 225-231 [DOI: 10.11834/jig.20170210]
Yan L L and Liang J F. 2008. The quadratic Bezier curves that shape can adjust. Journal of East China Institute of Technology (Natural Science), 31(1): 93-97
严兰兰, 梁炯丰. 2008. 形状可调二次Bezier曲线. 东华理工大学学报(自然科学版), 31(1): 93-97 [DOI: 10.3969/j.issn.1674-3504.2008.01.019]
Zhao Y B, Zhu W M and Wei Y H. 2017. Human body data extraction system based on personalized customization. Shanghai Textile Science and Technology, 45(11): 9-10, 62
赵雅彬, 朱伟明, 卫杨红. 2017. 服装定制人体测量技术的研究. 上海纺织科技, 45(11): 9-10, 62 [DOI: 10.16549/j.cnki.issn.1001-2044.2017.11.003]
相关作者
相关机构
京公网安备11010802024621