首页 > 最新文献

Proceedings of 3DBODY.TECH 2018 - 9th International Conference and Exhibition on 3D Body Scanning and Processing Technologies, Lugano, Switzerland, 16-17 Oct. 2018最新文献

英文 中文
Designing of Standard-Size Shapes of Heads for Selection from Customized and Mass-Produced Headwear 从定制和批量生产的头饰中选择标准尺寸的头形设计
K. Karavaev, M. Truphanov
The presented research introduces the method along with soft and hardware which allows to design gear and headwear and provides further easy selection of the necessary items among the standard mass produced goods which best match the individual requirements of a client. The paper introduces the results of the research and the developed method along with the description of special soft and hardware which allows the fast and precise selection of an individual item of gear or headwear using the commonly available means. The advantage of the presented method and the means is the combined use of information and data on available size ranges of headwear and protective sports headgear together with individual size and shape of a client’s head, which guarantees reasonable price/quality ratio and allows a client to choose that precise item among the mass-produced goods which provides maximum comfort. Another distinctive feature of the presented approach is that it allows fast selection of the required item by means of creation and further use of the unique code index which defines the shape, size and other individual characteristics of a particular client. To sum up, the devoted solutions which are introduced in this presentation combine the advantages of the customized approach and the selection from the mass-produced gear thus providing the fast and accurate way to choose a particular sports gear item or headwear that best matches the individual requirements of a client.
所提出的研究介绍了该方法以及软、硬件,允许设计齿轮和头饰,并提供进一步方便的选择必要的项目在标准批量生产的产品中,最符合客户的个人要求。本文介绍了研究成果和开发方法,并介绍了特殊的软、硬件,可以使用一般的方法快速、精确地选择单个齿轮或头饰。所提出的方法和手段的优点是结合使用的信息和数据的可用尺寸范围的头罩和保护性运动头罩,以及个人尺寸和形状的客户的头,这保证了合理的价格/质量比,并允许客户选择精确的项目在批量生产的商品,提供最大的舒适度。所提出的方法的另一个显著特征是,它允许通过创建和进一步使用唯一代码索引来快速选择所需的项目,该索引定义了特定客户端的形状、大小和其他个人特征。综上所述,本次介绍的专用解决方案结合了定制方法的优势和批量生产装备的选择,从而提供了快速准确的方法来选择最符合客户个人要求的特定运动装备项目或头饰。
{"title":"Designing of Standard-Size Shapes of Heads for Selection from Customized and Mass-Produced Headwear","authors":"K. Karavaev, M. Truphanov","doi":"10.15221/18.120","DOIUrl":"https://doi.org/10.15221/18.120","url":null,"abstract":"The presented research introduces the method along with soft and hardware which allows to design gear and headwear and provides further easy selection of the necessary items among the standard mass produced goods which best match the individual requirements of a client. The paper introduces the results of the research and the developed method along with the description of special soft and hardware which allows the fast and precise selection of an individual item of gear or headwear using the commonly available means. The advantage of the presented method and the means is the combined use of information and data on available size ranges of headwear and protective sports headgear together with individual size and shape of a client’s head, which guarantees reasonable price/quality ratio and allows a client to choose that precise item among the mass-produced goods which provides maximum comfort. Another distinctive feature of the presented approach is that it allows fast selection of the required item by means of creation and further use of the unique code index which defines the shape, size and other individual characteristics of a particular client. To sum up, the devoted solutions which are introduced in this presentation combine the advantages of the customized approach and the selection from the mass-produced gear thus providing the fast and accurate way to choose a particular sports gear item or headwear that best matches the individual requirements of a client.","PeriodicalId":416022,"journal":{"name":"Proceedings of 3DBODY.TECH 2018 - 9th International Conference and Exhibition on 3D Body Scanning and Processing Technologies, Lugano, Switzerland, 16-17 Oct. 2018","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125751340","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Anthropometric Investigation of Head Measurements for Indian Adults 印度成年人头部测量的人体测量学研究
Parth B. Shah, Y. Luximon, Fang Fu, Vividh Makwana
One of the primary purpose of head related products is to protect the head. To perform their function well, these products need to be in close contact with the head, so in order to ensure a good fit, the designers need accurate anthropometric data. Till date only a few studies have been conducted on Indian adult population to acquire their head shape data and hence there is a need of conducting such studies so as to help in customizing products for Indian population. In this paper authors presents a preliminary investigation of four anthropometric parameters namely head length, width, circumference and anterior height. Thirty male and thirty female adults participated in the study, in which their anthropometric measurements were acquired from 3D head models developed from Computed Tomography (CT) image data. The acquired data was further statistically analyzed to create an understanding of the head shape of Indian adults. The mean values of the acquired data showed the difference in sizes of males and female heads. The analysis also showed a significant correlation between head length and circumference for both male and female participants.
头部相关产品的主要目的之一是保护头部。为了更好地发挥其功能,这些产品需要与头部紧密接触,因此为了确保良好的贴合,设计师需要准确的人体测量数据。迄今为止,仅对印度成年人进行了几项研究,以获取他们的头部形状数据,因此有必要进行此类研究,以帮助为印度人口定制产品。本文作者提出了四个人体测量参数,即头长,宽度,周长和前高的初步调查。30名男性和30名女性成年人参与了这项研究,他们的人体测量数据是通过计算机断层扫描(CT)图像数据开发的3D头部模型获得的。对获得的数据进行进一步的统计分析,以了解印度成年人的头部形状。所得数据的平均值显示了雄性和雌性头部大小的差异。分析还显示,男性和女性参与者的头长和围度之间存在显著的相关性。
{"title":"Anthropometric Investigation of Head Measurements for Indian Adults","authors":"Parth B. Shah, Y. Luximon, Fang Fu, Vividh Makwana","doi":"10.15221/18.114","DOIUrl":"https://doi.org/10.15221/18.114","url":null,"abstract":"One of the primary purpose of head related products is to protect the head. To perform their function well, these products need to be in close contact with the head, so in order to ensure a good fit, the designers need accurate anthropometric data. Till date only a few studies have been conducted on Indian adult population to acquire their head shape data and hence there is a need of conducting such studies so as to help in customizing products for Indian population. In this paper authors presents a preliminary investigation of four anthropometric parameters namely head length, width, circumference and anterior height. Thirty male and thirty female adults participated in the study, in which their anthropometric measurements were acquired from 3D head models developed from Computed Tomography (CT) image data. The acquired data was further statistically analyzed to create an understanding of the head shape of Indian adults. The mean values of the acquired data showed the difference in sizes of males and female heads. The analysis also showed a significant correlation between head length and circumference for both male and female participants.","PeriodicalId":416022,"journal":{"name":"Proceedings of 3DBODY.TECH 2018 - 9th International Conference and Exhibition on 3D Body Scanning and Processing Technologies, Lugano, Switzerland, 16-17 Oct. 2018","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128292927","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
3D Profilomer Combined with Hyperspectral Camera for Simplified Rheumatoid Arthritis Diagnostics 3D轮廓机结合高光谱相机简化类风湿关节炎诊断
U. Pavlovčič, J. Stergar, L. Rogelj, Jure Kosir, M. Jezeršek, M. Milanič
Rheumatoid arthritis is a disease, which significantly impairs patient’s quality of life and ability to work. It has been proven that early diagnosis is of paramount importance, since early treatment has a higher likelihood for improving the course of the disease. Thus, the onset of the disease should be detected as early as possible. Changes in tissue oxygenation, blood concentration, light scattering and joint shape indicate joint inflammation, which could be detected and quantified using optical techniques. That is why a proposed system combines the hyperspectral imaging system and 3D profilometer. It enables measuring a spectrum of the reflected light from small joints with about 1 nm resolution, and a shape of the surface with a precision of about 0.02 mm × 0.13 mm × 0.02 mm. In this study a RA diagnostics prototype comprising of a hyperspectral imaging system and a 3D scanning system is used to aid the rheumatoid arthritis diagnostics.
类风湿关节炎是一种严重影响患者生活质量和工作能力的疾病。事实证明,早期诊断至关重要,因为早期治疗更有可能改善病程。因此,该病的发病应尽早发现。组织氧合、血液浓度、光散射和关节形状的变化表明关节炎症,可以使用光学技术检测和量化。这就是为什么提出的系统结合了高光谱成像系统和3D轮廓仪。它可以测量来自小接头的反射光光谱,分辨率约为1nm,表面形状的精度约为0.02 mm × 0.13 mm × 0.02 mm。在本研究中,一个由高光谱成像系统和3D扫描系统组成的RA诊断原型被用来辅助类风湿关节炎的诊断。
{"title":"3D Profilomer Combined with Hyperspectral Camera for Simplified Rheumatoid Arthritis Diagnostics","authors":"U. Pavlovčič, J. Stergar, L. Rogelj, Jure Kosir, M. Jezeršek, M. Milanič","doi":"10.15221/18.031","DOIUrl":"https://doi.org/10.15221/18.031","url":null,"abstract":"Rheumatoid arthritis is a disease, which significantly impairs patient’s quality of life and ability to work. It has been proven that early diagnosis is of paramount importance, since early treatment has a higher likelihood for improving the course of the disease. Thus, the onset of the disease should be detected as early as possible. Changes in tissue oxygenation, blood concentration, light scattering and joint shape indicate joint inflammation, which could be detected and quantified using optical techniques. That is why a proposed system combines the hyperspectral imaging system and 3D profilometer. It enables measuring a spectrum of the reflected light from small joints with about 1 nm resolution, and a shape of the surface with a precision of about 0.02 mm × 0.13 mm × 0.02 mm. In this study a RA diagnostics prototype comprising of a hyperspectral imaging system and a 3D scanning system is used to aid the rheumatoid arthritis diagnostics.","PeriodicalId":416022,"journal":{"name":"Proceedings of 3DBODY.TECH 2018 - 9th International Conference and Exhibition on 3D Body Scanning and Processing Technologies, Lugano, Switzerland, 16-17 Oct. 2018","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131027617","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
A New Method for Finding the Shoulder Complex Rotation Centre Using 3D Body Scanning 基于三维身体扫描的肩部复合旋转中心定位新方法
S. G. Rozevink, I. Kingma, D. Spies, M. Paalman, Johan F.M. Molenbroek, B. Naagen, M. Maas, G. Streekstra, H. Daanen
To avoid radiation exposure to the body, the rotation centre of the shoulder complex is often assessed using the Optotrak motion capture system instead of X-ray imaging. Recently, 3D body scanning techniques evolved from static to temporal scanning. This study investigated if a time series of 3D body scans may be an alternative for motion capture systems focussing on the shoulder complex rotation centre which is relevant for exoskeleton alignment to the user’s body. 13 Male participants participated in this study (age 24.8±2.4 years, stature 182.2±5.5 cm, body mass 80.7±7.3 kg). Motion capture data (Optotrak) and 3D body scans (3dMD) were collected while the participant performed predefined movements (abduction, anteflexion and a combination of the two). The helical axes method was used to calculate the rotation centre from motion capture data as reference. The 3D scans were processed modelling the upper arm as a cylinder or as a set of perpendicular slices to the centroid axis. Also, a point 30 millimetres below the acromioclavicular joint, assessed from the 3D scan, was defined as the conventional method. The mean distance from the rotation centre of each individual to the mean rotation centre of the cylinder (19 mm), centroid (18 mm), conventional (16 mm) and helical axis method (21 mm) were much smaller than the distances between the 3D scan derived methods and the helical axes method (43-49 mm). The shoulder complex rotation centre location differed considerably between the four methods. Therefore, X-rays of the shoulder are necessary as a golden standard to indicate which method is closest to the real rotation centre and to determine the correction factor for each method that removes the systematic error. 3D body scans contain valuable anthropometric information and have the potential for biomechanical modelling since the random error does not exceed the error of the Optotrak motion capture system.
为了避免身体受到辐射,通常使用Optotrak运动捕捉系统来评估肩部复合体的旋转中心,而不是x射线成像。近年来,人体三维扫描技术从静态扫描发展到时间扫描。这项研究调查了3D身体扫描的时间序列是否可以作为运动捕捉系统的替代方案,该系统专注于肩部复杂的旋转中心,这与外骨骼与用户身体的对齐有关。男性13例,年龄24.8±2.4岁,身高182.2±5.5 cm,体重80.7±7.3 kg。当参与者进行预定的动作(外展、前屈和两者的结合)时,收集运动捕捉数据(Optotrak)和3D身体扫描(3dMD)。以运动捕捉数据为参考,采用螺旋轴法计算旋转中心。3D扫描将上臂建模为一个圆柱体或一组垂直于质心轴的切片。此外,从3D扫描中评估的肩锁关节以下30毫米的点被定义为常规方法。每个个体的平均旋转中心距离柱面(19 mm)、质心(18 mm)、常规(16 mm)和螺旋轴法(21 mm)的平均旋转中心远小于三维扫描衍生方法和螺旋轴法(43-49 mm)之间的距离。四种方法的肩部复合旋转中心位置差异很大。因此,肩部x光片作为黄金标准是必要的,以表明哪种方法最接近真实的旋转中心,并确定每种方法的修正系数,以消除系统误差。3D人体扫描包含有价值的人体测量信息,并且具有生物力学建模的潜力,因为随机误差不会超过Optotrak运动捕捉系统的误差。
{"title":"A New Method for Finding the Shoulder Complex Rotation Centre Using 3D Body Scanning","authors":"S. G. Rozevink, I. Kingma, D. Spies, M. Paalman, Johan F.M. Molenbroek, B. Naagen, M. Maas, G. Streekstra, H. Daanen","doi":"10.15221/18.019","DOIUrl":"https://doi.org/10.15221/18.019","url":null,"abstract":"To avoid radiation exposure to the body, the rotation centre of the shoulder complex is often assessed using the Optotrak motion capture system instead of X-ray imaging. Recently, 3D body scanning techniques evolved from static to temporal scanning. This study investigated if a time series of 3D body scans may be an alternative for motion capture systems focussing on the shoulder complex rotation centre which is relevant for exoskeleton alignment to the user’s body. 13 Male participants participated in this study (age 24.8±2.4 years, stature 182.2±5.5 cm, body mass 80.7±7.3 kg). Motion capture data (Optotrak) and 3D body scans (3dMD) were collected while the participant performed predefined movements (abduction, anteflexion and a combination of the two). The helical axes method was used to calculate the rotation centre from motion capture data as reference. The 3D scans were processed modelling the upper arm as a cylinder or as a set of perpendicular slices to the centroid axis. Also, a point 30 millimetres below the acromioclavicular joint, assessed from the 3D scan, was defined as the conventional method. The mean distance from the rotation centre of each individual to the mean rotation centre of the cylinder (19 mm), centroid (18 mm), conventional (16 mm) and helical axis method (21 mm) were much smaller than the distances between the 3D scan derived methods and the helical axes method (43-49 mm). The shoulder complex rotation centre location differed considerably between the four methods. Therefore, X-rays of the shoulder are necessary as a golden standard to indicate which method is closest to the real rotation centre and to determine the correction factor for each method that removes the systematic error. 3D body scans contain valuable anthropometric information and have the potential for biomechanical modelling since the random error does not exceed the error of the Optotrak motion capture system.","PeriodicalId":416022,"journal":{"name":"Proceedings of 3DBODY.TECH 2018 - 9th International Conference and Exhibition on 3D Body Scanning and Processing Technologies, Lugano, Switzerland, 16-17 Oct. 2018","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114448903","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Prediction of Fat Mass and Validation Using 3D-Whole Body Scanner in Healthy Indian Males 使用3d全身扫描仪预测印度健康男性的脂肪量并验证
L. R. Varte, S. Rawat, I. Singh, Shilpa Choudhary, S. R. Singh
Background: BMI generally overestimates adiposity (i.e. body fat tissue) and underestimates excess body fat on those with less lean body mass. Aim: We wanted to assess the hypothesis that Fat Mass (FM) measured by bio impedance analysis (BIA) is comparable to the predicted Body Fat Mass (BFM) using 3D scanned anthropometric dimensions. Methods: The present paper investigates whether anthropometric measurements using 3D whole body scanner can provide clinically reliable prediction equation to assess adiposity. 3D whole body scanner provides a fast and precise alternative where the scanner gives upto 140 measurements within a few seconds. Intra-and inter-individual error margins in traditional anthropometric measurements frequently arises for large sample studies, besides, manually taking measurements are time-consuming and challenging to perform within acceptable limits. Six hundred and eight (608) healthy adults were scanned using a 3D whole body scanner and their body composition was measured using the Tanita Bipodal bioelectrical impedance analysis (BIA). 486 formed the development group (for the prediction equation) and 20% of the total (i.e. 122 formed the validation group) based on alphabetical order of participant’s name. Linear regressions were performed to predict an equation wherein the body circumferential measurements like Waist Girth, Hip Girth and Chest Girth were predictors and Fat Mass was the dependent variable. Results: Predictive body composition equation based on volumetric body circumference (girth) proposed for healthy Indian males is FM = 0.420 (Waist Girth) + 0.241 (Chest Girth) + 0.051 (Hip Girth) 51.817. The predicted fat mass value was used for the validated population and we did not see much of a difference between the predicted and measured fat mass. The mean age among the 608 volunteers was 32.54 ± 6.3 years, weight was 71.26 kg ±7.8 kg and BMI was 24.1 ± 2.57 kg/mt. Average difference between body fat measured by BIA predicted body fat mass was 0.13 kg, median 0.50 kg, IQR: 0.80 to 0.20 kg, adjusted R 0.74. Conclusions: 3D whole body scanner technology offer defined and accurate automated anthropometric dimensions and measurements of body shape. Further studies are warranted to reveal important relationships between body shape, body composition and metabolic health across sex, age, BMI and ethnicity groups.
背景:BMI通常高估了肥胖(即身体脂肪组织),而低估了瘦体重较少的人体内多余的脂肪。目的:我们想评估通过生物阻抗分析(BIA)测量的脂肪质量(FM)与使用3D扫描人体测量尺寸预测的体脂质量(BFM)相当的假设。方法:研究三维全身扫描仪人体测量是否能提供临床可靠的肥胖预测方程。3D全身扫描仪提供了一种快速和精确的替代方案,扫描仪在几秒钟内提供多达140次测量。传统的人体测量在大样本研究中经常出现个体内和个体间的误差范围,此外,手动测量既耗时又具有挑战性,难以在可接受的范围内完成。采用3D全身扫描仪对668名(608名)健康成人进行扫描,并使用Tanita双足生物电阻抗分析(BIA)测量他们的身体成分。486人组成了开发组(用于预测方程),总人数的20%(即122人组成了验证组)基于参与者姓名的字母顺序。进行线性回归来预测一个方程,其中腰围、臀围和胸围等身体周长测量是预测因子,脂肪量是因变量。结果:印度健康男性基于体围(围)的预测体构成方程为FM = 0.420(腰围)+ 0.241(胸围)+ 0.051(臀围)51.817。预测的脂肪质量值用于验证人群,我们没有看到预测和测量脂肪质量之间的太大差异。608名志愿者平均年龄为32.54±6.3岁,体重为71.26 kg±7.8 kg, BMI为24.1±2.57 kg/mt。BIA测得体脂预测体脂质量的平均差异为0.13 kg,中位数为0.50 kg, IQR为0.80 ~ 0.20 kg,调整后R为0.74。结论:三维全身扫描仪技术提供了定义和准确的自动化人体测量尺寸和体型测量。有必要进行进一步的研究,以揭示体型、身体成分和代谢健康之间的重要关系,这些关系跨越性别、年龄、体重指数和种族群体。
{"title":"Prediction of Fat Mass and Validation Using 3D-Whole Body Scanner in Healthy Indian Males","authors":"L. R. Varte, S. Rawat, I. Singh, Shilpa Choudhary, S. R. Singh","doi":"10.15221/18.195","DOIUrl":"https://doi.org/10.15221/18.195","url":null,"abstract":"Background: BMI generally overestimates adiposity (i.e. body fat tissue) and underestimates excess body fat on those with less lean body mass. Aim: We wanted to assess the hypothesis that Fat Mass (FM) measured by bio impedance analysis (BIA) is comparable to the predicted Body Fat Mass (BFM) using 3D scanned anthropometric dimensions. Methods: The present paper investigates whether anthropometric measurements using 3D whole body scanner can provide clinically reliable prediction equation to assess adiposity. 3D whole body scanner provides a fast and precise alternative where the scanner gives upto 140 measurements within a few seconds. Intra-and inter-individual error margins in traditional anthropometric measurements frequently arises for large sample studies, besides, manually taking measurements are time-consuming and challenging to perform within acceptable limits. Six hundred and eight (608) healthy adults were scanned using a 3D whole body scanner and their body composition was measured using the Tanita Bipodal bioelectrical impedance analysis (BIA). 486 formed the development group (for the prediction equation) and 20% of the total (i.e. 122 formed the validation group) based on alphabetical order of participant’s name. Linear regressions were performed to predict an equation wherein the body circumferential measurements like Waist Girth, Hip Girth and Chest Girth were predictors and Fat Mass was the dependent variable. Results: Predictive body composition equation based on volumetric body circumference (girth) proposed for healthy Indian males is FM = 0.420 (Waist Girth) + 0.241 (Chest Girth) + 0.051 (Hip Girth) 51.817. The predicted fat mass value was used for the validated population and we did not see much of a difference between the predicted and measured fat mass. The mean age among the 608 volunteers was 32.54 ± 6.3 years, weight was 71.26 kg ±7.8 kg and BMI was 24.1 ± 2.57 kg/mt. Average difference between body fat measured by BIA predicted body fat mass was 0.13 kg, median 0.50 kg, IQR: 0.80 to 0.20 kg, adjusted R 0.74. Conclusions: 3D whole body scanner technology offer defined and accurate automated anthropometric dimensions and measurements of body shape. Further studies are warranted to reveal important relationships between body shape, body composition and metabolic health across sex, age, BMI and ethnicity groups.","PeriodicalId":416022,"journal":{"name":"Proceedings of 3DBODY.TECH 2018 - 9th International Conference and Exhibition on 3D Body Scanning and Processing Technologies, Lugano, Switzerland, 16-17 Oct. 2018","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132484167","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Estimating Body Fat from Depth Images: Hand-Crafted Features vs Convolutional Neural Networks 从深度图像中估计身体脂肪:手工制作的特征与卷积神经网络
Marco Carletti, M. Cristani, V. Cavedon, C. Milanese, C. Zancanaro, Andrea Giachetti
In this paper, we compare different approaches to estimate body fat percentages from simple depth images that can be captured by low-cost sensors. We implemented two frameworks, one based on hand-crafted features, using simple image processing methods to estimate directly from images a set of body measurements (e.g. areas, lengths girths), and one based on Convolutional Neural Networks, applying a direct regression from the grayscale maps representing the body depth, based on a pretrained networks. With these frameworks, we evaluated the fat percentage predictions obtained with the different methods on depth images of 350 subjects with known body composition estimated with a DXA scanner. Depth images were generated by extracting the z-buffer from the renderings of the 3D body scan models acquired on the group of subjects. In our validation experiments, we evaluated the effect of different simulated acquisition setups, parameters settings, different image preprocessing and data-augmentation procedures and the addition of priors on height and weight on the prediction accuracy. Furthermore, since the dataset used is composed of professional sportsmen and a control group, we evaluated also the ability of both frameworks of predicting the sport practiced by the subjects with a cross-validation experiment. In specific, we propose a customized ResNet50 regressor to evaluate the whole body fat percentage of the subjects directly from the depth acquisitions. Using the same input data, we also set up a neural classifier to predict the sport category of the athlets. Despite the limited numbers of subjects and the restricted variability of body types (all males, Caucasian, with a small number of obese), the results obtained are promising and can be considered a first step towards the development of quick and cheap body fat estimation tools that can be extremely useful for sport, health and fitness applications.
在本文中,我们比较了从低成本传感器捕获的简单深度图像中估计体脂百分比的不同方法。我们实现了两个框架,一个基于手工制作的特征,使用简单的图像处理方法直接从图像中估计一组身体测量(例如面积,长度,周长),另一个基于卷积神经网络,基于预训练的网络,应用代表身体深度的灰度图的直接回归。利用这些框架,我们评估了用不同方法获得的脂肪百分比预测,这些预测是用DXA扫描仪估计的350名已知身体成分的受试者的深度图像。深度图像是通过从被试组获得的3D身体扫描模型渲染图中提取z缓冲区生成的。在我们的验证实验中,我们评估了不同的模拟采集设置、参数设置、不同的图像预处理和数据增强程序以及添加高度和重量先验对预测精度的影响。此外,由于使用的数据集由专业运动员和对照组组成,我们还通过交叉验证实验评估了这两个框架预测受试者练习运动的能力。具体而言,我们提出了一个定制的ResNet50回归因子,直接从深度采集中评估受试者的全身脂肪百分比。使用相同的输入数据,我们还建立了一个神经分类器来预测运动员的运动类别。尽管受试者数量有限,身体类型的可变性有限(所有男性,高加索人,少数肥胖),但获得的结果是有希望的,可以被认为是朝着开发快速和廉价的身体脂肪估计工具迈出的第一步,这些工具对运动,健康和健身应用非常有用。
{"title":"Estimating Body Fat from Depth Images: Hand-Crafted Features vs Convolutional Neural Networks","authors":"Marco Carletti, M. Cristani, V. Cavedon, C. Milanese, C. Zancanaro, Andrea Giachetti","doi":"10.15221/18.201","DOIUrl":"https://doi.org/10.15221/18.201","url":null,"abstract":"In this paper, we compare different approaches to estimate body fat percentages from simple depth images that can be captured by low-cost sensors. We implemented two frameworks, one based on hand-crafted features, using simple image processing methods to estimate directly from images a set of body measurements (e.g. areas, lengths girths), and one based on Convolutional Neural Networks, applying a direct regression from the grayscale maps representing the body depth, based on a pretrained networks. With these frameworks, we evaluated the fat percentage predictions obtained with the different methods on depth images of 350 subjects with known body composition estimated with a DXA scanner. Depth images were generated by extracting the z-buffer from the renderings of the 3D body scan models acquired on the group of subjects. In our validation experiments, we evaluated the effect of different simulated acquisition setups, parameters settings, different image preprocessing and data-augmentation procedures and the addition of priors on height and weight on the prediction accuracy. Furthermore, since the dataset used is composed of professional sportsmen and a control group, we evaluated also the ability of both frameworks of predicting the sport practiced by the subjects with a cross-validation experiment. In specific, we propose a customized ResNet50 regressor to evaluate the whole body fat percentage of the subjects directly from the depth acquisitions. Using the same input data, we also set up a neural classifier to predict the sport category of the athlets. Despite the limited numbers of subjects and the restricted variability of body types (all males, Caucasian, with a small number of obese), the results obtained are promising and can be considered a first step towards the development of quick and cheap body fat estimation tools that can be extremely useful for sport, health and fitness applications.","PeriodicalId":416022,"journal":{"name":"Proceedings of 3DBODY.TECH 2018 - 9th International Conference and Exhibition on 3D Body Scanning and Processing Technologies, Lugano, Switzerland, 16-17 Oct. 2018","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129690951","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Fast Foot Measurement System Based on 3D Measurement Network 基于三维测量网络的快速足部测量系统
Qijian Tang, Xinyun Liu, Chang Liu, Xiaoli Liu, Menglong Liu, Xiang Peng
A multi-node 3D foot measurement network system is proposed based on digital speckle correlation method. For each node, two cameras build a binocular system, the corresponding points between the left and right cameras are established through the spatial correlation method. In order to improve the search speed of corresponding points, the epipolar and parallax constraints are adopted. The sub-pixel corresponding point location is achieved by Newton-Raphson iterative optimization method to improve the reconstruction accuracy, and the single-node depth data is finally reconstructed based on the stereo vision principle. Multi-view depth data is matched by means of the measurement network calibration technology. The whole foot data acquisition takes less than one second, which has a great commercial application prospect.
提出了一种基于数字散斑相关方法的多节点三维足部测量网络系统。对于每个节点,两台摄像机构建双目系统,通过空间相关法建立左右摄像机之间的对应点。为了提高相应点的搜索速度,采用极差约束和视差约束。采用Newton-Raphson迭代优化方法实现亚像素对应点定位,提高重建精度,最后基于立体视觉原理重建单节点深度数据。采用测量网络标定技术对多视点深度数据进行匹配。整个足部数据采集用时不到1秒,具有很大的商业应用前景。
{"title":"Fast Foot Measurement System Based on 3D Measurement Network","authors":"Qijian Tang, Xinyun Liu, Chang Liu, Xiaoli Liu, Menglong Liu, Xiang Peng","doi":"10.15221/18.170","DOIUrl":"https://doi.org/10.15221/18.170","url":null,"abstract":"A multi-node 3D foot measurement network system is proposed based on digital speckle correlation method. For each node, two cameras build a binocular system, the corresponding points between the left and right cameras are established through the spatial correlation method. In order to improve the search speed of corresponding points, the epipolar and parallax constraints are adopted. The sub-pixel corresponding point location is achieved by Newton-Raphson iterative optimization method to improve the reconstruction accuracy, and the single-node depth data is finally reconstructed based on the stereo vision principle. Multi-view depth data is matched by means of the measurement network calibration technology. The whole foot data acquisition takes less than one second, which has a great commercial application prospect.","PeriodicalId":416022,"journal":{"name":"Proceedings of 3DBODY.TECH 2018 - 9th International Conference and Exhibition on 3D Body Scanning and Processing Technologies, Lugano, Switzerland, 16-17 Oct. 2018","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129441668","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Study of Fashion Accessories Design Based on 3D Printing Technology 基于3D打印技术的服装配饰设计研究
Siyu Chen, Huanyun Wei, Li Zhou
The shape of clothing accessories includes internal styling and external styling. Through analyzing roles that 3D printing plays in spatial relations construction of garment accessories and in realizing these roles through utilizing internal processes and materials, 3D printing's functions in constructing the internal styling of garment accessories are highlighted; through analyzing its applications in functional additions and styling of garment accessories, 3D printing's applications in external styling of garment accessories are also reflected. Based on the manufacturing principle and material properties of 3D printing technology, this paper takes the castle backpack design as the experimental object, carries out experimental analysis and research. In the course of the experiment, 3D printing technology solved the difficulty of the castle modeling, the work is fine and the success rate is higher. The advantages of these experiments can be seen in every design and manufacture. The maturity of 3D printing technology makes the complex and changeable garment accessories design can be obtained by 3D printing technology. The success of the experiment provides a 3D printing technology information library for the design of clothing accessories.
服装配饰的造型包括内部造型和外部造型。通过分析3D打印在服装配饰空间关系构建中的作用,以及利用内部工艺和材料实现这些作用,突出3D打印在服装配饰内部造型构建中的作用;通过分析3D打印在服装配饰的功能添加和造型方面的应用,也体现了3D打印在服装配饰外观造型方面的应用。基于3D打印技术的制造原理和材料特性,本文以城堡背包设计为实验对象,进行实验分析和研究。在实验过程中,3D打印技术解决了城堡建模的难点,做工精细,成功率较高。这些实验的优点在每一个设计和制造中都可以看到。3D打印技术的成熟使得复杂多变的服装辅料设计可以通过3D打印技术获得。实验的成功为服装配饰设计提供了一个3D打印技术信息库。
{"title":"Study of Fashion Accessories Design Based on 3D Printing Technology","authors":"Siyu Chen, Huanyun Wei, Li Zhou","doi":"10.15221/17.084","DOIUrl":"https://doi.org/10.15221/17.084","url":null,"abstract":"The shape of clothing accessories includes internal styling and external styling. Through analyzing roles that 3D printing plays in spatial relations construction of garment accessories and in realizing these roles through utilizing internal processes and materials, 3D printing's functions in constructing the internal styling of garment accessories are highlighted; through analyzing its applications in functional additions and styling of garment accessories, 3D printing's applications in external styling of garment accessories are also reflected. Based on the manufacturing principle and material properties of 3D printing technology, this paper takes the castle backpack design as the experimental object, carries out experimental analysis and research. In the course of the experiment, 3D printing technology solved the difficulty of the castle modeling, the work is fine and the success rate is higher. The advantages of these experiments can be seen in every design and manufacture. The maturity of 3D printing technology makes the complex and changeable garment accessories design can be obtained by 3D printing technology. The success of the experiment provides a 3D printing technology information library for the design of clothing accessories.","PeriodicalId":416022,"journal":{"name":"Proceedings of 3DBODY.TECH 2018 - 9th International Conference and Exhibition on 3D Body Scanning and Processing Technologies, Lugano, Switzerland, 16-17 Oct. 2018","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130785582","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
Proceedings of 3DBODY.TECH 2018 - 9th International Conference and Exhibition on 3D Body Scanning and Processing Technologies, Lugano, Switzerland, 16-17 Oct. 2018
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1