基于单个kinect红外测量技术的人体着装测量研究
|
摘要
非接触式三维人体自动测量是现代化人体测量技术的主要特征,是人体测量的发展趋势。采用kinect红外扫描仪进行人体着装测量,通过图像拼接技术获取人体3D图像,然后基于图像的人体特征区域和特征参数提取得到人体上衣定制的关键尺寸信息,包括肩宽、胸围、腰围、袖长、上领围和后中长。对由kinect红外扫描仪测量和手工测量的150组人体特征尺寸数据进行统计分析,建立两者的回归关系。结果表明,两者的测量误差小于±2 cm。根据GB 1335—1991《服装号型》国家标准,由kinect红外扫描仪提取的数据通过该回归方程转化后可用于定制服装或者推荐标准服装号型。
Non-contact three-dimensional human body automatic measurement is the main character of a modern measurementtechnology, and also is the development trend of body measurement. A kinect technique is used to scan human body in wearing state, and 3Dimages are obtained with image stitching technology, as well as human characteristics based on the image for customized clothing(includingshoulder width, bust width, waist width, sleeve length, neck around and centre of back). The 150 sets of characteristic size data by kinectIR scanner measurements and manual measurement are statistically analyzed, and the relationship between them is established by regressionmodal. Results show that the measuring error is less than 2cm according to the GB 1335—1991 standards of the garment, the measuring datafrom kinect IR scanner after converting by the regression equation can be used for customized clothing or recommending with standard models.
Non-contact three-dimensional human body automatic measurement is the main character of a modern measurementtechnology, and also is the development trend of body measurement. A kinect technique is used to scan human body in wearing state, and 3Dimages are obtained with image stitching technology, as well as human characteristics based on the image for customized clothing(includingshoulder width, bust width, waist width, sleeve length, neck around and centre of back). The 150 sets of characteristic size data by kinectIR scanner measurements and manual measurement are statistically analyzed, and the relationship between them is established by regressionmodal. Results show that the measuring error is less than 2cm according to the GB 1335—1991 standards of the garment, the measuring datafrom kinect IR scanner after converting by the regression equation can be used for customized clothing or recommending with standard models.
引文
[1]张海波,张艾莉,郭平建.浅析我国服装电子商务应用的现状和发展趋势[J].商场现代化,2009(30):24-25.
[2]李勇,付小莉,尚会超.三维人体测量方法的研究[J].纺织学报,2001,22(4):261-263.
[3]季勇,杨佑国,赵晓.基于网络化的线上服装品牌消费行为影响研究及其创新应用[J].北京服装学院学报:自然科学版,2015(2):64-69.
[4]任倩慧.浅析互联网上原创的服装品牌的营销方式[J].赤子:上中旬,2015(22):238.
[5]陶维冉.服装网络营销目前存在的问题及解决方法[J].科技信息,2012(23):177.
[6]宋红星,李重,倪慧,等.基于近似最短路径的三维人体尺寸提取[J].纺织学报,2011,32(3):138-142.
[7]葛宝臻,郭华婷,彭博,等.基于人体特征提取的模特体型尺寸自动测量方法[J].纺织学报,2012,33(4):129-135.
[8]王云龙.基于三维扫描的人体尺寸测量方法研究[J].自动化技术与应用,2015,34(11):129-135.
[9]Cheung R K,Chen C Y.A two-stage stochastic network model and solution methods for the dynamic empty container allocation problem[J].Transportation Science,1998,32(2):142-162.
[10]Meadows D M,Johnson W O,Allen J B.Generation of surface contours by moirépatterns[J].Applied Optics,1970,9(4):942-947.
[11]Choate A G.Optical and digital processing techniques in a machine vision metrology system[J].Optical Engineering,1989,28(12):1311-1316.
[12]胡智.基于三维重构的人体尺寸测量研究[D].武汉:武汉纺织大学,2013.
[2]李勇,付小莉,尚会超.三维人体测量方法的研究[J].纺织学报,2001,22(4):261-263.
[3]季勇,杨佑国,赵晓.基于网络化的线上服装品牌消费行为影响研究及其创新应用[J].北京服装学院学报:自然科学版,2015(2):64-69.
[4]任倩慧.浅析互联网上原创的服装品牌的营销方式[J].赤子:上中旬,2015(22):238.
[5]陶维冉.服装网络营销目前存在的问题及解决方法[J].科技信息,2012(23):177.
[6]宋红星,李重,倪慧,等.基于近似最短路径的三维人体尺寸提取[J].纺织学报,2011,32(3):138-142.
[7]葛宝臻,郭华婷,彭博,等.基于人体特征提取的模特体型尺寸自动测量方法[J].纺织学报,2012,33(4):129-135.
[8]王云龙.基于三维扫描的人体尺寸测量方法研究[J].自动化技术与应用,2015,34(11):129-135.
[9]Cheung R K,Chen C Y.A two-stage stochastic network model and solution methods for the dynamic empty container allocation problem[J].Transportation Science,1998,32(2):142-162.
[10]Meadows D M,Johnson W O,Allen J B.Generation of surface contours by moirépatterns[J].Applied Optics,1970,9(4):942-947.
[11]Choate A G.Optical and digital processing techniques in a machine vision metrology system[J].Optical Engineering,1989,28(12):1311-1316.
[12]胡智.基于三维重构的人体尺寸测量研究[D].武汉:武汉纺织大学,2013.