Creating Custom Human Avatars for Ergonomic Analysis using Depth Cameras

Ergonomic analysis of industrial tasks is often conducted through the use of human figure modeling software, such as the Jack software from Siemens. Typically, figures are scaled by inputting overall anthropometric dimensions, such as stature, body weight, and erect sitting height. This paper presents a method for rapidly generating a figure that matches the body dimensions and shape of an individual. A system with two Microsoft Kinect depth cameras is used to gather shape data. A statistical body shape model (SBSM) generated from analysis of over 250 men and women is used to fit the data. The output of the shape fitting, expressed as a set of 20 principal component scores, is input to the same male or female SBSM implemented in the Jack software. The result is a figure model that closely matches both the size and shape of the scanned individual. This methodology will be useful for a range of applications for which having a customized manikin is advantageous.

[1]  Matthew P. Reed.  A Pilot Study of Three-Dimensional Child Anthropometry for Vehicle Safety Analysis , 2012 .

[2]  Andrea Fossati,et al.  Consumer Depth Cameras for Computer Vision , 2013, Advances in Computer Vision and Pattern Recognition.

[3]  Matthew P. Reed,et al.  Rapid Generation of Custom Avatars using Depth Cameras , 2014 .

[4]  I. Jolliffe.  Principal Component Analysis , 2002 .

[5]  Michael J. Black,et al.  Home 3D body scans from noisy image and range data , 2011, 2011 International Conference on Computer Vision.

[6]  Georges M. Fadel,et al.  Proceedings of the ASME Design Engineering Technical Conference , 2012, DAC 2012.

[7]  Matthew B. Parkinson,et al.  Developing and Implementing Parametric Human Body Shape Models in Ergonomics Software , 2014 .

[8]  Ian T. Jolliffe,et al.  Principal Component Analysis , 2002, International Encyclopedia of Statistical Science.

[9]  Michael Riis Andersen,et al.  Kinect Depth Sensor Evaluation for Computer Vision Applications , 2012 .

[10]  Matthew B. Parkinson,et al.  MODELING VARIABILITY IN TORSO SHAPE FOR CHAIR AND SEAT DESIGN , 2008, DAC 2008.

[11]  Tomás Pajdla,et al.  3D with Kinect , 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops).

[12]  Ligang Liu,et al.  Scanning 3D Full Human Bodies Using Kinects , 2012, IEEE Transactions on Visualization and Computer Graphics.