Data Capture and Hardware

For capturing foot pressure data, we will be using the T&T Medilogic Foot Pressure Measuring System.  
The Medilogic system consists of two insole pressure sensors (one for each foot) that are inserted in the shoe. Each insole sensor contains 240 pressure sensors and operate at 120hz.

For comparison with motion capture data, we will use the Vicon motion capture system, with 12 cameras operating at 120hz. Additionally we have two force plates that run synchronized with the Vicon mocap system. These two force plates capture ground reaction forces and center of pressure at 960hz.

Abstract

We present a data-driven animation tool that uses foot pressure sensors to control character carrying motions. During an offline training phase, we captured a high dimensional data set of synchronized multimodal motion capture consisting of sole pressure sensors and full body motion capture. Our subjects carried a variety of weighted objects. Our approach provides highly accurate recognition of both the type of carrying motion and weight of the object from only the sole pressure signal. We present a technique for synthesizing carrying motions on characters by overlaying our inverse kinematic algorithm on skeletal motion. We compare the generated animation to ground truth animation created directly from the motion capture data.

Introduction

Hi All!

I am David Yang, a undergraduate at the University of Pennsylvania in the Digital Media Design program., working at the SIG Center for Computer Graphics.

This blog will document my work (with the help of my two Ph.D. advisors Joseph T. Kider Jr. and Aline Normoyle ) on Carry It, a data-driven animation tool that aims to use foot pressure sensors to predict and control character upper body carrying motions.

I plan to document my thoughts, progress and findings on this project through this blog. Hopefully you will find some interesting and cool stuff here. Feel to contact me if you have any comments or questions.

-D