Shape Reconstruction of Human Foot from Multi-Camera Images Based on PCA of Human Shape Database

Abstract

Recently, researches and developments for measuring and modeling of human body are taking much attention. Our aim is to capture accurate shape of human foot, using 2D images acquired by multiple cameras, which can capture dynamic behavior of the object. In this paper, 3D active shape models is used for accurate reconstruction of surface shape of human foot. We apply principal component analysis (PCA) of human shape database, so that we can represent human's foot shape by approximately 12 principal component shapes. Because of the reduction of dimensions for representing the object shape, we can efficiently recover the object shape from multi-camera images, even though the object shape is partially occluded in some of input views. To demonstrate the proposed method, two kinds of experiments are presented: high accuracy reconstruction of human foot in a virtual reality environment with CG multi-camera images and in real world with eight CCD cameras. In those experiments, the recovered shape error with our method is around 2mm, while the error is around 4mm with volume intersection method.