Building external anatomical structures from images using a single off-the-shelf camera

Three-dimensional (3D) geometric reconstruction and characterization of the human body from bidimensional (2D) images has been a major research topic in Computer Vision. However, it is still a complex problem to solve, when automation, speed and precision are required. Volumetric based methods are a recent and successful solution for 3D structures reconstruction from images. In this work, using an uncalibrated turntable image sequence, acquired with a single off-the-shelf CCD camera, a 3D geometric model of the structure in cause is built. Our main goal is the reconstruction of 3D shapes of external anatomical structures from images, with good precision and photorealistic appearance. Teresa C. S. Azevedo, Joao M. R. S. Tavares and Mario A. P. Vaz

[1]  Daniel Thalmann.  Human Modelling and Animation , 1993 .

[2]  Thomas Malzbender,et al.  A Survey of Methods for Volumetric Scene Reconstruction from Photographs , 2001, VG.

[3]  Steven M. Seitz,et al.  Photorealistic Scene Reconstruction by Voxel Coloring , 1997, International Journal of Computer Vision.

[4]  Thomas Malzbender,et al.  Generalized Voxel Coloring , 1999, Workshop on Vision Algorithms.

[5]  Zhengyou Zhang,et al.  A Flexible New Technique for Camera Calibration , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  William E. Lorensen,et al.  Marching cubes: A high resolution 3D surface construction algorithm , 1987, SIGGRAPH.

[7]  A. Laurentini,et al.  The Visual Hull Concept for Silhouette-Based Image Understanding , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Richard Szeliski,et al.  Rapid octree construction from image sequences , 1993 .

[9]  Marianne Dooley,et al.  Anthropometric Modeling Programs-A Survey , 1982, IEEE Computer Graphics and Applications.