Shape and Pose Parameter Acquisition of 3D Multi-Part Objects on Multiple Viewpoint Image Sequences

Satoshi Yonemoto¹, Naoyuki Tsuruta² and Rin-ichiro Taniguchi¹

¹Department of Intelligent Systems, Kyushu University, 6-1, Kasuga-Koen, Kasuga, Fukuoka 816-8580, Japan
²Department of Electronics Engineering and Computer Science, Fukuoka University, 8-19-1 Nanakuma, Jo-nan-ku, Fukuoka 814-0180, Japan

(Received December 7, 1998; Accepted January 29, 1999)

Keywords: Computer Vision Application, Multi-Part Objects, Motion Analysis

Abstract. This paper presents a shape and pose estimation method for 3D multi-part objects, the purpose of which is to easily map objects in the real world into virtual environments. In general, complex 3D multi-part objects cause unwanted self-occlusion and non-rigid motion. To deal with the problem, here we employ multiple viewpoint image sequences, since there is enough information to estimate the parameters in the sensory data. In our framework, to minimize the error between the selected image feature points and the estimated model parameters, we employ a model fitting procedure which can adaptively select corresponding pairs. We have demonstrated that our system works well for multiple-part objects using the real image sequences.