Extracting Average Shapes from Occluded Non-rigid Motion

This paper presents a method to efficiently estimate average 3-D shapes from non-rigid motion in the case of missing data. Such a shape can be further used to accomplish full reconstruction of deformable objects and registration of non-rigid shapes. The approach is based firstly on a power method which linearly provides an initial estimate of the 3-D structure and motion components of the object shape. Secondly, non-linear optimisation is used to refine the initial linear estimation. Tests on both real and synthetic sequences show the procedure effectiveness in dealing with different degrees of occlusions in the measurements.

• Type: Conference
• Year: 2007
• Where: IBPRIA
• Authors: Alessio Del Bue
• Keywords: Average 3-D Shapes, IBPRIA 2007, Image, Image Analysis, Non-rigid Motion, Non-rigid Shapes