Modeling Adaptive Deformations during Free-Form Pose Estimation

In this article we discuss the 2D-3D pose estimation problem of deformable 3D free-form contours. In our scenario we observe objects of any 3D shape in an image of a calibrated camera. Pose estimation means to estimate the relative position and orientation of the 3D object to the reference camera system. The object itself is modeled as free-form contour. The fusion of modeling free-form contours within the pose estimation problem is achieved by using the conformal geometric algebra: Free-form contours are modeled as unique entities with 3D Fourier descriptors and combined with an ICP (Iterative Closest Point) algorithm they are embedded in the pose problem. The modeling of object deformations within free-form pose estimation is achieved by a combination of adaptive kinematic chain segments within Fourier descriptors.