POSE DETERMINATION OF PARAMETERIZED OBJECT MODELS FROM A MONOCULAR IMAGE

Pose determination of parameterized object models plays an important role in verification of model based recognition systems and real-time tracking of objects in images. Described herein is a data structure that models 3D parametric objects. Algorithms are presented for obtaining analytical partial derivatives of distance functions from projected model edges and endpoints to corresponding image segments, with respect to changes in model and camera parameters. These parameters include rotational, translational, scale and dilation in camera and object model. Solving for camera and model parameters in a 2D image (pose determination) is a nonlinear least squares paradigm. Weights are considered for line-to-line and point-to-point matchings to allow for the applicability of the methods to images with noisy data. A number of complex models are tested, and convergence to proper values occurs from a wide range of initial error, using advanced numerical analysis techniques. The experimentation suggests that by treating the model and camera parameters uniformly, correct pose determination can be obtained from minimal matching information relative to the number of matches required per component individually. The robust verification of model parameters thus simplifies associated object recognition problems.