Invariant representation, matching and pose estimation of 3D space curves under similarity transformations

摘要

This paper presents a system for matching and pose estimation of 3D space curves under the similarity transformation composed of rotation, translation and uniform scaling. The system makes use of constraints not only on the feature points but also on curve segments. A representation called the similarity-invariant coordinate system (SICS) is presented for deriving semi-local invariants of 3D curves. The SICS also enables an efficient exploration of constraints on the shape of the entire curve. Model-based curve matching is performed in the principle of maximum a posteriori (MAP) probability in which Markov random fields (MRFs) are used to model the prior probability. Results are given to demonstrate the matching with missing and extra feature points. The extensive exploration of the curve shape constraints in both the matching and the pose estimation stages are shown to significantly improve the quality of the recognition and pose estimation.