Intrinsic correspondence using statistical signature-based matching for 3D surfaces

A wide variety of applications including object recognition and terrain mapping, rely upon automatic three dimensional surface modelling. The automatic correspondence stage of the modelling process has proven challenging. Intrinsic correspondence methods determine matching segments of partially overlapping 3D surfaces, by using properties intrinsic to the surfaces. These methods do not require initial relative orientations to begin the matching procedures. Hence, intrinsic methods are well-suited for automatic matching. This paper introduces a novel intrinsic automatic correspondence algorithm. Local feature support regions are described using distance and angular metrics, which are used to construct cumulative distribution function signatures. Local correspondences are hypothesised by comparing the signatures of two surfaces. A geometric consistency test is then applied to select the best local correspondences. Finally, registrations are computed from the remaining correspondences and the best alignment is selected. Results demonstrating the algorithm’s accuracy in selecting correspondences for mutual partially overlapping surfaces, are presented. The algorithm’s parameters prove robust, with only the local region size being surface dependent.