Registration of combined range-intensity scans: Initialization through verification

This paper presents an automatic registration system for aligning combined rangeintensity scan pairs. The overall approach is designed to handle several challenges including extensive structural changes, large viewpoint differences, repetitive structure, illumination differences, and flat regions. The technique is split into three stages: initialization, refinement, and verification. During initialization, intensity keypoints are backprojected into the scans and matched to form candidate transformations, each based on a single match. We explore methods of improving this image-based matching using the range data. For refinement, we extend the DualBootstrap ICP algorithm for alignment of range data and introduce novel geometric constraints formed by backprojected image-based edgel features. The verification stage determines if a refined transformation is correct. We treat verification as a classification problem based on accuracy, stability, and a novel boundary alignment measure. Experiments with 14 scan pairs show both the overall effectiveness of the algorithm and the importance of its component techniques.