Accurate Overlap Area Detection Using a Histogram and Multiple Closest Points

In this paper, we propose a novel ICP variant that uses a histogram in conjunction with multiple closest points to detect the overlap area between range images geing registered. Tentative correspondences sharing similar distances are normally all within, or all outside, the overlap area. Thus, the overlap area can be detected in a bin by bin batch manner using a histogram. Using multiple closest points is likely to enlarge the distance difference for tentative correspondences in the histogram, and pull together the images being registered, facilitating the overlap area detection. Our experimental results based on real range images show that the performance of our proposed algorithm enhances the state of the art.