A Structure-Based Iterative Closest Point Using Anderson Acceleration for Point Clouds with Low Overlap

Abstract

The traditional point-cloud registration algorithms require large overlap between scans, which imposes strict constrains on data acquisition. To facilitate registration, the user has to strategically position or move the scanner to ensure proper overlap. In this work, we design a method of feature extraction based on high-level information to establish structure correspondences and an optimization problem. And we rewrite it as a fixed-point problem and apply the Lie algebra to parameterize the transform matrix. To speed up convergence, we introduce Anderson acceleration, an approach enhanced by heuristics. Our model attends to the structural features of the region of overlap instead of the correspondence between points. The experimental results show the proposed ICP method is robust, has a high accuracy of registration on point clouds with low overlap on a laser datasets, and achieves a computational time that is competitive with that of prevalent methods.