Robust point cloud registration based on topological graph and Cauchy weighted <i>l<sub>q</sub></i> -norm
发布时间：2025-01-07 点击次数：
DOI码：10.1016/j.isprsjprs.2019.12.008
所属单位：School of Remote Sensing and Information Engineering, Wuhan University, China
发表刊物：ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
关键字：Point Cloud Registration (PCR),Coarse-to-fine registration,Feature correspondence,Iterative Closest Point (ICP),Robust estimation
摘要：Point Cloud Registration (PCR) is a fundamental and important issue in photogrammetry and computer vision. Its goal is to find rigid transformations that register multiple 3D point sets. This paper proposes a robust and efficient PCR method based on topological graph and Cauchy weighted l(q)-norm. Our method does not require initializations and is highly robust to outliers and partial overlaps. It contains two major steps: (1) correspondence-based coarse registration, which is called Weighted l(q) Coarse Registration (WCR). In the Wl(q)CR method, we represent feature point sets as topological graphs and transform the point matching problem to an edge matching problem. We build a mathematical model for edge correspondence maximization. We also present an edge voting strategy to distinguish potential correct matches from mismatches. Then, we define a concept called edge vector, which has a property that it is invariant to translations. Based on this property, six Degrees of Freedoms (DoF) PCR problem can be simplified into two three DoF subproblems, i.e., rotation estimation and translation estimation. (2) fine registration based on Weighted l(q) Iterative Closest Point (Wl(q)ICP). We propose a new ICP method called Wl(q)ICP, which is much more robust to partial overlaps compared with traditional ICP. In both rotation estimation and Wl(q)ICP, we use a new Cauchy weighted l(q)-norm (0 < q < 1) instead of l(2)-norm for object function construction, which has a high degree of robustness. Extensive experiments on both simulated and real data demonstrate the power of the proposed method, i.e., our method is more robust (is able to tolerate up to 99% of outliers) and much faster than compared state-of-the-art methods (Wl(q)CR is almost two orders of magnitude faster than RANdom SAmple Consesus (RANSAC) and its variants under 95% of outliers). The source code will be made publicly available in http://www.escience.cn/people/lijiayuan/index.html.
合写作者： Mingyao,Hu,Ai, Qingwu, Pengcheng,Zhao, Jiayuan,Li
论文类型：期刊论文
学科门类：工学
文献类型：J
卷号：160
页面范围：244-259
ISSN号：0924-2716
是否译文：否
CN号：WOS:000510525500017
发表时间：2020-02-01
