ROCVOct 10, 2020

A Termination Criterion for Probabilistic PointClouds Registration

arXiv:2010.04979v11 citations
Originality Synthesis-oriented
AI Analysis

This work addresses a practical efficiency issue for users of point cloud registration algorithms, but it is incremental as it builds on an existing method.

The paper tackles the problem of determining when to stop the Probabilistic Point Clouds Registration (PPCR) algorithm to avoid unnecessary computational time, and shows that their chosen termination criterion achieves results comparable to using a high number of iterations while saving time.

Probabilistic Point Clouds Registration (PPCR) is an algorithm that, in its multi-iteration version, outperformed state of the art algorithms for local point clouds registration. However, its performances have been tested using a fixed high number of iterations. To be of practical usefulness, we think that the algorithm should decide by itself when to stop, to avoid an excessive number of iterations and, therefore, wasting computational time. With this work, we compare different termination criterion on several datasets and prove that the chosen one produce very good results that are comparable to those obtained using a very high number of iterations while saving computational time.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes