Point Cloud Registration Algorithm Based on the Grey Wolf Optimizer

Yaqing Feng,Zhuang Zhou,Qinglang Su,Binghua Su,Jialin Tang

doi:10.1109/access.2020.3013706

Abstract

In view of the long computation time and low registration accuracy of the current point cloud registration algorithm, a point cloud registration algorithm based on the grey wolf optimizer (GWO) is proposed, denoted PCR-GW. The algorithm uses the centralization method to solve the translation matrix and then simplifies the points of the initial point cloud models by using the intrinsic shape signatures (ISS) feature. Next, various parameters of the rotation matrix are obtained via the GWO algorithm by employing the quadratic sum of the distances between corresponding points in the simplified point cloud as the objective function. Finally, the point cloud registration process is completed by using the obtained transformation matrix. By conducting a registration experiment on the point cloud library model and comparing PCR-GW with the traditional algorithms, the algorithm proposed in this article is shown to be promising for improving the computation speed and registration accuracy.

Highlights

In recent years, 3D reconstruction has been extensively applied in medical images, industrial inspection, self-driving cars, cultural relic reconstruction, and indoor modeling [1]
The results show that grey wolf optimizer (GWO) has a better convergence performance and global search capability than the other algorithms
Our method is compared with 4-point congruent set (4PCS), the algorithm based on fast point feature histogram (FPFH), and the method based on the particle swarm optimization (PSO) algorithm

Summary

Introduction

3D reconstruction has been extensively applied in medical images, industrial inspection, self-driving cars, cultural relic reconstruction, and indoor modeling [1]. It has been widely used in aerospace, agriculture, and other fields. The 3D model is built through the steps of data collection, point cloud registration, surface reconstruction, and texture mapping. In the process of data collection, due to the limited visibility of the scanning system, the scanner needs to scan multiple angles and splice the data to obtain a complete point cloud model. The result of point cloud registration can directly affect the accuracy of the point cloud model; point cloud registration is a key step in the construction of the point cloud model

Methods

Results

Conclusion