Color Point Cloud Registration Algorithm Based on Hue

Siyu Ren,Yi Wang,Haitao Liang,Huaiyu Cai,Haotian Li,Xiaodong Chen

doi:10.3390/app11125431

Abstract

ICP is a well-known method for point cloud registration but it only uses geometric information to do this, which will result in bad results in some similar structures. Adding color information when registering will improve the performance. However, color information of point cloud, such as gray, varies differently under different lighting conditions. Using gray as the color information to register can cause large errors and even wrong results. To solve this problem, we propose a color point cloud registration algorithm based on hue, which has good robustness at different lighting conditions. We extract the hue component according to the color information of point clouds and make the hue distribution of the tangent plane continuous. The error function consists of color and geometric error of two point clouds under the current transformation. We optimize the error function using the Gauss–Newton method. If the value of the error function is less than the preset threshold or the maximum number of iterations is reached, the current transformation relationship is required. We use RGB-D Scenes V2 dataset to evaluate our algorithm and the results show that the average recall of our algorithms is 8.63% higher than that of some excellent algorithms, and its RMSE of 14.3% is lower than that of the other compared algorithms.

Highlights

With the development of three-dimensional scanning equipment, reconstruction technology has been more and more widely used
The point cloud is an important form of data, and its registration is the process to estimate the transformation between different point cloud according to the overlap between them, different data collected at the different positions can be spliced together according to the transformation relationship between the point clouds to form a whole scene data
We present a color point cloud registration algorithm based on hue, which converts the color information of point cloud from gray to hue for registration in order to improve the robustness under varying lighting conditions

Summary

Introduction

With the development of three-dimensional scanning equipment, reconstruction technology has been more and more widely used. Reconstruction is an important method of modeling in which registration technology plays a crucial role. Because the collection field of the three-dimensional scanning device is limited, only part of the whole scene data can be obtained in one operation. In order to gain complete data, collection operations must be performed several times and spliced together to obtain the whole data. The point cloud is an important form of data, and its registration is the process to estimate the transformation between different point cloud according to the overlap between them, different data collected at the different positions can be spliced together according to the transformation relationship between the point clouds to form a whole scene data

Objectives

Methods

Findings

Conclusion