Citation: Wu, A.; Ding, Y.; Mao, J.;
Zhang, X. A Fast Point Clouds
Registration Algorithm Based on
ISS-USC Feature for the 3D Laser
Scanner. Algorithms 2022, 15, 389.
https://doi.org/10.3390/a15100389
Academic Editors: George
Karakostas, Shuai Li, Dechao Chen,
Mohammed Aquil Mirza, Vasilios
N. Katsikis, Dunhui Xiao and
Predrag S. Stanimirovic
Received: 25 September 2022
Accepted: 20 October 2022
Published: 21 October 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
A Fast Point Clouds Registration Algorithm Based on ISS-USC
Feature for the 3D Laser Scanner
Aihua Wu, Yinjia Ding, Jingfeng Mao * and Xudong Zhang
School of Mechanical Engineering, Nantong University, Nantong 226019, China
* Correspondence: mao.jf@ntu.edu.cn
Abstract:
The point clouds registration is a key step in data processing for the 3D laser scanner
to obtain complete information of the object surface, and there are many algorithms. In order to
overcome the disadvantages of slow calculation speed and low accuracy of existing point clouds
registration algorithms, a fast point clouds registration algorithm based on the improved voxel filter
and ISS-USC feature is proposed. Firstly, the improved voxel filter is used for down-sampling to
reduce the size of the original point clouds data. Secondly, the intrinsic shape signature (ISS) feature
point detection algorithm is used to extra feature points from the down-sampled point clouds data,
and then the unique shape context (USC) descriptor is calculated to describe the extracted feature
points. Next, the improved random sampling consensus (RANSAC) algorithm is used for coarse
registration to obtain the initial position. Finally, the iterative closest point (ICP) algorithm based
on KD tree is used for fine registration, which realizes the transform from the point clouds scanned
by the 3D laser scanner at different angles to the same coordinate system. Through comparing with
other algorithms and the registration experiment of the VGA connector for monitor, the experimental
results verify the effectiveness and feasibility of the proposed algorithm, and it has fastest registration
speed while maintaining high registration accuracy.
Keywords:
point clouds registration; voxel filter; intrinsic shape signatures; unique shape context;
random sampling consensus; iterative closest point
1. Introduction
With the rapid development of 3D laser scanning technology, it has been widely
used in many fields such as robotics [
1
], reverse engineering [
2
], geological survey [
3
]
and cultural protection [
4
]. Due to the influence of the angle of the scanning device, the
shape of the scanned object and environmental factors, it is impossible to complete the
data collection of the physical scanning at one time. In order to obtain the complete 3D
information of the object surface, it is necessary to collect data from multiple angles and
blocks of the object, and then splice or register the 3D point clouds collected from different
angles, so as to obtain the point clouds containing complete information of the object under
the same coordinate system.
The point clouds registration [
5
] is a key step to obtain complete information of the
object surface, and it also plays an important role in 3D reconstruction, 3D localization
and pose estimation. Take the palletizing and sorting robot as an example, which have
been widely used in food, medicine, chemical and other automatic production enterprises,
point clouds registration technology is an essential step. It can also provide high-precision
services for intelligent mobile robots.
At present, the most widely used and classic registration algorithm is the iterative
closest point (ICP) algorithm [
6
]. The algorithm is simple, but it requires a good initial
position, and two point clouds must have overlapping parts, otherwise it is easy to fall
into the local optimal solution, which leads to poor final registration effect. In recent
years, researchers have put forward many improvement schemes based on the original
Algorithms 2022, 15, 389. https://doi.org/10.3390/a15100389 https://www.mdpi.com/journal/algorithms
