3-D Deep Feature Construction for Mobile Laser Scanning Point Cloud Registration

Zhenxin Zhang

doi:10.1109/LGRS.2019.2910546

3-D Deep Feature Construction for Mobile Laser Scanning Point Cloud Registration

2019-12-01

30

PRE

AI

DOI：10.1109/LGRS.2019.2910546

Original

Original request for help

Save

Abstract

En 中文

Due to errors in sensors and positioning, there exist mismatches between different phases of mobile laser scanning point clouds, which impede the application of point cloud, such as changing detection and deformation monitoring. To rectify such mismatches, we designed a 3-D deep feature construction method for point cloud registration. The proposed method combines two 3-D convolutional neural networks into a uniform deep learning model to extract 3-D deep features. First, the corresponding points and noncorresponding points are set to train the deep learning model to minimize the distance between corresponding points' features and maximize the distance between features of noncorresponding points. Second, in the test phase, the 3-D deep feature for each keypoint was extracted by the trained deep learning model. This could be used to determine the corresponding points by the k-dimensional tree and random sample consensus (RANSAC) algorithm. Finally, a transformation matrix was calculated based on the corresponding points and was then applied to point cloud registration. The experimental results illustrated that the proposed method of using 3-D deep features is more efficient at a corresponding point search than representatives of three existing methods. It also improved registration accuracy.

Keywords:

3-D deep features

convolutional neural networks (CNNs)

mobile laser scanning (MLS) point clouds

registration

3-D Deep Feature Construction for Mobile Laser Scanning Point Cloud Registration

Abstract

AI Summary

Journal

Organization