An Efficient and Stable Registration Framework for Large Point Clouds at Two Different Moments
Open Access
Abstract
Point cloud registration plays a great role in many application scenarios; however, the registration of large-scale point clouds for actual different moments suffers from the problems of low efficiency, low accuracy, and a lack of stability. In this paper, we propose a registration framework for large-scale point clouds at different moments, which firstly downsamples large-scale point clouds using a random sampling method, then performs a random expansion strategy to make up for the loss of information caused by the random sampling, then completes the first registration by a deep learning network based on the extraction of keypoints and feature descriptors in combination with RANSAC, and finally completes the registration using the point-to-point ICP method. We conducted validation experiments and application experiments on large-scale point clouds of key train components, and the experimental results are much higher in accuracy or efficiency than other methods, which proves the effectiveness of our framework, which can be applied to actual large-scale point clouds.Keywords
This publication has 32 references indexed in Scilit:
- RORNet: Partial-to-Partial Registration Network With Reliable Overlapping RepresentationsIEEE Transactions on Neural Networks and Learning Systems, 2023
- PANet: A Point-Attention Based Multi-Scale Feature Fusion Network for Point Cloud RegistrationIEEE Transactions on Instrumentation and Measurement, 2023
- SACF-Net: Skip-Attention Based Correspondence Filtering Network for Point Cloud RegistrationIEEE Transactions on Circuits and Systems for Video Technology, 2023
- Evolutionary Multiform Optimization With Two-Stage Bidirectional Knowledge Transfer Strategy for Point Cloud RegistrationIEEE Transactions on Evolutionary Computation, 2022
- INENet: Inliers Estimation Network With Similarity Learning for Partial Overlapping RegistrationIEEE Transactions on Circuits and Systems for Video Technology, 2022
- STORM: Structure-Based Overlap Matching for Partial Point Cloud RegistrationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
- DDRNet: Fast point cloud registration network for large-scale scenesISPRS Journal of Photogrammetry and Remote Sensing, 2021
- Scalable non-rigid registration for multi-view stereo dataISPRS Journal of Photogrammetry and Remote Sensing, 2018
- Fast and simple automatic alignment of large sets of range mapsComputers & Graphics, 2015
- A method for registration of 3-D shapesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1992