.png){kind=icon}
.png){kind=icon}
Return
An efficient initial guess for the ICP method
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patrec.2019.07.019.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The iterative closest point (ICP) method is a widely accepted solution for the point-based surface match problem, various improved visions are proposed based on this method. Although various improved visions are proposed, the fundamental of these methods is still the point to point correspondence. In this paper, a pseudo closed form solution is proposed. The proposed method is based on the co-variance matrix. For fully overlapped regions, the proposed method finds the rigid transformation without the point to point correspondence. For partially overlapped point clouds, the proposed method estimates the overlapped regions from a statistic. After the overlapped regions are found, the initial guesses of the ridge transformation are found for each of the corresponding points. Next, the correct correspondences are selected out based on the number of neighbors. Finally, the rigid transformation is found from the correct correspondences. Experiments demonstrate that the proposed method is robust and suit for partially overlapped point clouds. (C) 2019 Elsevier B.V. All rights reserved.
Keywords:
ICP
Statistics
Covariance
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.3
Papers:
7.8K
Citations:
1.6W