A new method for the registration of three-dimensional point-sets: The Gaussian Fields framework
作者:
Highlights:
•
摘要
In this paper, we present a 3D automatic registration method based on Gaussian Fields and energy minimization. A continuously differentiable energy function is defined, which is convex in a large neighborhood of the alignment parameters. We show that the size of the region of convergence can be significantly extended reducing the need for close initialization and overcoming local convergence problems of the standard Iterative Closest Point (ICP) algorithms. Moreover, the Gaussian criterion can be applied with linear computational complexity using Fast Gauss Transform methods. Experimental evaluation of the technique using synthetic and real datasets demonstrates the usefulness as well as the limits of the approach.
论文关键词:Rigid registration,Gaussian Fields,Moment invariants,Fast Gauss Transform,Optimization
论文评审过程:Received 18 October 2006, Revised 22 May 2008, Accepted 7 May 2009, Available online 22 May 2009.
论文官网地址:https://doi.org/10.1016/j.imavis.2009.05.003