Application of an Improved ICP Algorithm in Building Registration
In recent years,using multi-source data fusion modeling has become a research hotspot,and the key to multi-source data fu-sion modeling is point cloud registration. The most widely used algorithm for point cloud registration is the Iterative Nearest Point Algorithm (ICP),however,this algorithm has the drawbacks of high requirements for the initial position of the point cloud and slow convergence speed. Therefore,it is proposed to use the Sample Consensus Initial Registration Algorithm ( SAC-IA) for initial registration and the improved ICP algorithm for precise registration for building registration. The experimental results show that this algorithm has greatly improved registration speed and accuracy compared to traditional point cloud registration algorithms.
NETL
NSTL
万方数据
