Study on Huizhou architecture of point cloud registration based on optimized ICP algorithm

3rd International Conference on Energy Equipment Science and Engineering

Zhang, Runmei^1 ; Wu, Yulu^1 ; Zhang, Guangbin^1 ; Zhou, Wei^1 ; Tao, Yuqian^1

Anhui Jianzhu University, Hefei, ANHUI

230601, China^1

关键词: Calculation models;    Heavy workloads;    Iterative closest point algorithm;    Local coordinate system;    Point cloud registration;    Processing effects;    Registration methods;    Transformation matrices;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/128/1/012098/pdf
DOI  :  10.1088/1755-1315/128/1/012098

来源: IOP

【 摘 要 】

In view of the current point cloud registration software has high hardware requirements, heavy workload and moltiple interactive definition, the source of software with better processing effect is not open, a two - step registration method based on normal vector distribution feature and coarse feature based iterative closest point (ICP) algorithm is proposed in this paper. This method combines fast point feature histogram (FPFH) algorithm, define the adjacency region of point cloud and the calculation model of the distribution of normal vectors, setting up the local coordinate system for each key point, and obtaining the transformation matrix to finish rough registration, the rough registration results of two stations are accurately registered by using the ICP algorithm. Experimental results show that, compared with the traditional ICP algorithm, the method used in this paper has obvious time and precision advantages for large amount of point clouds.