In this paper,an improved ICP point cloud registration algorithm based on WHI feature descriptors is proposed to address the problems of poor accuracy,low computational efficiency and susceptibility to noise interference in two step point cloud registration.Firstly,the ISS algorithm is used to extract the feature point set from the point cloud with a large amount of data as the registration point cloud.Then,the WHI feature descriptor of the feature point cloud is calculated,and the random sampling consensus algorithm is used to complete the rough registration.Finally,based on Anderson accelerated iteration,the ICP algorithm performs precise registration on the coarse registration point cloud.The proposed algorithm is verified by multiple sets of point cloud datasets.The experimental results show that the algorithm is highly accurate and fast in alignment,and its advantages are more obvious in datasets containing noise.Under different point cloud models,the proposed algorithm improves the alignment efficiency by more than two times,and has certain robustness in the noise environment.