An improved ICP algorithm for kinect point cloud registration

Ye, Qin; Yao, Yongxue; Gui, Popo; Lin, Yi

doi:10.1109/fskd.2016.7603507

Cited by 7 publications

(1 citation statement)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ICP (Iterative Closest Point) algorithm [11] has been widely used for accurate registration; however, it has the disadvantages of low efficiency and of easily falling into local minima. Therefore, many improved ICP algorithms have been proposed to optimize a part of the iterative process and then to improve the traditional ICP algorithm, including nearest point search [12][13][14][15], feature description [16,17], correspondence building [18,19], and convergence judgment [20]. Among them, feature description can effectively conduct the registration of point clouds with uneven-density and high-noise and therefore improve the performance of the traditional ICP algorithm.…”

Section: Introductionmentioning

confidence: 99%

LIDAR Point Cloud Registration for Sensing and Reconstruction of Unstructured Terrain

Zhu

et al. 2018

Applied Sciences

View full text Add to dashboard Cite

When 3D laser scanning (LIDAR) is used for navigation of autonomous vehicles operated on unstructured terrain, it is necessary to register the acquired point cloud and accurately perform point cloud reconstruction of the terrain in time. This paper proposes a novel registration method to deal with uneven-density and high-noise of unstructured terrain point clouds. It has two steps of operation, namely initial registration and accurate registration. Multisensor data is firstly used for initial registration. An improved Iterative Closest Point (ICP) algorithm is then deployed for accurate registration. This algorithm extracts key points and builds feature descriptors based on the neighborhood normal vector, point cloud density and curvature. An adaptive threshold is introduced to accelerate iterative convergence. Experimental results are given to show that our two-step registration method can effectively solve the uneven-density and high-noise problem in registration of unstructured terrain point clouds, thereby improving the accuracy of terrain point cloud reconstruction.

show abstract