Structured Down-Sampling and Registration Method for 3D Point Cloud of Indoor Scene

Abstract

In this paper, noted by the regular geometric structure of indoor scene, a biased down-sampling scheme is designed to automatically adjust the local sampling rate according to the local density and distribution. Our down-sampling results can effectively remain the main structure while greatly reduce the data number for the following work. Moreover, an improved Iterative Closest Point (ICP) algorithm for point clouds registration is proposed with the prior of structure information. Sampled structured data is weighted to give their contributions for registration. This leads the parameter estimation to naturally focus on aligning the structures of indoor scenes. The experimental results demonstrate the effectiveness of the proposed method on improving the registration accuracy with the same level of down-sampling data.