Cloud Partitioning Iterative Closest Point (CP-ICP): um estudo comparativo para registro de nuvens de pontos 3D

Abstract

In relation to the scientific and technologic evolution of equipment such as cameras and image sensors, the computer vision presents itself more and more as a consolidated engineering solution to issues in diverse fields. Together with it, due to the 3D image sensors dissemination, the improvement and optimization of techniques that deals with 3D point clouds registration, such as the classic algorithm Iterative Closest Point (ICP), appear as fundamental on solving problems such as collision avoidance and occlusion treatment. In this context, this work proposes a sampling technique to be used prior to the ICP algorithm. The proposed method is compared to other five variations of sampling techniques based on three criteria: RMSE (root mean squared error), based also on an Euler angles analysis and an autoral criterion based on structural similarity index (SSIM). The experiments were developed on four distincts 3D models from two databases, and shows that the proposed technique achieves a more accurate point cloud registration in a smaller time than the other techniques.