Comparing Seven Methodogies for Rigid Alignment of Point Clouds with Focus on Frame-to-Frame Registration in Depth Sequences

Authors

  • Fernando Akio Yamada Universidade Federal de Juiz de Fora
  • Gilson Antonio Giraldi National Laboratory for Scientific Computing
  • Marcelo Bernardes Vieira Universidade Federal de Juiz de Fora
  • Liliane Rodrigues Almeida Universidade Federal de Juiz de Fora
  • Antonio Lopes Apolinário Jr. Universidade Federal da Bahia

Keywords:

Rigid registration, Iterative Closest Point, Frame-to-Frame Registration, Depth Images, Rotation Error Metric, Gaussian Mixture, Tensor Shape Descriptors

Abstract

Pairwise rigid registration aims to find the rigid transformation that best registers two surfaces represented by point clouds. This work presents a comparison between seven algorithms, with different strategies to tackle rigid registration tasks. We focus on the frame-to-frame problem, in which the point clouds are extracted from a video sequence with depth information generating partial overlapping 3D data. We use both point clouds and RGB-D video streams in the experimental results. The former is considered under different viewpoints with the addition of a case-study simulating missing data. Since the ground truth rotation is provided, we discuss four different metrics to measure the rotation error in this case. Among the seven considered techniques, the Sparse ICP and Sparse ICP-CTSF outperform the other five ones in the point cloud registration experiments without considering incomplete data. However, the evaluation facing missing data indicates sensitivity for these methods against this problem and favors ICP-CTSF in such situations. In the tests with video sequences, the depth information is segmented in the first step, to get the target region. Next, the registration algorithms are applied and the average root mean squared error, rotation and translation errors are computed. Besides, we analyze the robustness of the algorithms against spatial and temporal sampling rates. We conclude from the experiments using a depth video sequences that ICP-CTSF is the best technique for frame-to-frame registration.

Downloads

Download data is not yet available.

Author Biographies

Fernando Akio Yamada, Universidade Federal de Juiz de Fora

Computer Science Department

Gilson Antonio Giraldi, National Laboratory for Scientific Computing

Area de pesquisa: Computação Gráfica, processamento de imagens e aplicações

Marcelo Bernardes Vieira, Universidade Federal de Juiz de Fora

Computer Science Department

Liliane Rodrigues Almeida, Universidade Federal de Juiz de Fora

Computer Science Department

Antonio Lopes Apolinário Jr., Universidade Federal da Bahia

Computer Science Department

Downloads

Published

2018-08-29

Issue

Section

Special Issue - SVR 2017