PCL Robotics and Automation Magazine Registration Tutorial

 

Publication

Dirk Holz, Alexandru-Eugen Ichim, Federico Tombari, Radu B. Rusu, and Sven Behnke

A modular framework for aligning 3D point clouds - Registration with the Point Cloud Library

Accepted for IEEE Robotics and Automation Magazine, to appear in 2015.



Click on the image to download the full version of the paper:


Datasets

Large-scale 3D Laser Scans

The dataset used for the examples in the paper can be downloaded here: Subsampled Bremen dataset


For more high resolution laser scan datasets, we recommend the dataset collection of the University of Osnabrueck:
Robotic 3D Scan Repository

Sparse Low-resolution 3D Laser Scans

The dataset used for the examples in the paper can be downloaded here: Selected MAV dataset


For more 3D laser scanning data using MAVs, visit the webpage of the University of Bonn:

3D Laser-based Mapping with Micro Aerial Vehicles

Sequences of RGB-D Images

The dataset used for the examples in the paper can be downloaded here:

Sitting table dataset

Toy cars dataset

Other datasets

For more datasets, please visit the pcl dataset webpage, where some of the most popular 3D datasets are indexed:

Source Code

We provide source code set up to experiment with the methods described in the paper. All the projects require PCL 1.7, and are build using CMake. Please check the Point Cloud Library Tutorials on how to set up your system and become familiar with the basic building concepts: http://pointclouds.org/documentation/tutorials/

General Tutorial and RGB-D Registration

Large-scale 3D Laser Scans

Sparse Low-resolution 3D Laser Scans (requires the trunk version of PCL as of 24.06.2015)

Authors:

For further questions or suggestions, please do not hesitate to contact the authors via e-mail.