About

What is PCL?

The Point Cloud Library (or PCL) is a large scale, open project [1] for 2D/3D image and point cloud processing. The PCL framework contains numerous state-of-the art algorithms including filtering, feature estimation, surface reconstruction, registration, model fitting and segmentation. These algorithms can be used, for example, to filter outliers from noisy data, stitch 3D point clouds together, segment relevant parts of a scene, extract keypoints and compute descriptors to recognize objects in the world based on their geometric appearance, and create surfaces from point clouds and visualize them -- to name a few.

 

PCL is released under the terms of the 3-clause BSD license and is open source software. It is free for commercial and research use.

PCL is cross-platform, and has been successfully compiled and deployed on Linux, MacOS, Windows, and Android/iOS. To simplify development, PCL is split into a series of smaller code libraries, that can be compiled separately. This modularity is important for distributing PCL on platforms with reduced computational or size constraints (for more information about each module see the documentation page). Another way to think about PCL is as a graph of code libraries, similar to the Boost set of C++ libraries. Here's an example:

Who is developing PCL?

The project is being developed by a large number of engineers and scientists from many different organizations, geographically distributed all around the world, including:

 

3D Visual Simulations Ltd Aptina, USA National Institute of Advanced Industrial Science and Technology (AIST), Japan Arizona State University (ASU), USA Australian National University (ANU), Australia University of California Berkeley, USA Bielefeld University, Germany University of Bologna, Italy Dinast University of Bonn, Germany University of British Columbia, Canada Brown University, USA Universidad Carlos III de Madrid, Spain ICTI: Information & Communication Technologies Institute - Carnegie Mellon University (CMU), Portugal Eindhoven University of Technology (TU/e), The Netherlands Technical University of Denmark, Denmark University of Extremadura, Spain École Polytechnique Fédérale de Lausanne (EPFL), Switzerland Università degli studi di Firenze, Italy Swiss Federal Institute of Technology (ETH) Zurich, Switzerland Fotonic University of Freiburg, Germany Fraunhofer IPM, Germany Fordham University, USA Georgia Institute of Technology, USA Honda Research Institute, USA Intel, USA Indian Institute of Technology, Bombay, India International Institute of Information Technology, Hyderabad, India Italian National Research Council (ICAR-CNR), Italy ITSeez, Russia Katholieke Universiteit Leuven, Belgium Active Vision Group University of Koblenz-Landau, Germany Korea Institute of Industrial Technology, South Korea University of Houston, USA University of Applied Sciences Kempten, Germany Leica Geosystems, USA Laboratory for Analysis and Architecture of Systems (LAAS/CNRS), France National Research Nuclear University (MEPhI) Obninsk Institute for Nuclear Power Engineering, Russia Universidad de Málaga, Spain Polytechnic University of Ancona, Italy Massachusetts Institute of Technology (MIT), USA MITRE, USA University of Michigan, USA Middle East Technical University, Turkey Moscow State University, Russia National Institute of Standards and Technology (NIST), USA NVidia, USA New York University, USA Open Perception, Inc Optronic Ocular Robotics University of Osnabrück, Germany University of Padua, Italy Queensland University of Technology, Australia Center for Research in Engineering, Media, and Performance, University of California at Los Angeles (UCLA), USA Rochester Institute of Technology (RIT), USA Hochschule Bonn-Rhein-Sieg, Germany Sandia Intelligent Systems and Robotics Scanalyse Spectrolab Inc., a Boeing Company, USA Stanford University, USA Steuart Systems Southwest Research Institute (SwRI), USA TetraVue, USA University of Toronto, Canada Trimble University of Tokyo, Japan Urban Robotics Technical University of Cluj-Napoca, Romania Technische Universität München (TUM), Germany Texas A&M University, USA Toyota Velodyne Acoustics Vienna University of Technology, Austria Willow Garage, USA Washington University in St. Louis, USA

 

Please see the developers website at http://dev.pointclouds.org/ for more details.

Who is financially supporting PCL?

The project is financially supported by Open Perception, Willow Garage, NVidia, Google (GSOC 2011,2012), Toyota, Trimble, Urban Robotics, Honda Research Institute, Sandia Intelligent Systems and Robotics, Dinast, Optronic, Velodyne, Spectrolab, Fotonic, Leica Geosystems, National Institute of Standards and Technology, Southwest Research Institute, Ocular Robotics, TetraVue, Aptina, Intel, and REMAP UCLA. We would also like to thank and acknowledge the support of the Ministry of Knowledge and Economy (MKE) from South Korea, who has generously awarded PCL with the First Prize at the Open Source Software World Challenge in 2011.

Open Perception, Inc Willow Garage nVidia Google Toyota Trimble Urban Robotics Ministry of Knowledge and Economy (MKE), South Korea Honda Research Institute Sandia Intelligent Systems and Robotics Fotonic Ocular Robotics Dinast Velodyne Acoustics Optronic Leica Geosystems, USA Spectrolab Inc., a Boeing Company, USA National Institute of Standards and Technology (NIST), USA Southwest Research Institute (SwRI), USA TetraVue, USA Aptina, USA Intel, USA Center for Research in Engineering, Media, and Performance, University of California at Los Angeles (UCLA), USA

If you're interested in supporting the project in any form (anything from a check to a pat on the shoulder will do), please use the contact form here, or get in touch with us through our host organization, Open Perception. Thank you in advance for your support.

What is a Point Cloud?

A point cloud is a data structure used to represent a collection of multi-dimensional points and is commonly used to represent three-dimensional data. In a 3D point cloud, the points usually represent the X, Y, and Z geometric coordinates of an underlying sampled surface. When color information is present (see the figures below), the point cloud becomes 4D.

Point clouds can be acquired from hardware sensors such as stereo cameras, 3D scanners, or time-of-flight cameras, or generated from a computer program synthetically. PCL supports natively the OpenNI 3D interfaces, and can thus acquire and process data from devices such as the PrimeSensor 3D cameras, the Microsoft Kinect, or the Asus XTionPRO.

OpenNI

For more information about point clouds and 3D processing please visit our documentation page.

References

[1] For more information, including a scientific citation (more to be added soon), please see: 

@InProceedings{Rusu_ICRA2011_PCL,
  author    = {Radu Bogdan Rusu and Steve Cousins},
  title     = {{3D is here: Point Cloud Library (PCL)}},
  booktitle = {{IEEE International Conference on Robotics and Automation (ICRA)}},
  month     = {May 9-13},
  year      = {2011},
  address   = {Shanghai, China}
}

Download PDF here.