News Articles

QUT CyPhy Lab Quadrotor powered by PCL

Our friends and colleagues from QUT (Queensland University of Technology) built a quadrotor robot, that uses PCL and a stripped down Kinect to create 3D maps and navigate around. See the video below for more information, kudos to Inkyu Sa.

Compressing Point Clouds

Julius Kammerl from Technische Universitaet Muenchen, Munich, Germany spent his internship at Willow Garage working on the Point Cloud Library (PCL). To find out more, please watch the video above. You can also read the slides below (download pdf) for more technical details.

Robots such as the PR2 by Willow Garage employ depth sensors for acquiring information about the shape and geometry of their environment. These sensors discretely sample the three dimensional space with high spatial resolution and high update rate and therefore generate large point data sets. Once these so called point clouds have to be stored on the robot or transmitted over rate-limited communication channels, the interest in compressing this kind of data emerges and efficient algorithms for compressing and communicating point clouds become highly relevant. Further applications for point cloud compression can be found in the field of 3D television/conferencing.

In our work we compress the point distribution by performing a spatial decomposition based on octree data structures. Furthermore, by correlating and referencing the…

PCL 1.0!

We're thrilled to announce that Point Cloud Library (PCL) version 1.0 has been released!

PCL 1.0

PCL is a large-scale, cross-platform, open project for point cloud processing that is free for commercial and research use. The PCL framework comprises state-of-the-art algorithms that have endless uses, such as filtering outliers from noisy data, stitching 3D point clouds together, segmenting relevant parts of a scene, extracting keypoints and creating surfaces from point clouds. With the 1.0 release, PCL is now a completely standalone library, using a few "system" dependencies (Boost, Qhull, VTK) with some extra third-party libraries (FLANN, Eigen, CMinpack, OpenNI). The release features a number of changes and updates to help you do more -- and help you do it more easily. A few highlights:

  • Full Linux, Windows and Mac OSX support. If you can connect an OpenNI camera to it, PCL can run on it
  • Complete OpenNI interface for PSDK, Asus WAVI XTion and Kinect. Just hook up your camera and start hacking in 3D
  • Complete Octree interface for point cloud compression, nearest neighbor search, change detection and more
  • Lots of tutorials and demos – with more on the way

A project of this magnitude can only be accomplished with a fantastic…

OpenCV team joins PCL development

Due to a generous grant from nVidia, our friends and collaborators from ITSeez, the maintainers of OpenCV, are joining forces with the PCL development team, in order to provide GPGPU optimizations for PCL.

ITSeez has been proudly developing and maintaining OpenCV for the past few years, and are bringing in a large baggage of Computer Vision algorithmic knowledge and optimizations.

Part of PCL 2.x (development will start soon), we plan to completely integrate GPU accelerations for all our 3D algorithms. Together with the OpenCV team, we will try to concentrate and coagulate our efforts to better support the 2D/3D perception community. Our collaboration started after last year's GTC (see slides below), but will intensify from now onwards.

Bilibot powered by PCL

Our friends and colleagues from MIT built a robot called Bilibot, that uses OpenNI compatible cameras, PCL and ROS, with the purpose to both push the boundaries of technology and train future generations of researchers. Bilibot joins other cheap robotic platforms, including Willow Garage's Turtlebot, in an attempt to create a robotics platform for exploration and create a community of robotics enthusiasts.

The Point Cloud Library allows Bilibot to process the enormous volume of 3D data. Check http://www.bilibot.com/node/36 for more information.

Google Summer Of Code (GSOC) 2011

Our organization was awarded 11 slots for the Google Summer Of Code (GSOC) 2011. It looks like this summer will be a busy one!

We would like to thank all the GSOC students for their applications. It came as a surprise to us how many talented individuals out there want to work with us! We hope to be able to collaborate with all of you, within but also outside GSOC. This is just the beginning.

The list of approved projects for GSOC 2011 is (from PCL's GSOC page), in no order:

  • Alexandru-Eugen Ichim on Geometric Object Recognition;
  • Andreas Mützel on Fast Approximate Nearest Neighbors (KDTree) on GPU;
  • Gabe O'Leary on Tutorials;
  • Gheorghe Lisca on Point Cloud Registration;
  • Gregory Long on Surface Reconstruction with Textures;
  • Ioan Dumitru Dragan on Real-time Segmentation and Tracking;
  • Khai Tran on Surface Reconstruction with Textures;
  • Nick Vanbaelen on Fast Approximate Nearest Neighbours (KDTree) on GPU/multi-core;
  • Pararth Shah on Point Cloud Registration;
  • Roman Shapovalov on Geometric Object Recognition;
  • Siddharth Choudhary on Fast Search Methods (Octrees) on GPU/multi-core;

Mapping with Octree structures

Kai Wurm from the University of Freiburg (Germany) recently visited Willow Garage. During his stay, he worked on integrating the 3D mapping library OctoMap into the ROS and PCL frameworks. To provide real-time 3D maps of the workspace of the PR2 robot, the runtime and memory requirements of OctoMap were substantially reduced. To make OctoMap more attractive for mobile manipulation, he also investigated the use of collections of multi-resolution maps to model movable objects at millimeter resolution.

For more technical information, please see the slides below (download PDF). For more information on using OctoMap with ROS, please see octomap_mapping.

Modular components for point cloud registration

Dirk Holz from the University of Bonn in Germany spent his internship at Willow Garage working on the Point Cloud Library (PCL). He implemented a set of modular components for registering point clouds to create three-dimensional models of objects and environments. The work on the registration part of PCL is a joint effort with other researchers from the PCL community and an ongoing project. Please watch the video above for first demonstrations of what is already achievable or read the slides below (download pdf) for more technical details. The software is available as open source part of the PCL project.

PCL Tutorial at RSS 2011

Tutorial on 3D Point Cloud Processing: PCL (Point Cloud Library)

July 1, 2011 @ USC in Los Angeles, California (full day)

In conjunction with RSS (Robotics: Science and Systems) 2011

 

http://www.pointclouds.org/media/rss2011.html

 

Tutorial Description

With the advent of new, low-cost hardware such as OpenNI compatible cameras and continued efforts in advanced open source 3D point cloud processing, 3D perception gains more and more importance in robotics, as well as other fields. The workshop attempts to motivate new developers and ideas to delve into this subject by offering a tutorial on point cloud processing using the emerging Point Cloud Library (PCL), which presents an advanced and extensive approach to the subject, as well as providing an overview of existing systems applying these techniques. Our goal is to provide an excellent reference material for students and researchers interested in this subject and take our guests through a complete application demonstration (given live) that combines subjects such as filtering, feature estimation, segmentation, registration, object recognition and finally surface reconstruction. The tutorial will be held using OpenNI compatible sensors, so we encourage the audience to bring theirs so we can follow all the steps together. We're…

  • First
  • <<
  • 3
  • 4
  • 5
  • 6
  • 7
  • 8
  • 9
  • >>
  • Last
  • Latest Posts

    Latest Comments