PCL Tutorial at RSS 2011
When: July 1, 2011
Where: Robotics: Science and Systems (RSS) 2011, University of Southern California, in Los Angeles, California, USA.
Organizers:
- Radu Bogdan Rusu, Willow Garage
- Bastian Steder, University of Freiburg
- Nico Blodow, Technical University of Munich
- Dirk Holz, University of Bonn
Short 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 assembling a great list of invited speakers that will talk about the usage of PCL in their work and show impressive demos.
List of speakers:
- Nico Blodow, Technische Universität München
- Michael Dixon, Willow Garage
- Suat Gedikli, Willow Garage
- Dirk Holz, Universität Bonn
- Julius Kammerl, Technische Universität München
- Adam Leeper, Stanford University
- Zoltan-Csaba Marton, Technische Universität München
- Marius Muja, University of British Columbia
- Michael Ruhnke, University of Freiburg
- Radu Bogdan Rusu, Willow Garage
- Jochen Sprickerhof, University of Osnabrück
- Bastian Steder, University of Freiburg
Schedule:
| Time | Session name | Title/Author |
| 09:00 - 09:10 | Welcome | Introductions + solve basic technical problems |
| 09:10 - 09:40 | Introduction | Radu B. Rusu Hello, World! |
| 09:40 - 10:00 | PCL I/O (code) | Nico Blodow and Suat Gedikli[*] Learning the PCD format and the Grabber interface. |
| 10:00 - 10:30 | PCL Visualization (part 1, part 2) | Radu B. Rusu and Bastian Steder How to display your data on screen. |
| 10:30 - 10:45 | Coffee & cookies | |
| 10:45 - 11:00 | PCL Filters (I) | Radu B. Rusu Filtering your data: outliers vs inliers. |
| 11:00 - 11:30 | PCL Segmentation + Filters (II) (code) | Nico Blodow Segmenting geometric primitives. The SAmple Consensus (SAC) framework. |
| 11:30 - 11:45 | Invited talk | Adam Leeper, Stanford University Telemanipulation using PCL |
| 11:45 - 12:15 | PCL Keypoints and Features (code) | Michael Dixon and Radu B. Rusu How to estimate 3D features. |
| 12:15 - 13:30 | Lunch | |
| 13:30 - 14:00 | PCL Search | Marius Muja, Julius Kammerl[*] KdTrees and Octrees in PCL. Change detection. Point cloud compression. |
| 14:00 - 14:20 | Invited talk | Nico Blodow and Radu B. Rusu Technology preview: PCL on CUDA |
| 14:20 - 14:45 | PCL Range Images | Bastian Steder Compact range image representations. NARF keypoints and features. Object recognition using NARF. |
| 14:45 - 15:00 | Invited talk | Michael Ruhnke, University of Freiburg Sparse Surface Adjustment - Joint Optimization of Sensor Poses and Surface Points |
| 15:00 - 15:30 | Coffee & cookies | |
| 15:30 - 16:10 | PCL Registration (code) | Jochen Sprickerhof, Dirk Holz[*], Michael Dixon How to align scans in a SLAM framework. Creating 3D object models. Mapping. |
| 16:10 - 16:40 | PCL Surface | Zoltan-Csaba Marton Creating surface meshes from point clouds VFH cluster recognition |
| 16:40 - 17:00 | Join Us! | Radu B. Rusu ...for drinks |
Preparations:
Before the tutorial starts, please make sure that:
- you have a laptop computer with an USB 2.0 port that you can use for the tutorial
- you have a Microsoft Kinect or an Asus XTion Pro camera (or a PSDK) -- please e-mail the organizers if you are unable to get one, and need to borrow a camera
- you have an operating system that PCL supports (see http://www.pointclouds.org/downloads for the list of supported systems)
- you preinstall PCL and its dependencies on your machine