Call for Papers
The Point Cloud Library (or PCL) is a large scale, open project for 2D/3D image and point cloud processing. Since 2011, PCL grew with an exceptional trend and became a reference library for 3D processing, providing numerous state-of-the art algorithms for filtering, feature estimation, surface reconstruction, registration, model fitting and segmentation and drivers for the most diffused 3D sensors. Moreover, complete pipelines needed for solving a number of complex robot perception problems are also present, such as object recognition and tracking, people detection and large-scale 3D reconstruction. PCL is the backbone of most of perception algorithms for robots equipped with RGB-D sensors, also thanks to its integration with the Robot Operating System. The aim of this workshop is to bring together researchers presenting novel 3D perception algorithms and 3D systems for mobile robots building on the Point Cloud Library, in order to create a forum to discuss advances in 3D Robot Perception and the role that the Point Cloud Library had, has and will have in robotics research and industrial applications.Submissions are encouraged on the following topics:
- 3D data filtering
- 3D keypoint and feature estimation
- segmentation and surface modeling
- point cloud registration
- 3D reconstruction
- 3D object recognition and pose estimation
- people detection and tracking in point clouds
- 3D sensors and drivers
- point cloud compression, streaming and visualization
- 3D robot perception
- 3D data processing in industry
- other applications of the Point Cloud Library
Selected contributions will be presented at the workshop as talks and/or posters. Accepted papers will be inserted in a CD-ROM containing all papers of all conference workshops (tentative title "IAS-13 Workshop Proceedings") with page numbers for each paper and unique ISBN code.
Papers must be written in English and submitted through the EasyChair portal. Please click this link to start the submission process. Authors that do not have an EasyChair account should create one in order to access the submission procedure. Papers must be prepared according the following guidelines:
and must be generated using the Springer templates:
- Latex template – please use llncs.dem as a paper example;
- Microsoft Word template.
Latex is the preferred format. Please follow the instruction included in the zip archives provided. Submission of multimedia attachments showing experimental results is encouraged; accepted file formats are: avi, mpg, wmv.
Important Dates
| Submission open | March 27, 2014 |
| Submission deadline | May 10, 2014 (11:59pm PST) (**extended**) |
| Acceptance notification | June 03, 2014 |
| Camera-ready due | June 17, 2014 |
| Workshop date | July 15, 2014 |
Invited Speakers
Juergen Sturm, Technical University Munich, GermanyScanning and Printing Objects in 3D Abstract: The advancements in 3D printing technology have led to a significant breakthrough in rapid prototyping in recent years. However, generating detailed, printable 3D models is still a cumbersome process and represents a significant amount of work even for a skilled graphical designer. In my talk, I will present our recent work on dense visual odometry and 3D reconstruction that allows us to quickly scan rooms, persons and objects in 3D using an RGB-D camera. To demonstrate this, I will scan a person during my talk and show how the model can be printed as a small figurine. Bio: Dr. Jürgen Sturm worked as a postdoctoral researcher in the Computer Vision and Pattern Recognition group of Prof. Daniel Cremers at the Department of Computer Science of the Technical University of Munich. His major research interests lie in direct localization and mapping techniques for RGB-D cameras. In 2011, he obtained his PhD from the Autonomous Intelligent Systems lab headed by Prof. Wolfram Burgard at the University of Freiburg. He won several awards including the TUM TeachInf best lecture award 2012 and 2013 for his course "Visual Navigation for Flying Robots" and the ECCAI best dissertation award in 2011.
| Time | Speaker | Title |
| 08:45 - 09:15 | Dirk Holz | Approximate Reconstruction and Registration of Surfaces using PCL |
| 09:15 - 09:45 | Sergey Alexandrov | Geometrical Segmentation of Point Cloud Data using Spectral Clustering |
| 09:45 - 10:30 | Juergen Sturm | Invited talk: Scanning and Printing Objects in 3D |
| 10:30 - 11:00 | Mauro Bellone | Road Surface Analysis for Driving Assistance |
| 11:00 - 11:30 | Coffee Break | |
| 11:30 - 12:00 | Matteo Munaro | OpenPTrack: People Tracking for Heterogeneous Networks of Color-Depth Cameras |
| 12:00 - 12:30 | All | Discussion and conclusions |