RGB-D: Advanced Reasoning with Depth Cameras

in conjunction with RSS 2010

Update: please stay tuned with the upcoming RGB-D 2011 workshop! It is to be held June 27, 2011 in conjunction with RSS 2011.


Welcome to RGB-D 2010!

This is a full-day workshop in conjunction with the Robotics Science and Systems (RSS) conference 2010. The workshop took place on Sunday, June 27, 2010, at the Universidad de Zaragoza, in Zaragoza, Spain.

Thank you everyone for contributing to the success of the workshop! It was a well-attended, inspiring workshop with many thought-provoking discussions. Presentation slides have been made available; please check out the program section below.

MOTIVATION

The last years have seen dramatic improvements in the capabilities of depth cameras (RGB-D), which provide per pixel RGB and Depth information (as in Microsoft Kinect). The combination of high-resolution depth and visual information opens up new challenges and opportunities for some of the most fundamental research areas in robotics, including 3D mapping and localization, object and activity recognition, people tracking, and object manipulation. Different research communities have made substantial progress in dealing with either 3D depth scans or camera images; it is time to leverage these advances and examine the combination of both.

The goal of this workshop is to bring together some of the leading researchers from robotics, computer vision, and machine learning to present and discuss recent advances in 3D perception techniques developed by these communities. The key outcomes of the workshop will be a better understanding of, (1), the state of the art in 3D perception, (2), the possible applications of RGB-D cameras, and, (3), the key challenges and opportunities for research in this domain.

Workshop Schedule

09:00am - 09:10am Welcome to RGB-D 2010!
09:10am - 09:50am Overview of RGB-D Cameras and Open Research Issues
[ pptx ][ pptx with video ]

Dieter Fox and Xiaofeng Ren
University of Washington, Intel Labs Seattle
09:50am - 10:30am Invited Talk: Time-of-Flight Imaging in Computer Graphics [ ppt ][ ppt with video ]
Christian Theobalt
Max Planck Institute
10:30am - 11:00am Semantic Parsing in Indoor and Outdoor Scenes [ ppt ]
Jana Kosecka
George Mason University
11:00am - 11:30am Coffee Break
11:30am - 11:50am 3D Pose Estimation, Tracking and Model Learning of Articulated Objects from Dense Depth Video using Projected Texture Stereo [ pdf ]
Juergen Sturm, Kurt Konolige, Cyrill Stachniss and Wolfram Burgard
University of Freiburg and Willow Garage
11:50am - 12:10pm Learning Deformable Object Models for Mobile Robot Navigation using Depth Cameras and a Manipulation Robot [ pdf ] [ ppt ][ ppt with video ]
Barbara Frank, Ruediger Schmedding, Cyrill Stachniss, Matthias Teschner and Wolfram Burgard
University of Freiburg
12:10pm - 12:30pm 3D Indoor Mapping for Micro-UAVs Using Hybrid Range Finders and Multi-Volume Occupancy Grids [ pdf ][ ppt ]
William Morris, Ivan Dryanovski and Jizhong Xiao
City College of New York
12:30pm - 01:40pm Lunch Break
01:40pm - 02:20pm Invited Talk: Topological Mapping with Spatial and Visual Appearance [ ppt ]
Paul Newman
Oxford University
02:20pm - 03:00pm 3D Modeling and Object Recognition at Willow Garage
[ pptx ]
Kurt Konolige and Radu Rusu
Willow Garage
03:00pm - 04:00pm Poster Session and Wrap-Ups

Poster Presentations

Online Bundle Adjustment for Indoor Spaces
Kurt Konolige, Willow Garage
RGB-D Mapping: Using Depth Cameras for Dense 3D Modeling of Indoor Environments [ pdf ]
Peter Henry, Michael Krainin, Evan Herbst, Xiaofeng Ren and Dieter Fox
University of Washington and Intel Labs Seattle
Scene Understanding through Audio-Visual Fusion [ pdf ]
Eric Martinson, Ed Lawson and Ben Fransen, Naval Research Laboratory
Sparse Distance Learning for Object Recognition Combining RGB and Depth Information [ pdf ]
Kevin Lai, Liefeng Bo, Xiaofeng Ren and Dieter Fox
University of Washington and Intel Labs Seattle
Surface RRR (Resampling, Reconstruction, Recognition) in PCL (Point Cloud Library)
Radu Rusu, Willow Garage
Vision Only Pose Estimation and Scene Reconstruction on Airborne Platforms [ pdf ]
Michael Warren, David McKinnonraction, He Hu, Michael Shiel, Dawid Preller and Ben Upcroft
University of Queensland and Australasian Council for Interaction Design

Workshop Organizers

Dieter Fox Intel Labs Seattle, University of Washington
Kurt Konolige Willow Garage
Jana Kosecka George Mason University
Xiaofeng Ren Intel Labs Seattle
counter for RSS workshop