RGB-D Workshop on 3D Perception in Robotics
Date and Venue:
Abstract:
In the past year, novel camera systems like Microsoft's Kinect that provide both color and dense depth images became readily available. There are great expectations that such systems will lead to a boost of new applications in the field of 3D perception which is particularly relevant for robots operating in unstructured environments and under real-world conditions. Research fields that are expected to benefit from RGB-D-based perception include 3D mapping and localization, path planning, navigation, object recognition, people tracking, activity recognition, and human-robot interaction.
The goal of this workshop is to bring together researchers from robotics and computer vision to present and discuss current approaches on 3D perception using RGB-D sensors in robotics. The key outcomes of the workshop will be to establish an overview over a) the currently available sensor hardware, b) the state-of-the-art in 3D perception, c) the possible applications in industry, and d) stimulate a discussion of the key challenges and opportunities of RGB-D-based perception in robotics.
Topics and Submissions:
We solicit one-page A4 paper abstract submissions, optionally accompanied by a video both of which will be reviewed by the program committee. Topics of interest include (but are not limited to):
- sensor technology, calibration and data pre-processing,
- RGB-D interest points and feature descriptors,
- SLAM and semantic mapping,
- object recognition and localization,
- people tracking and activity recognition,
- navigation,
- industrial applications.
We would especially like to encourage live demos either during the talks or in a special demo session and plan to foster the discussion between the participants in a plenary discussion.
Submission process is closed, thank you very much for a large amount of excellent submissions.
Schedule:
1:00PM Welcome/Introduction (5min)
1:05PM Invited talk: Richard Newcombe - Live Dense Reconstruction with a Single Moving Camera [presentation]
1:35PM Contributed Paper: FAB-MAP 3D: Topological Mapping with Spatial and Visual Appearance (R. Paul and P. Newman) [abstract] [presentation]
1:55PM Contributed Paper: A test bench to improve registration using RGB-D sensors (F. Pomerleau, S. Magnenat, F. Colas, M. Liu, R. Siegwart) [abstract] [presentation]
2:15PM Contributed Paper: Real-time 3D visual SLAM with a hand-held RGB-D camera (N. Engelhard, F. Endres, J. Hess, J. Sturm, W. Burgard) [abstract] [presentation]
2:35PM Contributed Paper: Acting and Interacting in the Real World (J. Bohg, N. Bergstrom, M. Bjorkman, D. Kragic) [abstract] [presentation]
2:55PM Poster/demo overview
3:00PM Coffee break (and poster/demo setup)
3:30PM Demos + Poster session (1h)
- 2D/3D Object Categorization for Task Based Grasping (M. Madry, D. Song, D. Kragic) [abstract] [poster]
- The Articulated Scene Model: Model-less Priors for Robot Object Learning (A. Swadzba, N. Beuter, S. Wachsmuth, F. Kummert) [abstract] [poster]
- Autonomous Corridor Flight of a UAV Using an RGB-D Camera (S. Lange, N. Suenderhauf, P. Neubert, S. Drews, P. Protzel) [abstract] [poster]
- Outdoor terrain traversability analysis for robot navigation using a time-of-flight camera (G. De Cubber, D. Doroftei, H. Sahli, Y. Baudoin) [abstract] [poster]
- 2.5D Local Feature Matching System (E. Strachan, J. P. Siebert) [abstract] [poster]
- Evaluation of 3D Model Accuracy for Automated Unloading of Containers (A. Kirchheim, W. Echelmeyer, T. Stoyanov, A. Louloudi, M. Magnusson, A. Lilienthal) [abstract] [poster]
4.30 Invited talk: Kevin Lai - RGB-D Object Dataset and RGB-D Object Recognition, Detection and Pose Estimation [presentation]
5:00PM Contributed Paper: RGB-D object recognition and localization with clutter and occlusions (F. Tombari, S. Salti, L. Di Stefano) [abstract] [presentation]
5:20PM Contributed Paper: Efficient surface and feature estimation in RGBD (Z.-C. Marton, D. Pangercic, M. Beetz) [abstract] [presentation]
5:40PM Plenum Discussion (20min)
6.00PM End of Workshop
7:00PM Dinner at restaurant
Organizers:
Sponsored by:
Participation:
The workshop is open for everyone. We would kindly ask you to fill-in the following registration form in order to help us estimate the size of the audience group.
Contact:
dejan.pangercic (at) cs.tum.edu
sturm (at) informatik.uni-freiburg.de
