Workshop Program
Workshop Program
Program at a Glance
09:20 Welcome and Introduction
09:30 Tutorial on Visual Place Recognition by Peter Corke [ slides ]
10:30 Coffee Break
10:50 Oral Paper Presentations
10:50 Will Maddern, Alexander D. Stewart, Collin McManus, Ben Upcroft, Winston Churchill, and Paul Newman:
"Illumination Invariant Imaging: Applications in Robust Vision-aided Localisation, Mapping and Classification
for Autonomous Vehicles" [ PDF ] [ poster ]
11:10 Nicholas Carlevaris-Bianco and Ryan M. Eustice:
"Learning Visual Feature Descriptors for Dynamic Lighting Conditions" [ PDF ]
11:30 Kirk MacTavish and Timothy D. Barfoot:
"Towards Hierarchical Place Recognition for Long-Term Autonomy" [ PDF ] [ slides ] [ poster ]
11:50 Rares Ambrus, Nils Bore, John Folkesson and Patric Jensfelt:
"Meta-rooms: Building and Maintaining Long Term Spatial Models in a Dynamic World"
12:10 Ross Finman, Thomas Whelan, Liam Paull, and John J. Leonard:
"Physical Words for Place Recognition in Dense RGB-D Maps" [ PDF ]
12:30 Lunch Break
14:00 Invited Talk by Michael Milford: "A multi-pronged attack on the place recognition problem" [ slides ]
14:45 Short Talks of Poster Presentations
14:45 Tayyab Naseer, Luciano Spinello, Wolfram Burgard, Cyrill Stachniss:
"Visual Robot Localization Across Seasons using Network Flows" [ PDF ]
14:50 Nghia Ho, Punarjay Chakravarty:
"Localization on Freeways using the Horizon Line Signature" [ PDF ] [ poster ] [ video ]
14:55 Levente Tamas, Bjoen Jensen:
"All-Season 3D Object Recognition Challenges" [ PDF ] [ slides ] [ poster ]
15:00 K. Rebai, O. Azouaoui, N. Achour:
"HS Combined Histogram for Visual Memory Building and Scene Recognition in Outdoor Environments" [ PDF ]
15:05 Poster Session
15:30 Coffee Break and Poster Session
15:50 Invited Talk by Paul Newman
16:30 Open Discussion and Conclusions
Invited Speakers
• Paul Newman, University of Oxford
• Michael Milford, Queensland University of Technology [ slides ]
Tutorial
• Peter Corke, Queensland University of Technology – Place Recognition Background ad State of the Art [ slides ]