This half-day workshop at ICRA 2015 builds on the highly successful 2014 workshop of the same name by bringing together researchers working in different fields of robotics, computer vision, machine learning and visual neuroscience to discuss novel concepts and ideas for robust vision-based place recognition in severely changing environments.
Such changes – induced by the time of day, weather or seasonal effects as well as human activity – are a ubiquitous challenge for all autonomous systems aiming at long-term operations in both indoor and outdoor settings, and are highly relevant to visual neuroscience. The workshop features a tutorial that introduces the basic principles and the state of the art to participants without previous experience in the field. Two confirmed invited talks by Paul Newman and David Cox and a number of contributed talks discuss the newest developments, concepts and ideas in the areas covered by the workshop topics.
These topics comprise novel techniques for scene matching (both whole-image as well as feature-based), modelling and predicting systematic or repeating appearance changes, as well as learning non-changing or invariant features or exploiting semantic or prior knowledge. The workshop will also address questions of collecting long-term datasets in changing indoor and outdoor environments to enable standardized benchmarks. Finally, we will run an inaugural place recognition challenge in association with the workshop, with prizes to be awarded at the conclusion of the workshop.
- May 19: The list of accepted papers is online (see below). Links to PDFs, will appear shortly before the conference.
- May 19: The program has been updated (see below).
- May 17: The workshop already has 186 registered participants and will be held in Ballroom 6c.
- May 11: Extended deadline for submission of contributed papers
- May 15: Notification of acceptance (submitted papers will be reviewed timely and notification is given shortly after submission to ease planning of conference travel for the participants)
- Tuesday, May 26 2015: Workshop held at ICRA (afternoon session)
Call for Papers
Papers can be submitted by e-mail to email@example.com and should follow the usual ICRA guidelines for style and length (up to 8 pages). The papers will be reviewed and commented by the members of the program committee. The accepted papers will be published on the workshop website.
Papers will be presented in a short talk (expect 3-5 minutes) followed by an interactive poster session on individual screens.
Topics of Interest
Topics of interest to this workshop include, but are not necessarily limited to:
- Novel techniques for change-invariant whole image matching
- Approaches for invariant image feature learning
- Learning, modelling, and predicting systematic or repeating appearance changes over time
- Learning stable / non-changing environmental features
- Exploiting semantic information for long-term place recognition
- Novel concepts of incorporating uncertain place recognition in SLAM / navigation systems
- Standardized benchmarks and long-term datasets in changing environments
We explicitly encourage the submission of papers describing work in progress, preliminary results or novel concepts.
Jake Bruce, Jens Wawerla and Richard Vaughan
|The SFU Mountain Dataset: Semi-Structured Woodland Trails Under Changing Environmental Conditions||PDF|
Ross Finman, Liam Paull, and John J. Leonard
|Toward Object-based Place Recognition in Dense RGB-D Maps ||PDF|
Yanagihara Kentaro, Ando Masatoshi, Chokushi Yuuto, Tanaka Kanji
|An Experimental Study of the Effects of Landmark Discovery and Retrieval on Visual Place Recognition Across Seasons ||PDF|
|Tomáš Krajník, Jaime P. Fentanes, Joaõ M. Santos, Keerthy Kusumam, Tom Duckett ||FreMEn: Frequency Map Enhancement for Long-Term Mobile Robot Autonomy in Changing Environments ||PDF|
Stephanie Lowry and Michael J. Milford
|Change Removal: Robust Online Learning for Changing Appearance and Changing Viewpoint||PDF|
Alejandro Maldonado-Ramírez, L. Abril Torres-Méndez
|Using Super-color-pixels descriptors for Tracking Relevant Cues in Underwater Environments with Poor Visibility Conditions ||PDF|
Olga Vysotska, Cyrill Stachniss
|Lazy Sequences Matching Under Substantial Appearance Changes||PDF|
The workshop will be held in the afternoon of Tuesday, May 26 2015. This is the first day of the conference.
We will be in Ballroom 6c.
|1.30||Welcome and Introduction|
|1.35||Visual Place Recognition - Tutorial and Overview - Peter Corke (Australian Centre for Robotic Vision)|
|2.00||Invited Talk - David Cox (Harvard University)|
|2.30||Place Recognition Challenge - Presentation of Results|
|2.40||Short Presentations of Contributed Papers|
|2.40|| Bruce et al. – The SFU Mountain Dataset: Semi-Structured Woodland Trails Under Changing Environmental Conditions|
|2.45||Finman et al. – Toward Object-based Place Recognition in Dense RGB-D Maps |
|2.50||Kentaro et al. – An Experimental Study of the Effects of Landmark Discovery and Retrieval on Visual Place Recognition Across Seasons |
|2.55||Krajník et al. – FreMEn: Frequency Map Enhancement for Long-Term Mobile Robot Autonomy in Changing Environments |
|3.00||Lowry & Milford – Change Removal: Robust Online Learning for Changing Appearance and Changing Viewpoint|
|3.05||Maldonado-Ramírez et al. – Using Super-color-pixels descriptors for Tracking Relevant Cues in Underwater Environments with Poor Visibility Conditions |
|3.10||Vysotska & Stachniss – Lazy Sequences Matching Under Substantial Appearance Changes|
|3.15||Poster Session of Contributed Papers|
|3.30||Coffee Break and Poster Session|
|4.00||Poster Session continues|
|4.15||Invited Talk - Chi Hay Tong (Mobile Robotics Group, Oxford)|
|4.45||Open Discussion and Conclusions|
|5.00||Wrap-up / Social Event|
The ICRA Place Recognition Challenge
In conjunction with the workshop at ICRA we will organize a place recognition challenge. Participants can test their algorithms for visual place recognition on a challenging dataset and compare results with other participants.
We encourage you to participate in this challenge and send in your results. Please follow this link for information about the challenge and the dataset.
The workshop is organized by Dr Niko Sünderhauf, Dr Michael Milford, and Professor Peter Corke. All organizers are with the Australian Centre for Robotic Vision at QUT in Brisbane, Australia.
Dr Niko Sünderhauf
School of Electrical Engineering and Computer Science
Queensland University of Technology
Brisbane QLD 4000, Australia