Skip to end of metadata
Go to start of metadata

Contact Details

Dr Niko Sünderhauf

Postdoctoral Research Fellow

Australian Centre for Robotic Vision 

Robotics and Autonomous Systems
School of Electrical Engineering and Computer Science, Science and Engineering Faculty 
Queensland University of Technology

2 George Street, Brisbane QLD 4000, Australia
Email: niko.suenderhauf@qut.edu.au 
Phone: +61 7 3138 9971

Personal Website: www.nikosuenderhauf.info


News

  • June 2015 I am visiting the robotics researchers of the chair for Automation Technology, lead by Prof. Peter Protzel at Chemnitz University of Technology in Germany.
  • June 2015 Our paper – lead by Michael Milford – won the best workshop paper award at the workshop on computer vision in vehicle technology at CVPR.
  • June 2015 We ran two successful workshops on visual place recognition at the conferences ICRA and CVPR in Seattle and Boston.
  • May 2015 I am visiting the Computer Vision and Geometry Group lead by Marc Pollefeys at ETH in Zürich, Switzerland.
  • April 2015 Our submission to RSS, entitled "Place Recognition With ConvNet Landmarks: Viewpoint-Robust, Condition-Robust, Training-Free" has been accepted.
  • March 2015 The websites for our workshops at ICRA and CVPR are online: ICRA Workshop and CVPR Workshop
  • December 2014 In addition to the workshop at ICRA in May 2015, we will also organize a half-day workshop on place recognition at the CVPR conference in June in Boston.
  • November 2014 We will organize the 2nd edition of the workshop on Visual Place Recognition in Changing Environments at ICRA in Seattle (May 2015). Stay tuned for more news, we will set up a dedicated website in January and post a call for papers and participation soon.
  • October 2014 Our paper "Evaluation of Features for Leaf Classification in Challenging Conditions" has been accepted for publication at the WACV conference in January. In this work we analyzed the performance of different features for the task of leaf classification (given a leaf, identify the plant species). This work is part of our research in agricultural robotics and possible applications are the identification of different weed and crop species for a smarter weed management methods that use less or no herbicides and are therefore much more environment-friendly.
  • August 2014 I joined the Australian Centre for Robotic Vision and will be working on robust vision for spatio-temporal learning of places. This is exciting and I am looking forward to working with all the researchers from our partner universities in Australia and around the world.

Research Interests

My research interests are within the fields of mobile robotics and computer vision. During my PhD thesis (defended in April 2012) I focused on robust graph-based models for probabilistic estimation. More recently, place recognition and environmental perception under changing environments has attracted my attention.

Within the field of mobile robotics, probabilistic techniques for sensor and data fusion and the problem of simultaneous localization and mapping (SLAM) have been fascinating me for a long time. Related questions of visual perception (using monocular, stereo, or RGB-D cameras), such as structure from motion, place recognition or object recognition interest me as well. More recently, the topic of multipath mitigation and how to improve the localization accuracy for satellite-based navigation systems (such as GPS) have drawn my attention.

Besides all these Bayesian, algebraically well-defined techniques to do things, I find biologically inspired approaches for SLAM andperception extremely appealing. 

Software

Vertigo: Versatile Extensions for Robust Inference using Graphical Models

Vertigo provides a C++ implementation of the switchable constraints approach I developed during my thesis. It is an extension library for g2o and gtsam 2.0 and enables g2o or gtsam to solve pose graph SLAM problems in 2D and 3D despite a large number of false positive loop closure constraints. In addition, a re-implementation of the max-mixture model described in (Olson and Agrawal, 2012) for g2o and gtsam is also contained.

Furthermore, Vertigo contains a number of standard pose graph SLAM datasets and a script to spoil them with false positive loop closure constraints. These datasets have been used in our evaluations. They can serve as a set of benchmark datasets for future developments in robust pose graph SLAM.

Download: Vertigo is available at openslam.org. You can use SVN to check it out: svn co https://svn.openslam.org/data/svn/vertigo 

OpenSeqSLAM

OpenSeqSLAM is an open source Matlab implementation of SeqSLAM. SeqSLAM has been originally published by Michael Milford and Gordon Wyeth at ICRA 2012. Read their original paper here. Further information can be found in our own workshop paper for the ICRA workshop on long-term autonomy.

Download: OpenSeqSLAM is available at openslam.org. You can use SVN to check it out: svn co https://svn.openslam.org/data/svn/openseqslam 

Organized Workshops

ConferenceWorkshop ThemeCo-Organizers
ICRA 2015Visual Place Recognition in Changing EnvironmentsPeter Corke, Michael Milford (QUT, Brisbane)
CVPR 2015Visual Place Recognition in Changing EnvironmentsPeter Corke, Michael Milford (QUT, Brisbane), Torsten Sattler (ETH, Zürich)
ICRA 2014Visual Place Recognition in Changing EnvironmentsPeter Corke, Michael Milford (QUT, Brisbane)
ICRA 2013Robust and Multimodal Inference in Factor GraphsJohn Leonard (MIT CSAIL), Edwin Olson (University of Michigan)

Reviews and Community Services

I regularly serve as a reviewer for the major conferences and journals:

  • Journals:
    • IEEE Transactions on Robotics (TRO)
    • International Journal of Robotics Research (IJRR)
    • International Journal of Field Robotics (JFR)
    • Journal on Robotics and Autonomous Systems (RAS)
  • Conferences:
     
    • IEEE International Conference on Robotics and Automation (ICRA) 
    • IEEE International Conference on International Conference on Intelligent Robots and Systems (IROS)
    • IEEE Intelligent Vehicles Symposium

Publications

This list is up to date. You can also find me at Google Scholar.

2015

Sünderhauf, N., Shirazi, S., Jacobson, A., Pepperell, E., Dayoub, F., Upcroft, B., Milford, M. (2015). Place Recognition With ConvNet Landmarks: Viewpoint-Robust, Condition-Robust, Training-Free. Proceedings of Robotics: Science and Systems (RSS), Rome, Italy.

Sünderhauf, N., Upcroft, B., Milford, M. (2015). Continuous Factor Graphs for Holistic Scene UnderstandingComputer Vision and Pattern Recognition (CVPR) Workshop on Scene Understanding (SUNw).

McMahon, S., Sünderhauf, N., Upcroft, B., Milford, M. (2015). How Good Are EdgeBoxes, Really?. Computer Vision and Pattern Recognition (CVPR) Workshop on Scene Understanding (SUNw).

Michael Milford, Chunhua Shen, Stephanie Lowry, Niko Sünderhauf, Sareh Shirazi, Guosheng Lin, Fayao Liu, Edward Pepperell, Cesar Lerma, Ben Upcroft, Ian Reid (2015). Sequence Searching With Deep-Learnt Depth for Condition- and Viewpoint-Invariant Route-Based Place Recognition. Computer Vision and Pattern Recognition (CVPR) Workshop on Computer Vision in Vehicle Technology (CVVT). Best Workshop Paper Award.

Neubert, P., Sünderhauf, N., Protzel, P. (2015). Superpixel-based Appearance Change Prediction for Long-Term Navigation Across Seasons. Robotics and Autonomous Systems Journal.

Hall, DavidMcCool, ChrisDayoub, FerasSünderhauf, Niko, & Upcroft, Ben (2015) Evaluation of features for leaf classification in challenging conditions. In IEEE Winter Conference on Applications of Computer Vision (WACV), Hawaii, USA.

Jürgen Leitner, W. Chamberlain, D. Dansereau, M. Dunbabin, M. Eich, T. Peynot, J. Roberts, R. Russell, N. Sünderhauf (2015). LunaRoo: A Proposal for the Google Lunar XPrize Payload Opportunity with the Part Time Scientists team. Tech Report.

2014 

Sünderhauf, N., McCool, C., Upcroft, B., Perez, T. (2014). Fine-grained plant classification using convolutional neural networks for feature extractionWorking notes of CLEF 2014 conference.

Sünderhauf, N., Neubert, P., Truschzinski, M., Wunschel, D., Pöschmann, J., Lange, S., Protzel, P. (2014). Phobos and Deimos on Mars – Two Autonomous Robots for the DLR SpaceBot Cup. Proc. of International Symposium on Artificial Intelligence, Robotics and Automation in Space (iSAIRAS), Montreal, Canada.

2013 

Neubert,P., Sünderhauf, N., Protzel, P. (2013). Appearance Change Prediction for Long-Term Navigation Across SeasonsProc. of 6th European Conference on Mobile Robots (ECMR), Barcelona, Spain.

Sünderhauf, N., Neubert, P., Protzel, P. (2013). Predicting the Change - A Step Towards Life-Long Operation in Everyday Environments.Proc. of Robotics: Science and Systems (RSS) Robotics Challenges and Vision Workshop, Berlin, Germany.

Sünderhauf, N., Obst, M., Lange, S., Wanielik, G., Protzel, P. (2013). Switchable Constraints and Incremental Smoothing for Online Mitigation of Non-Line-of-Sight and Multipath EffectsProc. of IEEE Intelligent Vehicles Symposium (IV), Gold Coast, Australia

Sünderhauf, N., Lange, S., Protzel, P. (2013). Incremental Sensor Fusion in Factor Graphs with Unknown DelaysProc. of ESA Symposium on Advanced Space Technologies in Robotics and Automation (ASTRA), Noordwijk, the Netherlands .

Sünderhauf, N., Protzel, P. (2013). Switchable Constraints vs. Max-Mixture Models vs. RRR - A Comparison of Three Approaches to Robust Pose Graph SLAMProc. of IEEE International Conference on Robotics and Automation (ICRA), Karlsruhe, Germany.

Sünderhauf, N., Neubert, P., Protzel, P. (2013). Are We There Yet? Challenging SeqSLAM on a 3000 km Journey Across All Four SeasonsProc. of Workshop on Long-Term Autonomy, IEEE International Conference on Robotics and Automation (ICRA), Karlsruhe, Germany.

Lange, S., Sünderhauf, N., Protzel, P. (2013). Incremental Smoothing vs. Filtering for Sensor Fusion on an Indoor UAV. Proc. of IEEE International Conference on Robotics and Automation (ICRA), Karlsruhe, Germany.

2012 

Sünderhauf, N., Protzel, P. (2012). Switchable Constraints for Robust Pose Graph SLAMProc. of IEEE International Conference on Intelligent Robots and Systems (IROS), Vilamoura, Portugal.

Sünderhauf, N., Protzel, P. (2012). A Generic Approach for Robust Probabilistic Estimation with Graphical ModelsProc. of RSS Workshop on Long-term Operation of Autonomous Robotic Systems in Changing Environments, Sydney, Australia.

Sünderhauf, N., Obst, M., Wanielik, G., Protzel, P. (2012). Multipath Mitigation in GNSS-Based Localization using Robust Optimization.Proc. of IEEE Intelligent Vehicles Symposium (IV), Madrid, Spain.

Sünderhauf, N., Protzel, P. (2012). Towards a Robust Back-End for Pose Graph SLAMProc. of IEEE International Conference on Robotics and Automation (ICRA), St. Paul, USA.

Sünderhauf, N. (2012). Robust Optimization for Simultaneous Localization and Mapping. PhD Thesis, Chemnitz University of Technology.

Sünderhauf, N., Protzel, P. (2012). Towards Robust Graphical Models for GNSS-Based Localization in Urban EnvironmentsProc. of the IEEE Intl. Multi-Conference on Systems, Signals and Devices, SSD12, Chemnitz, Germany.

Neubert, P., Sünderhauf, N., Protzel, P. (2012). From Saliency Based Image Features Towards Semantic Mapping. Proc. of 7th German Conference on Robotics, München, Germany.

2011 

Sünderhauf, N., Protzel, P. (2011). BRIEF-Gist -- Closing the Loop by Simple MeansProc. of IEEE International Conference on Intelligent Robots and Systems (IROS), San Francisco, USA.

Lange, S., Sünderhauf, N., Neubert, P., Drews, S., Protzel, P. (2011). Autonomous Corridor Flight of a UAV Using a Low-Cost and Light-Weight RGB-D Camera. Proc. of International Symposium on Autonomous Minirobots for Research and Edutainment (AMiRE), Bielefeld, Germany.

2010 

Sünderhauf, N., Neubert, P., Protzel, P. (2010). The Causal Update Filter - A Novel Biologically Inspired Filter Paradigm for Appearance Based SLAMProc. of IEEE International Conference on Intelligent Robots and Systems (IROS), Taipeh, Taiwan.

Sünderhauf, N., Protzel, P. (2010). From Neurons to Robots: Towards Efficient Biologically Inspired Filtering and SLAMKI 2010: Advances in Artificial Intelligence, Lecture Notes in Computer Science, 6359:341-348, Springer Verlag.

Sünderhauf, N., Protzel, P. (2010). Beyond RatSLAM: Improvements to a Biologically Inspired SLAM SystemProc. of IEEE International Conference on Emerging Technologies and Factory Automation (ETFA), Bilbao, Spain, ISBN 978-1-4244-6848-5.

Sünderhauf, N., Protzel, P. (2010). Learning from Nature: Biologically Inspired Robot Navigation and SLAM - A ReviewKünstliche Intelligenz, Special Issue on SLAM, Springer Verlag.

2009 

Lange, S., Sünderhauf, N., Protzel, P. (2009). A Vision Based Onboard Approach for Landing and Position Control of an Autonomous Multirotor UAV in GPS-Denied EnvironmentsProc. of Int. Conf. on Advanced Robotics 2009, Munich, Germany.

Sünderhauf, N., Protzel, P. (2009). Using Image Profiles and Integral Images for Efficient Calculation of Sparse Optical Flow Fields.Proc. of Int. Conf. on Advanced Robotics 2009, Munich, Germany.

2008 

Lange, S., Sünderhauf, N., Protzel, P. (2008). Autonomous Landing for a Multirotor UAV Using Vision. Workshop Proc. of SIMPAR 2008 Intl. Conf. on Simulation, Modeling and Programming for Autonomous Robots, Venice(Italy), 2008, November, 3-4 ISBN 978-88-95872-01-8 pp. 482-491.

2007 

Sünderhauf, N., Lange, S., Protzel, P. (2007). Using the Unscented Kalman Filter for Mono-SLAM with Inverse Depth Parametrization for Autonomous Airship Control. Proc. of IEEE International Workshop on Safety Security and Rescue Robotics, SSRR 2007, Rome, Italy.

Neubert, P., Sünderhauf, N., Protzel, P. (2007). FastSLAM using SURF Features: An Efficient Implementation and Practical Experiences. Proc. of the International Conference on Intelligent and Autonomous Systems, IAV, Toulouse, Frankreich.

Sünderhauf, N., Protzel, P. (2007). Stereo Odometry - A Review of Approaches. Technical Report 3/07 

Bauer, J., Sünderhauf, N., Protzel, P. (2007). Comparing Several Implementations of Recently Published Feature Detectors. Proc. of the International Conference on Intelligent and Autonomous Systems, IAV, Toulouse, Frankreich.

2006 

Krüger, D., van Lil, I., Sünderhauf, N., Baumgartl R., Protzel, P. (2006). Using and Extending the Miro Middleware for Autonomous Mobile Robots. Proc. of Towards Autonomous Robotic Systems TAROS06, Guildford, UK, pp. 90-95.

Sünderhauf N., Protzel P. (2006) Towards Using Bundle Adjustment for Robust Stereo Odometry in Outdoor Terrain. Proc. of Towards Autonomous Robotic Systems TAROS06, Guildford, UK, pp. 206-213.

Sünderhauf, N., Krause, T., & Protzel, P. (2006). Bringing Robotics Closer to Students - A Threefold Approach. Proc. of IEEE International Conference on Robotics and Automation ICRA06, Orlando, USA, pp. 339-344.

2005 

Sünderhauf, N., Konolige, K., Lacroix, S. & Protzel, P. (2005). Visual Odometry using Sparse Bundle Adjustment on an Autonomous Outdoor Vehicle. In Levi, Schanz, Lafrenz, Avrutin (Hrsg.), Tagungsband Autonome Mobile Systeme 2005, Reihe Informatik aktuell, Springer Verlag, S. 157-163. 

Sünderhauf, N., Krause, T. & Protzel, P. (2005). RoboKing - Bringing Robotics closer to Pupils. Proc. of IEEE International Conference on Robotics and Automation ICRA05, Barcelona, Spain, pp. 4265-4270.

Sünderhauf, N., Konolige, K., Lemaire, T. & Lacroix, S. (2005). Comparison of Stereovision Odometry Approaches. IEEE International Conference on Robotics and Automation ICRA05 Barcelona, Planetary Rover Workshop. 

 

Attended Conferences and Workshops

Conference or WorkshopDatePlace
RSSJuly 2015Rome
CVPRJune 2015Boston
ICRAMay 2015Seattle
CVPRJune 2014Columbus
i-SAIRASJune 2014Montreal
ICRAJune 2014Hong Kong
RSSJune 2013Berlin
ESA ASTRAMay 2013Noordwijk
ICRAMay 2013Karlsruhe
IROSOctober 2012Vilamoura
RSSJuly 2012Sydney
Intelligent Vehicles SymposiumJune 2012Madrid
ICRAMay 2012St. Paul
IROSSeptember 2011San Francisco
euRobotics ForumApril 2011Västerås
IROSOctober 2010Taipeh
KISeptember 2010Karlsruhe
ETFASeptember 2010Bilbao
ICARJune 2009München
SIMPARNovember 2008Venice
SSRR & RRCSeptember 2007Rom
IAVSeptember 2007Toulouse
BIT Tutorial "Robot Middleware and Integration Frameworks"Dezember 2005Bonn
AMSNovember 2005Stuttgart
EURON Summer School Sensor Fusion and PerceptionSeptember 2005Ancona
ICRAApril 2005Barcelona
2nd SLAM Summer SchoolAugust 2004Toulouse
IAVJuly 2004Lissabon
DARSJune 2004Toulouse
AMSNovember 2003Karlsruhe

 

 

 

 


  • No labels