picture of me

Helmut Grabner

Computer Vision Laboratory
Department of Information Technology and Electrical Engineering
Eidgenössische Technische Hochschule Zürich
(Swiss Federal Institute of Technology Zurich)


Sternwartstrasse 7, ETZ J78
CH-8092 Zurich, Switzerland

Tel: +41 44 632 4990
Fax: +41 44 632 1199
e-mail: grabner@vision.ee.ethz.ch
www: http://www.vision.ee.ethz.ch/~hegrabne/

News
CV
Publications
Projects
Teaching & Talks
Links

  News

Since beginning 2015 I'm fully employed at Logitech Upicto GmbH.

I am happy to continue my research there, working in a great team and help developing exciting new products.

This web-page is no longer updated!


www.upicto.com
Together with Fabain Nater and
Luc Van Gool I founded upicto GmbH.

Mar. 5,
2015
Paper Accepted: CVPR'15
[Gygli et al., CVPR'15]: Video Summarization by Learning Submodular Mixtures of Objectives
Mar. 5,
2015
Paper Accepted: ICRA'15
[Nussberger et al., ICRA'15]: Robust Aerial Object Tracking in Images with Lens Flare
Jun. 17,
2014
Paper Accepted: ECCV'14
[Gygli et al., ECCV'14]: Creating Summaries from User Videos
Apr. 10,
2014
Paper Accepted: ICUAS'14
[Nussberger et al., ICUAS'14]: Aerial Object Tracking from an Airborne Platform
Sep. 25,
2013
Paper Accepted: ICCV'13
[Gygli et al., ICCV'13]: The Interestingness of Images
Aug. 08,
2013
Paper Accepted: ACM MM'13
[Grabner et al., MM'13]: Visual Interestingness in Image Sequences

  Short CV

Helmut Grabner received a MSc degree (Dipl.-Ing.) in Telematics and a PhD degree (Dr.techn) in Computer Science, both from Graz University of Technology in 2004 and 2008, respectively. He is currently a post doc researcher at the Computer Vision Lab at ETH-Zurich. His research interests are mainly on-line and incremental machine learning for computer vision (e.g., object detection, tracking, recognition and event detection) in particular in the field of visual surveillance.
In 2011 he co-founded upicto GmbH. upicto offers technology for the automated processing of video data and is a direct consequence from research at the Computer Vision Lab at ETH-Zurich. In 2015 upicto GmbH was acquired by Logitech.



  Selected Publications

click here for all publications
Visual Interestingness & Video Summarization

Video Summarization by Learning Submodular Mixtures of Objectives
M. Gygli, H. Grabner, and L.Van Gool
In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015

Supplementary Material
see project web-page (coming soon)

Creating Summaries from User Videos
M. Gygli, H. Grabner, H. Riemenschneider, and L.Van Gool
In Proceedings European Conference on Computer Vision (ECCV), 2014

Supplementary Material
see project web-page


The Interestingness of Images
M. Gygli, H. Grabner, H. Riemenschneider, F. Nater, and L. Van Gool

In Proceedings International Conference on Computer Vision (ICCV), 2013, Poster

Supplementary Material
see project web-page


Visual Interestingness in Image Sequences
H. Grabner, F. Nater, M. Druey, and L. Van Gool
In Proceedings ACM International Conference on Multimedia (MM), 2013, Talk

Supplementary Material
Dataset and human consensus base-line

Affordance Detection

 

What Makes a Chair a Chair?
H. Grabner, J. Gall, and L. Van Gool
In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011, Poster

Supplementary Material
Full resolution ranking lists (Fig. 7), our approach, appearance
Chair-Dataset

Context in Object Detection and Tracking


Robust Aerial Object Tracking in Images with Lens Flare.
A. Nussberger, H. Grabner, and L. Van Gool
In Proceedings International Conference on Robotics and Automation (ICRA), 2015


Aerial Object Tracking from an Airborne Platform
A. Nussberger, H. Grabner, and L. Van Gool
In Proceedings International Conference on Unmanned Aircraft Systems (ICUAS), 2014

Dynamic Objectness for Adaptive Tracking
S. Stalder, H. Grabner, and L. Van Gool
In Proceedings Asian Conference on Computer Vision (ACCV), 2012, Poster

Tracking the Invisible: Learning Where the Object Might be
H. Grabner, J. Matas, L. Van Gool, and P. Cattin
In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010, Talk,Video Lecture

Cascaded Confidence Filtering for Improved Tracking-by-Detection
S. Stalder, H. Grabner, and L. Van Gool
In Proceedings European Conference on Computer Vision (ECCV), 2010, Poster

overview

Exploring Context to Learn Scene Specific Object Detectors
S. Stalder, H. Grabner, and L. van Gool
In Proceedings CVPR09 Workshop on Performance Evaluation of Tracking and Surveillance (PETS), 2009

Realted (previous) work:
Classifier Grids for Robust Adaptive Object Detection
S. Sternig, P. Roth, H. Grabner, and H. Bischof
In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2009
Exploiting Temporal Structure in Image Sequences


Temporal Relations in Videos for Unsupervised Activity Analysis
F. Nater, H. Grabner, and L. Van Gool
In Proceedings British Machine Vision Conference (BMVC), 2011

Videos:
Supplementary Material




Unsupervised Workow Discovery in Industrial Environments
F. Nater, H. Grabner, and L. Van Gool
InProceedings ICCV’11 WS on Visual Surveillance, 2011

Related Work:
Automatic Workflow Monitoring in Industrial Environments
G. Veres, H. Grabner, L. Middleton, and L. Van Gool
In Proceedings Asian Conference on Computer Vision (ACCV), 2010



Keep Breathing! Common Motion Helps Multi-modal Mapping
V. De Luca, H. Grabner, L. Petrusca, R. Salomi, G. Szekely, and C. Tanner
In Proceedings International Conference on Medical Computing and Computer Assisted Intervention (MICCAI), 2011



Boosting based Trackers





Beyond Semi-Supervised Tracking: Tracking Should Be as Simple as Detection, but not Simpler than Recognition
S. Stalder, H. Grabner, and L. Van Gool
In Proceedings ICCV’09 WS on On-line Learning for Computer Vision, 2009

updateGif Binaries/Code/Evaluations:
see project web-page



Semi-supervised On-line Boosting for Robust Tracking
H. Grabner, C. Leistner, and H. Bischof
In Proceedings European Conference on Computer Vision (ECCV), 2008, Poster



overview Real-time Tracking via On-line Boosting
H. Grabner, M. Grabner, and H. Bischof. 
In Proceedings British Machine Vision Conference (BMVC), volume 1, pages 47-56, 2006, Talk

Video:
"Tracking Shrek and others"

M. Grabner, H. Grabner, and H. Bischof
In Video Proceedings in conjunction with IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2006


Event Detection / Abnormal Behavior Analysis
   

Exploiting Simple Hierarchies for Unsupervised Human Behavior Analysis
F. Nater, H. Grabner, and L. Van Gool
In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010

Videos:
Supplementary Material (more see project web-page)

Related Work:
 Discrimination of locomotion direction at different speeds: A comparison between macaque monkeys and algorithms
F. Nater, J. Vangeneugden, H. Grabner, L. Van Gool, and R. Vogels
In Proceedings ECML/PKDD Workshop on Detection and Identiffcation of Rare Audiovisual Cues, 2010
trackingTrees
Tracker Trees for Unusual Event Detection
F. Nater, H. Grabner, T. Jaeggli, and L. Van Gool
In Proceedings ICCV’09 WS on Visual Surveillance, 2009

Videos:
see project web-page

Realted work:
Transferring activities: Updating human behavior analysis
F. Nater, T. Tommasi, H. Grabner, L. Van Gool, and B. Caputo.
In Proceeding ICCV'11 WS on Visual Surveillance, 2011

nessietimeSquare
Hunting Nessie: Real Time Abnormality Detection from Webcams
M. Breitenstein, H. Grabner, and L. Van Gool
In Proceedings ICCV’09 WS on Visual Surveillance, 2009

Realted work:
Mining from Large Image Sets
L. Van Gool, M. Breitenstein, S. Gammeter, H. Grabner, and T. Quack
ACM Int. Conference on Image and Video Retrieval (CIVR) (Invited Paper), 2009

Real-time Detection of Unusual Regions in Image Streams
R. Schuster, R. Mörzinger, W. Haas, H. Grabner, and L. Van Gool
In Proceedings ACM 
Int. Conference on Multimedia - Video Program, 2010


Object Detection


Efficient 3D Object Detection using Multiple Pose-Specific Classifiers
M. Villamizar, H. Grabner, F. Moreno-Noguer, J. Andrade-Cetto, L. Van Gool, and A. Sanfeliu
In Proceedings British Machine Vision Conference (BMVC), 2011


 

On-line boosting-based car detection from arial images
s H. Grabner, T.T. Nguyen, B. Gruber, and H. Bischof.
ISPRS Journal of  Photogrammetry & Remote Sensing, 63(3):382-396, 2008



Scene Understanding
sutsu1sutsu2
sutsu3sutsu4

Segmentation-Based Urban Traffic Scene Understanding
A. Ess, T. Müller, H. Grabner, and L. Van Gool
In Proceedings British Machine Vision Conference (BMVC), 2009



On-line Learning


Training Sequential On-line Boosing Classifier for Visual Tracking
H. Grabner, J. Sochman, H. Bischof, and J. Matas
In Proceedings International Conference on Pattern Recognition (ICPR), 2008, Talk

overview
On-line Boosting and Vision
H. Grabner, and H. Bischof
In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR), volume 1, pages 260-267, 2006, Poster


click here for all publications

  Projects

Scovis Logo Self-configurable COgnitive VIdeo Supervision - Scovis
European Community's Seventh Framework Programme FP7 ICT

  Teaching and Talks

Teaching
Recent Invited Talks
  • Machine Learning Meetup, Zurich, CH, webcamaze -- Amazing Webcams, March, 2014, Slides, YouTube Video
  • V&C Seminar at Laboratory of Psychophysics, EPFL, Lausanne, CH, webcamaze -- Amazing Webcams, Jannuary, 2014.
  • The 33rd Pattern Recognition and Computer Vision Colloquium, Czech Technical University, CZ, webcamaze -- Amazing Webcams, November, 2013, Slides.
  • Sommerschule TUM/DLR (Technische Universitaet Muenchen and Deutsches Zentrum fuer Luft- und Raumfahrt) Ftan, CH, Robust Tracking using Visual Constrains and Context, July, 2011, Slides.
  • Seminar at Center for Processing Speech and Images, Katholic Univeristy of Leuven, BL, Context in Tracking, September 2010.
  • Seminar at Information: Signals, Images, Systems Research Group (ISIS), Univ. of Southampton, UK. Learning for Tracking and Lessons Learned from it. August 2009, Slides
  • Presentation at Visual Recognition and Geometric Reconstruction Symposium, Vienna, A. Simplifying Object Detection: Classifier Grids for Learning Robust Adaptive Object Detectors. April 2009, Slides
  • Seminar at Robotics Research Group, Univ. of Oxford, UK, Learning for Tracking and Lessons Learned from it. March 2009, Slides

  Students and Collaborators

I'm proud to have the availability working closely together with young and motivated PhD-Students in our lab:

Michael Gygli Visual Interestingness, ongoing, (together with Prof. Luc Van Gool).
Andreas Nussberger Visual Sense and Avoid for Unmanned Aircrafts, ongoing, (together with Prof. Luc Van Gool).
Severin Stalder Paradigms in Visual Object Tracking, 2012, (together with Prof. Luc Van Gool)
Fabian Nater Abnormal Behavior Detection in Surveillance Videos, 2012, (together with Prof. Luc Van Gool)

  Richard (Jan. 17. 2011) - Theresa (Dec. 12. 2012)


  BIWI Running

BIWI-running is every Monday, Wednesday and Friday at 11:30am! Meeting point: ETF C108. Just pass by and join!
You can find recorded tracks here.


Biwi Running on a bigger map.

  Links


Helmut Grabner, last updated: March 7, 2015
Not part of the official ETHZ web-pages.

logoETH