Research Website of Dr. Michael D. Breitenstein

Dr. Michael D. Breitenstein graduated with a MSc in Computer Science in 2006 and earned a PhD in 2009 with research in computer vision and pattern recognition, both from ETH Zurich. He is currently working for a professional services firm.
Michael did part of his research at Oxford University and at Mitsubishi Research in Boston. Before, he worked as a software engineer in San Francisco and Zurich. Furthermore, he co-founded a company for open innovation. Michael co-authored more than twelve peer-reviewed publications, is inventor of several patents, and won the ITG Innovation Award 2009 for his dissertation.

> Journal Paper about Tracking-by-Detection
<



The journal paper about our improved tracking-by-detection algorithm has been published in the September 2011 issue of IEEE Transactions on Pattern Analysis and Machine Intelligende (PAMI).

> Activity Mining
<


Our work on activity mining has been presented at CVPR'10. Code, data and the presentation (pdf, ppt, video) of are available here.
Reports from popular media about our work: MIT Technology Review Highlights of the month, ETH life, PHYSORG, treehugger

> Peer-reviewed Conference and Journal Publications


<

2010

Online Multiperson Tracking-by-Detection from a Single, Uncalibrated Camera
Michael D. Breitenstein, Fabian Reichlin, Bastian Leibe, Esther Koller-Meier, Luc Van Gool
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI)
 Vol. 33, No. 9, pp. 1820-1833, September, 2011
[IEEE link] [pdf] [project page, videos, datasets]

For this work, we won the ITG Innovation Award from the Information Technology Society Electrosuisse. Media reports:
Swiss Engineering magazine STZ (german), ETH Life article (german), ETH Life print article (pdf, german), Computerworld article (german)

What's going on? Discovering Spatio-Temporal Dependencies in Dynamic Scenes
Daniel Kuettel, Michael D. Breitenstein, Luc Van Gool, Vittorio Ferrari
IEEE Conference on Computer Vision and Pattern Recognition (CVPR'10), (oral)
San Francisco, US, 2010
[pdf] [code, data, presentation]
Media reports: ETH life, PHYSORG, treehugger

Evaluation of Agent Motion in Video: Online Tracking-by-Detection
Michael D. Breitenstein, Bastian Leibe, Luc Van Gool
Int. Conference on Cognitive Systems (CogSys'10), (oral)
Zurich, CH, 2010
[poster] [project page, videos, datasets]

bmvc'08

Fast and Automatic Object Pose Estimation for Range Images on the GPU
In Kyu Park, Marcel Germann, Michael D. Breitenstein, and Hanspeter Pfister
Machine Vision and Applications (MVA)
vol. 21, no. 5, pp. 749-766, August 2010
[springer] [pdf]

2009

iccv'09

Robust Tracking-by-Detection using a Detector Confidence Particle Filter
Michael D. Breitenstein, Fabian Reichlin, Bastian Leibe, Esther Koller-Meier, Luc Van Gool
IEEE Int. Conference on Computer Vision (ICCV'09)
 Kyoto, JP, 2009
[pdf] [project page, videos, datasets]

vs'09

Hunting Nessie -- Real-Time Abnormality Detection from Webcams
Michael D. Breitenstein, Helmut Grabner, Luc Van Gool
IEEE Int. Workshop on Visual Surveillance (VS'09)
 Kyoto, JP, 2009
[pdf] [movie (.avi)]

civr'09

Mining from Large Image Sets
Luc Van Gool, Michael D. Breitenstein, Stephan Gammeter, Helmut Grabner, Till Quack
ACM Int. Conference on Image and Video Retrieval (CIVR'09), (invited)
Santorini, GR, 2009
[pdf]

pets'09

Markovian Tracking-by-Detection from a Single, Uncalibrated Camera
Michael D. Breitenstein, Fabian Reichlin, Bastian Leibe, Esther Koller-Meier, Luc Van Gool
Proc. Int. IEEE CVPR Workshop on Performance Evaluation of Tracking and Surveillance (PETS'09), (oral)
Miami, US, 2009
[pdf] [project page, videos, datasets]

scia'09

Head Pose Estimation from Passive Stereo Images
Michael D. Breitenstein, Jeppe Jensen, Carsten Hoilund, Thomas B. Moeslund, Luc Van Gool
Scandinavian Conference on Image Analysis (SCIA'09), (oral)
Springer Lecture Notes in Computer Science 5575, pp. 219-228
 Oslo, N, 2009
[pdf]

2008

bmvc'08

Probabilistic Parameter Selection for Learning Scene Structure from Video
Michael D. Breitenstein, Eric Sommerlade, Bastian Leibe, Luc Van Gool, Ian Reid
Proc. British Machine Vision Conference (BMVC'08)
 Leeds, UK, 2008
[pdf] [bib] [poster]

cvpr'08

Real-Time Face Pose Estimation from Single Range Images
Michael D. Breitenstein, Daniel Kuettel, Thibaut Weise, Luc Van Gool, Hanspeter Pfister
Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR'08)
 Anchorage, US, 2008
[pdf] [poster] [movie (.mov)] [movie (.wmv)] [bib] [project page and dataset]

2007

3dim'07

Automatic Pose Estimation for Range Images on the GPU
Marcel Germann, Michael D. Breitenstein, In Kyu Park, Hanspeter Pfister
Proc. Int. Conference on 3D Digital Imaging and Modeling (3DIM'07)
 Montréal, CA, 2007
[pdf] [poster] [mov, 21MB] [bib]

> Patents


<

patent

Computer System and Method for Tracking Objects in Video Data

European Patent Application No. EP09007346; filed June 03, 2009

patent

Method and System for Determining Poses of Objects from Range Images Using Adaptive Sampling of Pose Spaces

U.S. Patent Application No. 12/238,618; filed Sept. 26, 2008

patent

Method and System for Determining Objects Poses from Range Images

European Patent No. EP20080005344; March 20, 2008
U.S. Patent No. US20070738642; April 23, 2007

> Theses, Various


<

thesis

Visual Surveillance: Dynamic Behavior Analysis at Multiple Levels
Michael D. Breitenstein, Doctoral Thesis, ETH Zurich, 2009

Computer Vision Lab, ETH Zurich
Examiners: Prof. Luc Van Gool (ETH), Dr. Ian Reid (Oxford U.), Prof. Bastian Leibe (Aachen U.)
[pdf] [e-collection] [book]

demo eccv

Real-Time 3D Scanning and its Applications: In-hand Modeling and Face Pose Estimation
Thibaut Weise, Michael D. Breitenstein, Daniel Kuettel, Bastian Leibe, Luc Van Gool, Hanspeter Pfister
European Conference on Computer Vision (ECCV'08), Demo Session
 Marseille, F, 2008
[pdf]

master

Pose Estimation for Face Recognition using Stereo Cameras
Michael D. Breitenstein, Master's Thesis, ETH Zurich, 2006

Mitsubishi Electric Research Labs (US) and Computer Graphics Lab, ETH Zurich
Advisors: Prof. Markus Gross, Prof. Hanspeter Pfister (Harvard)
[pdf]

master

Genomic Mismatch Scanning
Michael D. Breitenstein, Semester Thesis, ETH Zurich, 2005

Pattern Analysis and Machine Learning Group
Advisors: Dr. Bernd Fischer, Prof. Joachim Buhmann
[description]

master

Integration of Scale-Parts with Bayesian Networks for Face Detection
Michael D. Breitenstein, Semester Thesis, ETH Zurich, 2004

Perceptual Computing and Computer Vision Group
Advisors: Dr. Hannes Kruppa, Prof. Bernt Schiele

The Battle of the Brains 2006
Case Study Competition ETH vs. HSG about the future of Google
Organized by Monitor Group and Bilanz
INFK 06/06/2006, Bilanz 19/2006, Polykum 09/06, Visionen 05/2006, ETH Life 13/06/2006

> Copyright Notice
<
This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

The traffic on this page is analyzed by Google Analytics.