Personal tools

About

Present: I work as a researcher for the Intelligent Autonomous Systems group, part of the Computer Science department IX, Technische Universität München. My PhD supervisor is Prof. Michael Beetz, PhD. I'm involved in the CoTeSys cluster of excellence. I'm also affiliated with Prof. Odest Chadwicke Jenkins and the Robotics group at Brown University, Providence, RI, where I've been a visiting researcher from March 2009 until June 2009.
Past: I obtained my Diploma (equivalent to M.Sc.) in Computer Science from the Technische Universität München (Munich, Germany) in 2005. During my studies I have been focusing mainly on Mobile Robotics, Computer Vision and Efficient Algorithms. The title of my thesis has been "Stereo Vision for Collision Avoidance and Plane Estimation in Mobile Robots".

My current field of interest is Computer Vision and Robotics, where I work on markerless methods for Human Motion Capture in typical (living) environments. My research aims at fast, accurate and reliable recognition and tracking of arbitrary human motions. I'm also interested in low-dimensional representations of human motion for advanced motion priors and activity recognition. Intended areas of application are Activity and Intention Recognition in Smart Environments, Motion Analysis and Industrial Ergonomic Studies.

>> Click here for videos and details on my current research <<

Talks given: >> Here << are the slides for my invited talks at Carnegie Mellon University (March 30, 2009) and Brown University (May 6, 2009). These are also quite similar to the slides I used for my talk at the University of Tokyo (October 8, 2009). >> Here << are the slides for my presentations at Stanford University (November 23, 2009) and Willow Garage (November 24, 2009).

Current Research Projects

  • MeMoMan : Methods for Real-time Accurate Model-based Measurement of Human Motion: Tracking of human full-body motions.
  • COP : Cognitive Perception for CoTeSys: Part of the CoTeSys cluster of excellence.

Former Research Projects

  • ASPOGAMO : Automated Sport Game Analysis Model: Robust visual detection and tracking of football players from broadcasted video.

Teaching

Please go to my teaching page for an overview on my teaching assignments, as well as for a list of available or assigned student projects (SEPs, BAs, DAs, MAs).

Selected Publications

  • Radu Bogdan Rusu , Jan Bandouch , Franziska Meier, Irfan Essa, Michael Beetz , Human Action Recognition using Global Point Feature Histograms and Action Shapes, 2009, Advanced Robotics journal, Robotics Society of Japan (RSJ),
    (BibTeX)
  • Jan Bandouch , Michael Beetz , Tracking Humans Interacting with the Environment Using Efficient Hierarchical Sampling and Layered Observation Models, 2009, IEEE Int. Workshop on Human-Computer Interaction (HCI). In conjunction with ICCV2009,
    (BibTeX) (PDF)
  • Moritz Tenorth , Jan Bandouch , Michael Beetz , The {TUM} Kitchen Data Set of Everyday Manipulation Activities for Motion Tracking and Action Recognition, 2009, IEEE Int. Workshop on Tracking Humans for the Evaluation of their Motion in Image Sequences (THEMIS). In conjunction with ICCV2009,
    (BibTeX) (PDF)
  • Florian Engstler, Jan Bandouch , Heiner Bubb, MeMoMan - Model Based Markerless Capturing of Human Motion, 2009, The 17th World Congress on Ergonomics (International Ergonomics Association, IEA),
    (BibTeX)
  • Jan Bandouch , Florian Engstler, Michael Beetz , Evaluation of Hierarchical Sampling Strategies in 3D Human Pose Estimation, 2008, Proceedings of the 19th British Machine Vision Conference (BMVC),
    (BibTeX) (PDF)
  • Jan Bandouch , Florian Engstler, Michael Beetz , Accurate Human Motion Capture Using an Ergonomics-Based Anthropometric Human Model, 2008, Proceedings of the Fifth International Conference on Articulated Motion and Deformable Objects (AMDO),
    (BibTeX) (PDF)

Document Actions