Martin Spengler

Ph.D. Candidate in Computer Science

Research interests

Scene understanding, knowledge representations, and self-organization in the context of multi-object tracking. Currently, I am working on a Bayesian multi-object tracking framework based on sequential Monte Carlo methods (aka particle filters or Condensation).

Advisor: Bernt Schiele

Education

Dipl. Informatik-Ing. ETH (M.Sc. in Computer Science)
ETH Zürich, Switzerland, 2000.

Experience

Information Technologies Department, ABB Corporate Research Ltd Baden-Dättwil, Switzerland
Internship, April '98 - June '98
Advisor: Markus Strässler
Project: Visualization of large structures. - Java front-end for visualizing database structures with fisheye views and conventional tree views.

Short Bio

Since October 2000, Martin Spengler is a PhD student of Bernt Schiele in the Perceptual Computing and Computer Vision Group (PCCV), Department of Computer Science at ETH Zurich, Switzerland.

His current research interests are self-organizing systems, machine learning and perceptual computing. He is working on self-organized sensor integration applied to multi-modal object tracking with focus to probabilistic methods.

Before starting his PhD, Martin obtained a M.Sc. (Dipl.Ing.) in Computer Science from ETH Zurich, Switzerland, in 2000. His master's thesis was conducted in the field of self-organized sensor fusion and head tracking in the research group of Bernt Schiele at ETH Zurich. The thesis is titled Self-Organized Sensor Integration Applied to Multi-Modal Head Tracking

Publications

2003

Automatic Detection and Tracking of Abandoned Objects M. Spengler and B. Schiele. In Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, Nice, France, October 2003.

Multi-Object Tracking Based on a Modular Knowledge Hierarchy M. Spengler and B. Schiele. In 3th International Conference on Computer Vision Systems 2003, Graz, Austria, April 2003

Towards Robust Multi-Cue Integration for Visual Tracking. M. Spengler and B. Schiele, In Machine Vision and Applications, Vol. 14(1), pp. 50-58, Springer, 2003

2002

Multi-Object Tracking: Explicit Knowledge Representation and Implementation for Complexity Reduction M. Spengler and B. Schiele. In Cognitive Vision Workshop 2002, Zurich, Switzerland, September 2002.

2001

Context-driven Model Switching For Visual Tracking H. Kruppa, M. Spengler, and B. Schiele. In 9th International Symposium on Intelligent Robotic Systems 2001, Toulouse, France, July 2001.

Towards Robust Multi-Cue Integration for Visual Tracking. M. Spengler and B. Schiele. In 9th International Workshop of Computer Vision Systems, 2001, Vancouver, Canda, July 2001.

Towards Robust Perception and Model Integration B. Schiele, M. Spengler, and H. Kruppa. In Sensor Based Intelligent Robots, Lecture Notes in Computer Science, Springer, 2001.