PROTECTOR+: vision-based pedestrian protection
2000-now, Daimler Research, Germany.

Our long standing effort is directed towards a system for real-time visual detection and tracking of pedestrians from a moving vehicle. The current PROTECTOR+ system combines pedestrian detection, trajectory estimation, risk assessment and driver warning or vehicle braking

Ph.D. Students: Markus Enzweiler, Christoph Keller

Visual detection and tracking of humans, 2005-2009, Univ. of Amsterdam, Netherlands

The ability to recognize humans and their activities by vision is key for a machine to interact intelligently and effortlessly with a human-inhabited environment. There are numerous important applications ranging from public safety, elderly care and intelligent vehicles to human motion capture/analysis. In this research we investigate generic techniques for person detection and tracking.

Ph.D. Student: Michael Hofmann

CASSANDRA: Aggression Detection by Fusion Video and Audio, 2005-2009, Univ. of Amsterdam, Netherlands

This project pursues human activity recognition in dynamic environments, in particular, automatic aggression detection. Because events associated with the buildup or enactment of aggression are difficult to detect by a single sensor modality (e.g. shouting versus hitting-someone), CASSANDRA combines audio- and video-sensing.The current project status is described here.

Post Doctoral Researcher: Wojtek Zajdel

The Chamfer System
1997-now, Daimler Research, Germany.

I have been working on generic shape-based object detection based on hierarchical matching with distance transforms. The method was successfully applied in a variety of application domains ranging from intelligent vehicles to industrial inspection.
 

Multi-cue 3D Pedestrian Tracking
2002-now, DaimlerChrysler Research, Germany.

This work involves a spatio-temporal object representation termed Dynamic Point Distribution Models (DPDMs) which can deal with both continuous and discontinuous appearance changes and is learned automatically from training data. State propagation is achieved using a particle filter which  integrates shape, texture and depth information.

Ph.D. Student: Stefan Munder

Real-time Dense Stereo for Intelligent Vehicles
2003-2005, University of Amsterdam, The Netherlands.

With recent hardware advances, dense stereo algorithms have become feasible for real-time implementation on general-purpose processors. We developed a framework of such algorithms based on a SIMD architecture and examined their performance-speed trade-offs.

3D Human Body Tracking with Multiple Cameras
1993-1996, University of Maryland, USA.

First system for the vision-based 3D tracking of unconstrained whole-body movement, of that time. Using four cameras, the system recovered 3D body pose without requiring the human to wear special markers, as was (and still is) the norm in motion capture.
 

3D Head Model Acquisition
1996, MIT Media Lab, USA.

During my semester-long visit at the MIT Media Lab I worked on a “poor man’s Cyberware scanner”: a system that uses a single video-camera to create from a sequence of a user turning his head a realistic textured 3D head model.
 

Hermite Deformable Models
1995-1996, University of Maryland, USA.

This research introduces the Hermite contour representation for deformable shape tracking.  It combines a maximum-a-posteriori criterion for the energy function with a dynamical programming technique to find optimal solution of the resulting minimization problem.