I participated in a number of interesting projects at the University of Amsterdam and during my Job at Eagle Vision Systems. Below you will find a selection of those projects. Please contact me for more information, high resolution images or demos.

September 2012 - June 2013
WPSS: Watching people security services

To improve security, the number of surveillance cameras is rapidly increasing. However, the number of human operators remains limited and only a selection of the video streams are observed. Intelligent software services can help to find people quickly, evaluate their behavior and show the most relevant and deviant patterns. We present a software platform that contributes to the retrieval and observation of humans and to the analysis of their behavior. The platform consists of mono- and stereo-camera tracking, re-identification, behavioral feature computation, track analysis, behavior interpretation and visualization.

Read the article on SPIE.

Radial hue-saturation color histogram

September 2011 - June 2012
Recognising Individuals by Appearance across Non-overlapping Stereo Cameras

My masters project was about color and geometry based appearance models. The project involved people recognition using non overlapping top mounted (i.e. ceiling mounted) stereo cameras. The report discusses a number of methods, including a novel radial hue-saturation histogram. It is based on the circularity of the hue-saturation space where the value is neglected. I created a method to divide a circle into equal parts. The proof that the partitions are of equal size is provided in Appendix A of my thesis.

Download my Master Thesis or download the printable version.

April - May 2011
NS Data Visualisation

We used Protovis (now d3.js) for our visualisations.


June 2010
Lisa - Layered Interactive Sokoban Assistant

This project was a literature research on solving the Japanese game Sokoban. Inspiration is emerged from previous work to develop LISA (Layered Interactive Sokoban Assistant). LISA assists the player towards solving the puzzle. AI techniques are used to display strategic information about the game is visual assistance layers.

Download the report.

January 2010
Reconstructing a 3D Structure from Unknown Viewpoints using Uncalibrated Cameras

In this project we considered the problem of computing the 3D structure of an unknown arbitrarily-shaped scene from two photographs taken at unknown viewpoints using uncalibrated cameras.

Download the report.

June 2008
AIGOA - Artificial Intelligent Go Annotator

Every move in a Go game is automatically registered by a webcam. This is a completely automated process without any camera calibration. A lot of computer vision techniques are combined: background estimation, edge detection, feature detection, Hough lines etcetera.

Download the report.

June 2007
Real-time Billboard Substitution in a Video Stream of a Soccer Match

The goal of this project was to replace the adds at the borders of a soccer field in a live video stream with other (regional) advertisements. Further more it was the aim to do this fully automatically using computer vision, without any camera calibration.

Download the report (Dutch).

September 2006 - December 2006
Background Estimation

If you want to track objects or people in a video stream it is very convenient to have an accurate estimation of the background. Especially in outdoor situations this brings some issues. Think about changing weather, reflections in water waving leaves in a tree etcetera. These settings ask for a solid system using a multiple gaussian based Markov decision model.

Download the poster (Dutch).

June 2006

For this project we created a genetic algorithm (GA). Six Quake bots play against each other and the best two are selected to breed. This iterative process repeats itself until some optimum is found. The result is indeed a bot from which no human player can ever win.

Download the report (Dutch).