Home Projects Teaching Publications Software


Current Projects

I am currently working on the following projects:

In this project, we use simple binary sensors to measure how the state of health of elderly people evolves over time. In combination with the Vrije Universiteit, we investigate how we can intervene in the process by coaching people automatically to exercise more or have more social contact.
I am doing the daily supervision of two Ph.D. students for this project, Saskia Robben and Ahmed Nait Aicha.
This is a project for which I obtained STW funding in collaboration with Philips, where we attempt to make camera installation intervention free. The main aim is to have multiple cameras without overlapping field of view, and to recover approximate external calibration through the analysis of moving objects, and in particular, humans, in the cameras' field of view.
I hired and am supervising one postdoctoral researcher, Vijay John, on this project.
The Accompany project
Although I am not officially involved in this project, I do the daily supervision of one Ph.D. student, Ninghang Hu, who is developing novel methods for activity recognition using a combination of multiple cameras, 2D and 3D (kinect), both on a mobile robot platform and fixed in the environment.
This is a recently granted EU STREP project, for which we are currently hiring one Ph.D. student. The project starts in February 2013.

In this project, robots will interact with patients, staff and visitors in a hospital. Multiple robots will coordinate to solve tasks, which will rely on a level of basic "social intelligence": the robots will need to recognise individuals and types of individuals (such as patients, visitors and staff), as well as the mood of people, and take these into account during interaction.

Our interest in the project is in the perception of the more subtle social signals that occur in such an environment. Does a person want to interact or not, how do we recognise the basic signals such as greeting, etc.

Past projects

In the past, I have been working on:

Zorgen voor Morgen
We are recording and analysing large, real-world datasets of elderly people living alone. The recordings consist of simple binary sensors as used in the Cogniron project (below), but are more numerous, installed in many more houses, and record for months at a time.
This project focusses on tracking people with widely distributed camera's. It is a cooperation between the UvA and Eaglevision.
Within the context of the COGNIRON project we have aimed to achieve automatic, non intrusive monitoring of the health state of elderly people, by analysing patterns in simple binary sensor data (such as binary sensors on doors, electric appliances, etc.