Observation of animal behaviour is important to many fields of research in the life sciences. Its automation is crucial to advances in animal well-being and scientific research. In the Ethovision product made by Noldus, a Windows computer is attached to a camera which has a 2D topview of a homecage. The images are recorded and analyzed in real-time to generate statistics on what the animals are doing. For their wellfare, animals are housed socially in homecages. Recent very promising research, on real-time tracking of deformable rodent contours using probabilistic models of shape and motion, requires follow up for its application to multiple animals.

Assignment
The aim is to create a multi-animal tracking algoritm that is capable to identify multiple animal shapes reliably and that can handle the complex shapes resulting from occlusions. Literature shows there are many, mainly statistical approaches. The purpose of this assignment is to select and implement an approach to overcome this problem. Your background We are looking for students who are interested in research in the area of computer vision and statistical algorithms. Knowledge of C++ is required.

More information
If you are interested in this particular project, please contact Rob Ottenhoff or Wil van Dommelen. Background information: www.noldus.com.