Observation of animal behavior 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 top view of a confined space: for instance a cage, pool, or maze with animal(s) or insects in it. The images are recorded and analyzed in real-time to generate statistics on what the animals are doing. To reduce image processing effort, the user draws a simple shape over the video image, representing the confines within which the action unfolds: an arena. Additional shapes may identify zones of interest, such as a feeding tray, water bottle, underwater-platform, etc. The term arena setup is used for the collection of all user-defined shapes in a video image. Clearly, making an arena setup can involve a considerable amount of work.

Assignment
Since the types of arena used for experimental set-ups (a ‘maze’) are relatively few in number, it is possible to build a special knowledgebase of mazes and/or home cages into templates. Software will need to recognize complex geometric shapes under wildly varying real-world conditions. The ultimate goal is to automatically define arenas from video and to auto label zones and shapes by their commonly used names (such as water maze, radial maze, water bottle, underwater platform, e.g.).

More information
If you are interested in this particular project, please contact Rob Ottenhoff (r.ottenhof@noldus.nl)or Wil van Dommelen (w.van.dommelen@noldus.nl).