Today, we are launching a brand new Zooniverse project – Computer Vision: Serengeti. This project, which we built in collaboration with our friends at MICO, the Fraunhofer Institute and Snapshot Serengeti, invites you to take a trip back into the wilds of the Serengeti and help us analyse Snapshot Serengeti images in more detail.

We would like to build a computer vision system that can do some of the work of identifying animals in camera trap images automatically, using object detection and machine learning techniques. This would allow us to reduce the amount of work for volunteers on projects like Snapshot Serengeti and get results to scientists faster.

We need your help to do this – machine learning systems have to be carefully trained so that they can learn to recognise animals of different species in different orientations, light conditions and natural environments. What we need you to do is to draw boxes on Snapshot Serengeti images to show us where the animals are, which direction they are facing, how much of them is visible, and how hard they are to identify. We can then put your classifications together to give us a picture like this – a representation of where the animals are in the picture, which can be used to develop training images for the computer vision system:

Example aggregation of volunteer classifications from Computer Vision: Serengeti

There are 20,000 images to be classified – Get involved now at www.zooniverse.org/projects/alexbfree/computer-vision-serengeti and enjoy this chance to revisit the wildlife of the Serengeti!