discussion / AI for Conservation  / 15 January 2019

Conserving the Sumatran and Javan Rhino

Save Indonesian Endangered Species (SIES) will be building a machine to identify individual Indonesian rhino.  This will be challenging due to low data numbers.... Sumatran rhino 80, Javan rhino 70. We will be piggy backing off a larger machine trained in object identification on millions of images.  We will be loading images of coming 3 years and may need to use citizen science such as wildme.org to assist with labelling.

Thanks Steph, the project will commence mid year.  We are particularly interested in talking with anyone who has done AI for small population numbers with inherent small data issues? At this stage the engineer intends to leverage off a large mulitpurpose AI as a base. Any other ideas out there? Claire 


Hello Claire, 

Engineer at Wild Me here. We would love to start a conversation about a Wildbook for rhinos. 

Lets talk about citizen science and computer vision for identification possibilities. I'm curious about your current data set and the identification tools you are using as a starting point. I'm happy to talk here, or you can email our team at [email protected].

Hi Claire,

At the BearID Project, we are working on a similar problem for brown bears. We are currently using machine learning methods developed for human facial recognition (like Google FaceNet). We got some ok initial results, but now we are running up against small data issues. The method for human faces were trained with millions of images of hundreds of thousandes on individuals. We have a few thousand images of about a hundred individuals. We plan to investigate other methods in the future.

It will be great to keep in touch to see what methods you will be using.