If each animal could be photographed and uniquely identified many times each day, the science of ecology and population biology, together with the resource management, biodiversity, and conservation decisions that depend on this science, could be dramatically improved.

compbio.cs.uic.edu/IBEIS

IBEIS is a large autonomous computational system that starts from image collections and progresses all the way to answering ecological and conservation queries, such as population sizes, species distributions and interactions, and movement patterns. The images are taken by field scientists, tourists, and incidental photographers, and are gathered from camera traps and autonomous vehicles. IBEIS can detect various species of animals in those images and identify individual animals of most striped, spotted, wrinkled or notched species. It stores the information about who the animals are, where they are and when they are there in a database and provides query tools to that data for scientists and curious people to find out what those animals are doing and why they are doing it.

Monday, February 23, 2015

IBEIS Moves to Lewa

In mid-January we returned to Kenya to install the first full end-to-end prototype of the IBEIS software system, this time at the Lewa Wildlife Conservancy, which is just a bit north of Nanyuki.  The new version of the prototype includes an updated version of Wildbook as the back-end data management system.  (Marco and Clara had moved the powerful compute server up to Lewa last autumn.)  In addition to the usual efforts of working out kinks in the software, a major task was to integrate IBEIS into the workflow of the Lewa science team.  They already were using software called CyberTracker on their smart phones to record “metadata” about the sightings of each group of animals.  This is fed into a “SMART” database.  We figured out how to get data about where the animals were seen from SMART and combine it with the actual photos for input to IBEIS!  This is the start of something big!


Our initial target species at Lewa is Grevy’s zebras.  By doing a few new image collection runs during testing and training, and also by importing image sets from the 2nd half of 2014, our combined Lewa/IBEIS team managed to build a database of nearly 300 animals before we IBEISers had to leave.  In the next few months we plan to continue to upgrade the software, expand the use of IBEIS for Grevy’s zebras to Mpala and other conservancies in the Laikipia region, work closely with the Grevy’s Zebra Trust, and incorporate other species into the system.