If each animal in a population 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.

We would be able to accurately track population sizes, species distributions, and movement patterns. We would be able to understand social structures, mating patterns, inter-species relationships, and responses to environmental pressures, including land use by humans and long-term climate patterns. Wildlife managers could better monitor the health of entire populations, discover dangerous trends, and avoid conflicts between humans and wildlife. Contributing this information and access to it would increase the public’s engagement in science and conservation, making them true citizen scientists and policy makers.

Can we do it?

Yes! Images have become the most abundant, available and cheap source of data. The explosive growth in the use of digital cameras, together with rapid innovations in storage technology and automatic image analysis software, makes this vision possible particularly for large animals with distinctive striped, spotted, wrinkled or notched markings, such as elephants, giraffes and zebras. Scientists and visitors to a park may each take a thousand or more photos per day, while automatic image collection systems such as camera traps and camera-equipped drones may be used to gather thousands more. This large number of collected images must be analyzed automatically to produce a database that records who the animals are, where they are, and when they were photographed. Combining this with geographic, environmental, behavioral and climate data would enable the determination of what the animals are doing, and why they are doing it. This is our vision for Wildbook (formerly IBEIS: the Image-Based Ecological Information System).

We are doing it!

A team of faculty, students and engineers atPrinceton University, Rensselaer Polytechnic Institute, the University of Illinois-Chicago, and the non-profit organization Wild Me is dedicated to building Wildbook, turning massive collections of images into a high-resolution information database about animals.

IBEIS data and system schema

Our plan.

WIldbook is being developed, fielded and tested in three stages:

IBEIS-Lite, the “duct-tape” prototype, the stringing together of existing tools (Wildbook 5 + Hotspotter), was tested at Ol Pejeta Conservancy in Lakipia, Kenya in 2014-2015.  We tested it on elephants, giraffes, and zebras. Fielding a prototype quickly allowed us to gather scientific data and demonstrate technical viability. The precarious status of many species demands action now. Our tools can provide evidence and the scientific basis for this action. Wildbook Version 6 blends separate components (legacy Wildbook for data management and HotSpotter for image analysis) into an integrated toolkit. It is under development September 2014—September 2016. It is more autonomous and in field trials has handled images at a single park identify as well as additional species of individual animals (including marine species such as humpback whales). A beta version of IBEIS Version 1 will be installed at three sites in July 2015.  Full release is planned for September 2016. Wildbook Version 7 will be developed July 2016—June 2018. It will handle essentially unlimited number of images per day, coordinate animal sightings between multiple nearby conservancies, identify individual animals in species – including primates – based on their facial characteristics, and begin to automatically analyze the environmental context of each image. Wildbook Version 7 will allow software contributions from outside the WIldbook team.  Beta release in June 2017.

In short, each Wildbook release will handle greater image volumes, identify animals from a larger range of species, and work more autonomously, leading to deeper scientific understanding, more informed and timely conservation decision making, and increasingly widespread use.