We have been talking a lot about how Artificial Intelligence solutions are being applied across various industries and what are they achieving. In this week’s guide, we will get closer to nature and see how Artificial Intelligence applications are helping researchers study and preserve wildlife. Let’s get started.
BearID, a project to identify bears with facial recognition, could help conservationists monitor the health of bear populations in various parts of the world, and perhaps aid work with other animals, too. The model takes reference from the existing “dog hipsterizer,” Although trained on dogs, dog hipsterizer worked reasonably well on the similarly shaped faces of bears, giving a programming head start.
Creating a training data set for the deep learning program involved examining over 4,000 photos with bears in them. First, the deep learning algorithm finds the bear face using distinctive landmarks like eyes, nose tip, ears and forehead top. Then the app rotates the face to extract, encode and classify facial features.
The system’s accuracy rate of identifying bear faces is at 84%. It correctly distinguishes between known bears such as Lucky, Toffee, Flora and Steve.
An innovative animal-borne data collection system assisted by Artificial Intelligence is tracking the previously unobserved behaviours in the wild animals. The method used for data collection uses low-cost sensors that automatically detect and record specific behaviours in animals. The random sampling methods are outperformed by this new AI system. The researchers were able to observe previously unreported foraging behaviours in gulls. These findings can be applied to support further data collection in the wild.
Head to the Great Learning Academy for free courses on Artificial Intelligence and Machine Learning.0