Google has released an open-source AI model called SpeciesNet, designed to identify animal species by analyzing camera traps. These devices, which consist of digital cameras connected to infrared sensors, are widely used by researchers to study wildlife. However, processing data from such cameras takes a long time because they generate huge amounts of information.
To facilitate this process, Google created the Wildlife Insights initiative, launched about six years ago as part of its Google Earth Outreach program. This platform allows researchers to share, identify, and analyze wildlife images online, speeding up the processing of camera trap data.
The AI models for analysis in Wildlife Insights are based on SpeciesNet, which Google says was trained on more than 65 million publicly available images, as well as materials from organizations like the Smithsonian Conservation Biology Institute and the Wildlife Conservation Society. SpeciesNet is capable of classifying images into more than 2,000 categories, including different animal species, taxa, and non-animal objects, such as vehicles.
Google said that the release of this model will help developers, academic institutions, and startups involved in biodiversity conservation improve monitoring of natural ecosystems.
SpeciesNet is available on GitHub under the Apache 2.0 license, which allows it to be used for commercial purposes without restrictions.