Google launches SpeciesNet, an open artificial intelligence model designed to recognize animal species based on photos taken from camera traps. These devices, which include digital cameras with infrared sensors, are widely used by researchers to study wildlife.
Google launches the Wildlife Insights initiative, which works within the framework of the Google Earth Outreach charity program. This platform allows researchers to upload, analyze and identify wildlife images online, speeding up the processing of camera trap data.
The artificial intelligence used in Wildlife Insights is based on the SpeciesNet model. According to Google, it was trained on more than 65 million publicly available images, as well as material from organizations such as the Smithsonian Conservation Biology Institute and the Wildlife Conservation Society. SpeciesNet is capable of classifying images into more than 2,000 categories, covering different animal species, taxa, and even inanimate objects, including vehicles.
Google noted that the release of this model will contribute to the development of technologies in the field of biodiversity conservation. It will be useful for developers, academic institutions and startups involved in monitoring natural ecosystems. SpeciesNet is available on GitHub under the Apache 2.0 license, which allows its free use, including for commercial projects.
