Google Releases SpeciesNet, an AI Model Designed To Identify Wildlife (techcrunch.com) 15
An anonymous reader quotes a report from TechCrunch: Google has open sourced an AI model, SpeciesNet, designed to identify animal species by analyzing photos from camera traps. Researchers around the world use camera traps -- digital cameras connected to infrared sensors -- to study wildlife populations. But while these traps can provide valuable insights, they generate massive volumes of data that take days to weeks to sift through. In a bid to help, Google launched Wildlife Insights, an initiative of the company's Google Earth Outreach philanthropy program, around six years ago. Wildlife Insights provides a platform where researchers can share, identify, and analyze wildlife images online, collaborating to speed up camera trap data analysis.
Many of Wildlife Insights' analysis tools are powered by SpeciesNet, which Google claims was trained on over 65 million publicly available images and images from organizations like the Smithsonian Conservation Biology Institute, the Wildlife Conservation Society, the North Carolina Museum of Natural Sciences, and the Zoological Society of London. Google says that SpeciesNet can classify images into one of more than 2,000 labels, covering animal species, taxa like "mammalian" or "Felidae," and non-animal objects (e.g. "vehicle"). SpeciesNet is available on GitHub under an Apache 2.0 license, meaning it can be used commercially largely sans restrictions.
Many of Wildlife Insights' analysis tools are powered by SpeciesNet, which Google claims was trained on over 65 million publicly available images and images from organizations like the Smithsonian Conservation Biology Institute, the Wildlife Conservation Society, the North Carolina Museum of Natural Sciences, and the Zoological Society of London. Google says that SpeciesNet can classify images into one of more than 2,000 labels, covering animal species, taxa like "mammalian" or "Felidae," and non-animal objects (e.g. "vehicle"). SpeciesNet is available on GitHub under an Apache 2.0 license, meaning it can be used commercially largely sans restrictions.
Obligatory XKCD (Score:3, Informative)
Seems like we're there: https://xkcd.com/1425/ [xkcd.com]
iNaturalist and Seek do this (Score:3, Informative)
EXACTLY iNaturalist and Seek do this (Score:2)
Why use a limited data camera traps set compared to gbif.org or inaturalist.org ?
maybe Mike Werner, Tanya Birch or Dan Morris can actually answer that
seems silly
For the bird calls (Score:5, Informative)
The Merlin Bird ID works pretty well at identifying bird calls answering the age old question of what bird is making all that noise when you can't see it.
https://merlin.allaboutbirds.o... [allaboutbirds.org]
Re: (Score:2)
Re: (Score:2)
It mocks them right back. Hundreds of mocking birds is waiting for your call, and they ALL talking shit about you
Vetting existing data? (Score:2)
Re: (Score:2)
Chupacabra
Nessie
Re: (Score:1)
Absurd, As AI Consumes Natural Resouces (Score:2)
Re: (Score:1)
AGI redefined again (Score:2)
Now give us all the electricity."
Re: (Score:1)