The California Institute of Technology has published iWildCam, a dataset of nearly 300,000 images from 143 locations to foster the development of AI systems that can automatically detect animals in stationary wildlife cameras. The dataset includes 20 different animal classes, including bobcat, moose, and mountain goat. Biologists use wildlife cameras to monitor the biodiversity and population density of animal species, but automating the process can be difficult because images of the animals can be poorly illuminated, suffer from motion blur, and have distorted perspectives if the animals are too close to the camera. This dataset could make it easier to train AI systems to automate this process.
Automating the Detection of Animals in Wildlife Cameras
Michael McLaughlin is a research analyst at the Center for Data Innovation. He researches and writes about a variety of issues related to information technology and Internet policy, including digital platforms, e-government, and artificial intelligence. Michael graduated from Wake Forest University, where he majored in Communication with Minors in Politics and International Affairs and Journalism. He received his Master’s in Communication at Stanford University, specializing in Data Journalism.
View all posts by Michael McLaughlin