AI system accurately counts forest trees

Researchers at the University of Cambridge have developed a new system that uses artificial intelligence and simulation to train algorithms to recognize and count trees using drone data, potentially helping to improve forest monitoring and study the impacts of climate change. The university’s website reported last week that the system creates virtual forests using the Unreal Engine game engine, where digital drones equipped with virtual LiDAR sensors scan trees and generate three-dimensional maps used to train AI models, thereby reducing the time and effort required to collect and manually classify data.