A Birder in the Hand: Mobile Phone App Can Recognize Birds From Photos
12-14-16
Pietro Perona, Allen E. Puckett Professor of Electrical Engineering, and colleagues have developed the Merlin Bird Photo ID mobile app which uses machine-learning technology to identify hundreds of North American bird species it "sees" in photos. "This app is the culmination of seven years of our students' hard work and is propelled by the tremendous progress that computer-vision and machine-learning scientists are making around the world," says Professor Perona. "A machine that recognizes objects in images, like humans do, was a distant dream when I was a graduate student and now it's finally happening." [Caltech story]
Tags:
EE
research highlights
CMS
Pietro Perona
Counting L.A.’s Trees
07-27-16
Professor Pietro Perona, has developed a method using Google Earth and Google Street View to count the trees in the city of Los Angeles. The process of counting the trees using human tree counters is very expensive and would cost about $3 million today. The last time the city did such counting was more than two decades ago and at the time there were 700,000 street trees. Perona has tested the methodology in a section of Pasadena where the city recently commissioned a sidewalk survey. By comparing the results to the known inventory, he determined that the computer was about 80% accurate. [LA Times story] [KPCC story]
Tags:
EE
research highlights
CMS
Pietro Perona
Pietro Perona Trains Computers to Analyze Fruit-Fly Behavior
04-08-09
Researchers led by Pietro Perona, the Allen E. Puckett Professor of Electrical Engineering, and David J. Anderson, the Roger W. Sperry Professor of Biology and a Howard Hughes Medical Institute Investigator, have trained computers to automatically analyze aggression and courtship in fruit flies, opening the way for researchers to perform large-scale, high-throughput screens for genes that control these innate behaviors. The program allows computers to examine half an hour of video footage of pairs of interacting flies in what is almost real time; characterizing the behavior of a new line of flies "by hand" might take a biologist more than 100 hours. "This is a coming-of-age moment in this field," says Perona. "By choosing among existing machine vision techniques, we were able to put together a system that is much more capable than anything that had been demonstrated before." This work is detailed in the April issue of Nature Methods. [Caltech Press Release]
Tags:
EE
research highlights
Pietro Perona