Researchers at the Max Planck Institute for Intelligent Systems in Germany are working to help computers understand human behavior by feeding the system videos and images of computer-generated bodies walking, dancing, and doing cartwheels.
Although recognizing what is going on in images is natural for humans, enabling computers to do the same requires more effort, according to Max Planck researcher Javier Romero. He says using synthetic images to train computers could give them more meaningful information about the human world.
The researchers created the synthetic humans using three-dimensional rendering software, basing the work on existing human figure templates and motion data collected from real people to keep the results realistic. The team then generated animations by randomly selecting body shapes and clothing, and setting the figures in different poses.
The researchers generated more than 65,000 clips and 6.5 million frames.
From New Scientist
View Full Article
Abstracts Copyright © 2017 Information Inc., Bethesda, Maryland, USA