Researchers at Kingston University London and University College London in the U.K. are developing a camera-based artificial vision system for robots and smart devices that simulates the human eye.
The researchers will examine the use of neuromorphic sensors that dramatically reduce computing power and data storage needs by only updating the part of an image where movement occurs.
Kingston professor Maria Martini notes these sensors emulate how mammals' eyes process information. "These sensors...sample different parts of the scene at different rates, acquiring information only when there are changes in the light conditions," Martini says.
The cameras require far less energy and processing requirements, and Martini's team will explore how high-quality footage could be sourced efficiently from the dynamic sensors and then shared between machines or uploaded to a cloud-based server.
The researchers also will consider the role the sensors could play in the Internet of Things.
From Kingston University London (United Kingdom)
View Full Article
Abstracts Copyright © 2017 Information Inc., Bethesda, Maryland, USA
No entries found