Energy-efficient artificial vision system ‘mimics human eye’

A team of UK researchers are working to create a new energy-efficient artificial vision system that could be used in a range of robotic applications in future.

To be created by collaborators from King's College London and University College London, the system will utilise dynamic visual sensors that can drastically reduce the computing power and data storage requirements associated with such technology.

These neuromorphic sensors mimic how the eyes of humans and other mammals process information, quickly and efficiently detecting light changes in their field of vision and selectively updating the parts of an image where movement occurs.

In doing so, the energy and processing needs of the cameras can be minimised, while better capturing the fast-moving details of a dynamic scene by diverting processing power away from static areas.

During the research project, the team will look at how high-quality footage could be sourced efficiently from these dynamic visual sensors and shared between machines, or uploaded to a server in the cloud.

Study leader Professor Maria Martini said: "This energy saving opens up a world of new possibilities for surveillance and other uses, from robots and drones to the next generation of retinal implants."

With over 20 years of experience within the service engineering market, we at Zenopa have the knowledge, skills and expertise to help find the right job for you. To find out more about the current service engineering roles we have available, you can search for the latest job roles, register your details, or contact the team today.