A group of Swiss researchers discovered retina-inspired camera technology for drones, which will enable adjustment to low-light conditions and increased usability of devices “civilian and military applications.”
Robotics Perception Group chief at the University of Zurich, Davide Scaramuzza, said the newly identified Dynamic Vision Sensor (DVS) system process, “Instead of wastefully sending entire images at fixed frame rates, only the local pixel-level changes caused by movement in a scene are transmitted – at the time they occur.”
Currently, if flight speeds of drones are increased, images become blurred.
But, the researchers developed a camera that refreshes and resubmits changes in brightness for individual pixels.
Scaramuzz explained that DVS adjusts to the intensity of light, similar to the naked eye. These “events,” as the robotics expert calls them, will facilitate the capture of images in high-speed motion or low-lit scenarios.
"This research is the first of its kind in the fields of artificial intelligence and robotics, and will soon enable drones to fly autonomously and faster than ever, including in low-light environments," Professor Scaramuzza said, according to a report by Phys.org.
The group carried out two experiments and found that their DVS-equipped drone saw 130 percent better than a similar system relying on event data and 85 percent better than a system relying on standard data.
This new technology would enable drones to go beyond basic GPS tracking.
"There is still a lot of work to be done before these drones can be deployed in the real world since the event camera used for our research is an early prototype. We have yet to prove that our software also works reliably outdoors," explained Ph.D. student Henri Rebecq.
"We think this is achievable, however, and our recent work has already demonstrated that combining a standard camera with an event-based camera improves the accuracy and reliability of the system," Scaramuzza added.