The latest trend greatly supports smart devices that work on voice commands and recognize gestures. A team of researchers working at the Georgia Institute of Technology recently gave a new turn to this trend by developing an always-on camera. The device is a combination of a highly energy efficient image processing software and a low-power hardware. This allows the camera to remain on always and keep a check on specific kind of movements without consuming the complete battery of the camera.
Figure 1: Always on-camera gesture recognition
As Justin Romberg, the professor from Georgia Tech’s School of Electrical and Computer Engineering, likes to explain, "Right now cameras are very hard to run on passive power just because they burn so much power themselves. The combination of efficient signal processing and a novel hardware design lowers the power requirement and means that some of these other options to power it might be open."
The team focused on reducing the frame rates of the camera that ultimately leads to reduction in its power consumption. They have programmed the camera in such a manner that it tracks the movement in a more generalized manner and still keeps the crucial details safe about the thing that is being tracked. As per Romberg, "What this camera is actually looking at is not pixel values, but pixels added together in all different ways and a dramatically smaller number of measurements than if you had it in a standard mode."
The always-on camera was initially created with intent to activate devices. However, they recognized its unique ability to recognize specific gestures and modified it into some other applications. Arijit Ray Chowdhury, the associate professor from School of Electrical and Computer Engineering also explains, "We wanted to devise a camera that was capturing imges all of the time, and then once you have a particular gesture - like you write a ‘Z’ in the air - it’s going to wake up. To make it work without affecting the battery life, we wanted it to be so low power that you can power it with harvested ambient energy. SImple motion detection is a well- studied area of research, and there are commercial products that support motion detection. But the problem is that a camera that can just detect motion -and not specific patterns in motion or gestures -is going to wake up more often, even when it doesn’t need to.”