Researchers at the University of St Andrews located in Scotland have figured out a new way for computers to recognize different objects. The device is called the RadarCat and it identifies different types of material ranging from Glass bottles to keyboards and much more. RadarCat is short for Radar Categorization for input and interaction. Let’s dive in to see some more details on the sensor.
When Google first announced its Project Soli back in 2015, it showcased a way to create gesture controls for the future technology. A group of researchers from the University of St Andrews have made use of one of the alpha developer kit of Project Soli to create a radar that can identify different objects.
The sensor based on radar used in RadarCat was created to detect minute finger movements. However, the team saw potential in the technology and took it further into heights. Chairman of Human Computer Interaction at the university, Professor Aaron Quigley said, “The Soli miniature radar opens up a wide-range of new forms of touchless interaction. Once Soli is deployed in products, our RadarCat solution can revolutionize how people interact with a computer, using everyday objects that can be found in the office or home, for new applications and novel types of interaction.”
So how does RadarCat work? The base unit of the device shoots out electromagnetic waves at a specific target object. These electromagnetic waves bounce back from the target and return to the source. The system uses this information to analyse the shape and distance of the target object. One major point of the device is that Google’s Soli radars have the capability of recognizing the external as well as internal aspects of the object. The RadarCat is so accurate that it can identify the front and back of an object along with shape, size and orientation.
The size of the Soli chip is tinier than a quarter with dimensions of 8mm x 10mm. In this size, it packs the antenna ray and sensor both. As can be seen in the video embedded below, the RadarCat is connected to the Microsoft Surface 3 via the USB cable. When a user positioned his hand over the sensor, raw signals are generated on the program running on the laptop. Other items are also scanned and the results are amazing.
Another place where RadarCat is most effective is drawing additional information about the object. For instance, if you place an apple in front of the sensor, it will not just shape the object but tell the nutritional information as well. There can be many applications of the system ranging from in store grocery shopping to comparing different smartphones.