Kinect system keeps track of household objects
FITTING your house with a network of Kinect sensors could mean never losing your wallet, TV remote or other small items again.
“We want to make Google for your home,” says Shahriar Nirjon, a computer scientist at the University of Virginia in Charlottesville. To do this, Nirjon and colleague John Stankovic developed Kinsight, which records the location of household items using a Kinect depth camera in each room. It works by tracking people and detecting the size and shape of any objects they interact with. Each object is compared to Kinsight’s database for the house and either recognised or added to the list.
By following the location of objects over time, Kinsight can even distinguish between two identical-looking things – if it records a mug that seems to have jumped from the living room to the kitchen without passing through the space between, for example, it knows it is likely to be two mugs. The system can locate fist-sized objects with an accuracy of 13 centimetres.
Objects need to be manually tagged to be searchable in the system, but Nirjon plans to develop a smartphone app to make this easier. He presented the work at the Distributed Computing in Sensor Systems conference in Hangzhou, China, last month.