Bootstrapper - Using the Kinect to Recognize Tabletop Users by their Shoes
And you thought last Friday's post, Kinecting with your tongue (really), was an unusual use of the Kinect? I'm not sure if this week's tops it or not...
Bootstrapper - Recognizing Tabletop Users by their Shoes
In order to enable personalized functionality, such as to log tabletop activity by user, tabletop systems need to recognize users. DiamondTouch does so reliably, but requires users to stay in assigned seats and cannot recognize users across sessions. We propose a different approach based on distinguishing users’ shoes. While users are interacting with the table, Bootstrapper observes their shoes using one or more depth cameras mounted to the edge of the table. It then identifies users by matching camera images with a database of known shoe images. When multiple users interact, Bootstrapper associates touches with shoes based on hand orientation. The approach can be implemented using consumer depth cameras because (1) shoes offer large distinct features such as color, (2) shoes naturally align themselves with the ground, giving the system a well-defined perspective and thus reduced ambiguity. We report a simple study in which Bootstrapper recognized participants from a database of 18 users with 89% accuracy, based on a single observed frame.
Bootstrapper enables personalized functionality on tabletop systems by distinguishing users' shoes. Bootstrapper uses a Kinect depth camera mounted to the edge of the table and identifies users by matching camera images with a database of known shoe images. When multiple users interact, Bootstrapper associates touches with shoes based on hand and arm orientation.
Project Information URL: http://www.hpi.uni-potsdam.de/baudisch/projects/bootstrapper.html