Learning Instead of Markers: Flexible Recognition of Mobile Devices on Interactive Surfaces

摘要: We propose an approach for recognition of mobile devices on interactive surfaces that do not support optical markers. Our system only requires axis aligned bounding box the object placed touchscreen in combination with position data from integrated inertia measurement unit IMU. put special emphasis maximum flexibility terms compatibility varying multi-touch sensor techniques and different kinds devices. A new device can be added to a short training phase, during which is moved across surface. model automatically created recorded using vector machines. Different same size are identified by analyzing their IMU streams transitions into horizontally resting state. The has been tested museum environment.