Pattern Independent Fiducial Marker Detection for an Interactive Public Display

Abstract

The use of keyboard and mouse introduced with the advent of the first GUI operating system is a proven way of interaction with interfaces based on window, icon, menu and pointer (WIMP) paradigm, which has prevailed for few decades. Traditional input devices have limitations as they are originally designed to support two dimensional interfaces in single user environment, thus increasing interest on interactive software and use of novel ways of interaction. As a result, interaction using tangible real objects that can eliminate cumbersome intermediate input devices to provide natural interaction is deemed as an important approach for developing alternative interaction paradigms. This research attempts to develop an alternative interaction methodology to enable interaction using tangible real world objects with fiducial marker detection and using commonly available hardware such as webcam. The research explores two novel capabilities of using fiducial markers. First it attempts to enable pattern independent marker detection that can replicate mouse interface and finally it exploits multiple marker detection along with a multi-user driver to construct an interactive public display. Tests prove that both the attempts of the authors are applicable in practice and they promise to make human computer interaction more entertaining.