Interactive exploration of historic information via gesture recognition

Abstract

Developers of interactive exhibits often struggle to find appropriate input devices that enable intuitive control, permitting the visitors to engage effectively with the content. Recently motion sensing input devices like the Microsoft Kinect or Panasonic D-Imager have become available enabling gesture based control of computer systems. These devices present an attractive input device for exhibits since the user can interact with their hands and they are not required to physically touch any part of the system. In this thesis we investigate techniques to enable the raw data coming from these types of devices to be used to control an interactive exhibit. Object recognition and tracking techniques are used to analyse the user's hand where movement and clicks are processed. To show the effectiveness of the techniques the gesture system is used to control an interactive system designed to inform the public about iconic buildings in the centre of Norwich, UK. We evaluate two methods of making selections in the test environment.At the time of experimentation the technologies were relatively new to the image processing environment. As a result of the research presented in this thesis, the techniques and methods used have been detailed and published [3] at the VSMM (Virtual Systems and Multimedia 2012) conference with the intention of further forwarding the area.