Direct interaction with large displays through monocular computer vision

Abstract

Large displays are everywhere, and have been shown to provide higher productivity gain and user satisfaction compared to traditional desktop monitors. The computer mouse remains the most common input tool for users to interact with these larger displays. Much effort has been made on making this interaction more natural and more intuitive for the user. The use of computer vision for this purpose has been well researched as it provides freedom and mobility to the user and allows them to interact at a distance. Interaction that relies on monocular computer vision, however, has not been well researched, particularly when used for depth information recovery. This thesis aims to investigate the feasibility of using monocular computer vision to allow bare-hand interaction with large display systems from a distance. By taking into account the location of the user and the interaction area available, a dynamic virtual touchscreen can be estimated between the display and the user. In the process, theories and techniques that make interaction with computer display as easy as pointing to real world objects is explored. Studies were conducted to investigate the way human point at objects naturally with their hand and to examine the inadequacy in existing pointing systems. Models that underpin the pointing strategy used in many of the previous interactive systems were formalized. A proof-of-concept prototype is built and evaluated from various user studies. Results from this thesis suggested that it is possible to allow natural user interaction with large displays using low-cost monocular computer vision. Furthermore, models developed and lessons learnt in this research can assist designers to develop more accurate and natural interactive systems that make use of human’s natural pointing behaviours.