Natural Interaction with Projected Screen on Surfaces using Infrared Depth Camera

Abstract

<em>Technology advancement improves the way we interact with computer systems. Keyboard, mouse, and touchpad provide an easier and more natural way of interaction with a computer system. Nowadays, by introducing low cost and high performance depth cameras like Kinect and Xtion, new opportunities are available for creating even more natural interfaces. In this paper, a new model was demonstrated for natural interaction with a projected screen on a surface by detecting hand gestures and touch points using depth camera. Because lighting conditions, color, and background have little impact on the performance of systems based on depth camera, these systems can be integrated in a variety of applications in daily life. In this paper, a model was proposed for Microsoft Office as goal presentation. The main steps of the proposed model can be categorized as follows: hand detection, gesture detection, touch point detection, and control software. The proposed model had reasonably low cost with minimum configuration and calibration prerequisite and can replace the expensive and not-convenient-for-moving tablets.</em>