ePrints.FRI - University of Ljubljana, Faculty of Computer and Information Science

Laser pointer tracking for human-computer interaction

Elvis Žlender (2010) Laser pointer tracking for human-computer interaction. EngD thesis.

[img] PDF
Download (1496Kb)

    Abstract

    To control standard presentation systems consisting of a laptop connected to a projector the presenter uses computer input devices such as keyboard or a mouse. The speaker is forced to interact with the computer rather than the audience. This thesis introduces one of the possible solutions in the form of an interface that uses laser pointer to control the computer mouse. As additional equipment I used a laser pointer to control the mouse and an uncalibrated camera to capture the projection image. The projector-camera system calibrates itself by exploiting the homography between the projected image and the camera image. The projector actively manipulates the enviroment by projecting feature points onto the projection surface. With the implementation of some image processing methods camera enables the mouse pointer to follow the laser beam. The implemented interface allows us to perform all the elementary three-button mouse actions inside the Microsoft Windows operating system with the laser pointer (i.e. left click, double left click, drag and drop, right click and scroll). Right click and scroll are implemented using gesture recognition methods. This part of interface gives us an intuitive control over Microsoft PowerPoint presentation and Windows Media Player application. With simple gestures (e.g. laser beam motion across the right side of the projection screen) we can execute many different commands (e.g. move to the next slide). The interface can be upgraded with additional gestures to control additional applications.

    Item Type: Thesis (EngD thesis)
    Keywords: projector-camera system, laser pointer, calibration, homography, gesture recognition
    Number of Pages: 45
    Language of Content: Slovenian
    Mentor / Comentors:
    Name and SurnameIDFunction
    doc. dr. Matija Marolt271Mentor
    Link to COBISS: http://www.cobiss.si/scripts/cobiss?command=search&base=50070&select=(ID=8067924)
    Institution: University of Ljubljana
    Department: Faculty of Computer and Information Science
    Item ID: 1219
    Date Deposited: 09 Nov 2010 13:45
    Last Modified: 13 Aug 2011 00:38
    URI: http://eprints.fri.uni-lj.si/id/eprint/1219

    Actions (login required)

    View Item