19-12-2009, 10:43 AM
ABSTRACT
This seminar Indoor Positioning and Navigation with Camera Phones discuss about low-cost indoor navigation system runs on off-the-shelf camera phones. The system uses built-in cameras to determine user location in real time by detecting unobtrusive fiduciary markers. The required infrastructure is limited to paper markers and static digital maps, and common devices are used, facilitating quick deployment in new environments. marker-based navigation is easier to use than conventional mobile digital maps. the users' location awareness in navigation tasks improved. Experiences drawn from questionnaires, usage log data, and user interviews further highlight the benefits of this approach.
Introduction:
PS-based navigation systems have become very popular, mainly because they let people rapidly explore unknown areas. However, GPS works only outdoors, because the required satellite links are blocked or unreliable inside buildings. For indoor location sensing, many types of sensors exist, including ultrasonic, infrared, magnetic, and radio sensors. But they all require a permanent electronic infrastructure to facilitate measurements, and localizable objects relying on this infrastructure need special sensors or actuators. Practical problems such as power consumption, wiring, and overall infrastructure cost have inhibited such technologyâ„¢s deployment in entire buildings. In previous work,1 we demonstrated how to detect and decode square fiduciary markers in real time using off-the-shelf camera phones. Such markers contain a 2D barcode that provides a unique ID from the camera image, which the camera phone can use to estimate in real time its position and orientation relative to the marker. The indoor navigation system we describe in this article takes advantage of associating locations with markers to provide an inexpensive, building-wide orientation guide that relies solely on camera phones. Whereas previous work on barcode based location tracking, such as QR Codes (qrcode.com), relies on non-real-time snapshot processing, our approach allows for continuously scanning an environment in real time (15 Hz or more) in search of navigation hints. Thus, navigation scales from sparse, strategically placed fiduciary markers to continuous navigation in 3D. Real-time marker-based tracking of position is available in several desktop-based applications, but it has only recently become available in phones. Consequently, systems for continuous navigation using marker-based tracking havenâ„¢t been studied extensively. Non-real-time marker-based recognition in existing location based services usually takes several seconds, and the service providers typically place markers to highlight a particular location rather than to act as pure navigation landmarks (see the Indoor Navigation and Localization
download the full seminar report
http://wiki.fluidprojectdownload/attachm...0930021000
