Studienprojekte

Projekte sind ein essenzieller Bestandteil des Curriculums von Mobile Computing. Die Studierenden bekommen die Möglichkeit, das im Zuge ihres Studiums erworbene theoretische Wissen selbst praktisch umzusetzen. Ein sowohl für StudentInnen als auch für Lehrende immer wieder spannendes Unterrichtskonzept, in dem schon erfolgreiche Startups wie z.B. runtastic und Butleroy ihre Anfänge gefunden haben.

3D Positioning with Visual Camera Input based on Inter-Frame Calculation

Zeitraum
Mar 2015 - Jun 2015
FH Studierende
Andreas Tauböck
FH BetreuerIn
FH-Prof. Dr.-Ing. Jens Krösche

Positioning and Navigation is one of the key factors of the success of mobile devices. Indoor navigation however, is a broadly unsolved problem. Future devices like Google Glass or Microsoft HoloLens could use camera input to solve this problem without additional hardware intelligent systems or environments. The 3D trajectory of a camera given a video sequence is calculated and evaluated using different feature-algorithms calculation-approaches.

Ziel

Positioning and consequently navigation were one of the most important features of smartphones to become an as important part in our live as they are. When talking about Positioning and Navigation we first think of GPS. However, GPS is by far not the only technique to locate a mobile device.

For Indoor Positioning a variety of implementations exist, which require certain modification of the environment or a certain procedure to measure properties of the environment. Today, none of these techniques has led to a commercial success which leaves the problem of indoor positioning largely unsolved.

Imagining a system which is not dependent on certain capabilities of the environment, a camera could bring the necessary data to provide such a service. Different examples like Google Glass, Smartwatches and Microsoft HoloLens show that future mobile devices are not occluded anymore. These gadgets could be a potential target platform for positioning technologies using a camera.

This project investigates which techniques and technologies can be applied to fulfill such a task. Different approaches will be presented and compared with each other considering their accuracy, precision, functionality, error sensitivity and runtime complexity (and therefore energy efficiency)