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.

Tracking objects on webcam pictures

Zeitraum
Mar 2018 - Jul 2018
FH Studierende
Oliver Barth
FH BetreuerIn
FH-Prof. DI Dr. Erik Sonnleitner

Ziel

In a world of increasing traffic - especially in highly developed countries and their cities – there is a growing need for managing this traffic in an intelligent way.

The goal of this project is to find and implement a suitable object tracking approach to track moving objects from an ordinary and static camera. The object detection should work for both driving directions in parallel as well as for different kinds of intersections.

Umsetzung

In order to develop a suitable traffic management or surveillance system, the current traffic on the road in a specific area has to be recognized and measured, respectively. There exist several traffic measurements systems which are already in use and provide proper data about the current traffic situation, but they are most commonly very inflexible. As an example, induction loops are built directly into the road. Each vehicle moving over this induction loop is counted. This method is very precisely, but on the other hand also very costly and inflexible.

Because of the increasing power and speed of modern computer systems there are more possible and more flexible ways to measure traffic. Considering the low costs of camera systems, they can easily be deployed on interesting road positions to get an insight about the current traffic situation. The video frames produced by the camera can then be used by a computer system to analyze the data in a preferred way.

With the combination of a camera and computer system for utilizing the data, a more flexible and money saving approach for traffic measurements can be established.

In order to develop a camera-based traffic measurement system, a computer system must analyze the video frames using common computer vision techniques.

Due to the fact that the situation on the road can be recorded by the camera form nearly all possible positions in respect to all different weather, light and driving conditions, this task is not a trivial one and will be divided into multiple sub-projects.