Themen fuer Diplom- und SemesterarbeitenIm folgenden sind einige mögliche Semesterarbeiten (SA) und Diplomarbeiten (DA) aufgefuehrt, die in unserer Gruppe derzeit ausgeschrieben sind. Dies ist aber keineswegs eine vollständige Liste, sondern soll vielmehr ein erster Anhaltspunkt sein, was uns derzeit an möglichen Arbeiten vorschwebt. Weitere Anhaltspunkte koennen ältere Arbeiten geben, die in unserer Gruppe ausgeschrieben bzw. durchgeführt wurden. Sie sind auf dieser Seite aufgelistet. Für Fragen zu diesen oder möglichen anderen Themen wendet Euch bitte direkt an die jeweiligen Assistenten oder Prof. Schiele (siehe Kontakt-Seite). Allgemeine Infos: |
Tracking and detection for
overtaking maneuvers 
(Bachelor or Master thesis)
Recently computer vision algorithms are deployed in the area of automotive driver assistance systems. While tasks such as lane tracking or street sign detection are already “solved”, other tasks such as reliable car detection still remain an open research question. Currently we are investigating an computer vision application for overtaking scenarios. In particular we are aiming to detect and track the car to be overtaken. While detection and tracking works fine for sufficient distance already, the frontal end can not be determined with a high precision up to now.
The goal of this thesis is to implement a tracking scheme which is able to detect and track the frontal end of an overtaken car to allow driver assistance functions for changing back to the right lane after the overtaking maneuver is finished.
Environment:
|
Begin: |
|
|
Development Environment: |
|
|
Prerequisites: |
|
|
For more information contact: |
Christian Wojek <wojek@mis.tu-darmstadt.de> S02 | 02, office B104 |
Published September 26th 2008, Christian Wojek
Long-Term, Fine-Grained Actigraphy
(Studienarbeit, Diplomarbeit, Bachelorarbeit)
Actigraphy is a method of activity and sleep study, achieved by strapping a small watch-like unit on a person for an extended period of time. The unit continually records the movements it undergoes, and when the data is later read to a computer, it can be analysed for interesting patterns. This project aims at making a 'smarter' actigraphy unit that not just logs the sensor data, but does a bit of the recognition itself already...
In this thesis, the student is actively involved in a development and research cycle which aims at making a module that is as small and light as possible, and can be worn for long periods (days to weeks). This includes a large amount of embedded programming, learning about basic signal processing and classification algorithms, and a bit of elementary hardware design (including microcontroller interfaces, taking measurements and some surface-mount soldering).
The student will need to evaluate (and wear) his/her own selfbuilt unit for extended periods, and, if the final work is qualitative enough, scientific publication of the student's research will be encouraged, as well as practical usage of the actigraphy module by others.
Our main interest in this project is on the algorithms and research questions, but the unit's purpose is to be applied to problems in circadian rhythm analysis, wake-sleep patterns monitoring, and psychiatric trials with bipolar patients.
You must:
- be motivated to learn, and have a practical mindset
- in possession of creative thinking skills, not afraid to touch hardware and electronics
- know, or have an interest, in embedded sensor signal analysis and machine learning
- be eager to become proficient in C and C++
For more information, contact: Kristof Van Laerhoven, building S02/02, office B112