Studies
Open Theses

Open Theses

This page lists open theses for bachelor and master students. Individual changes to the topics are possible, please contact the respective supervisor.

In addition, there is the possibility of writing a thesis on a topic of your choice. For this purpose, please contact an employee to discuss the topic in detail.

 

 

Are you looking for work that has already been completed?

OPEN BACHELOR THESES

  • Crowdsourcing turning restrictions from OpenstreetMap
    Road intersections are locations where different movement patterns are observed: traffic participant go ahead, turn right or left, according both to their needs and most importantly to the traffic restrictions applied everytime at the current location (traffic signs). The aim of this thesis is the implementation of a method, where vehicles trajectories acquired from OpenstreetMap (OSM) are analysed in terms of the turning possibilities that drivers have at each intersection location. Final objective is to find out what kind of turning restrictions are found at those locations, like those shown on the figure right.
    Leaders: Zourlidou
    Year: 2019
  • Transformation of point clouds using Generative Adversarial Networks
    The goal of this thesis is to transform a DIM point cloud this way that it behaves like an ALS point cloud for the following processing steps. Firstly, both point clouds are rasterized, where each raster cell describes the distribution in height for all points within a raster cell. These rasterized images from both point clouds are then used to train a Generative Adversarial Network (GAN) such as the pix2pix network. The network outputs transformed height distributions, which can be back-projected to the original point clouds. Finally, those transformed point clouds can then be tested on different processing steps such as registration, change detection or classification.
    Team: Politz, Sester
    Year: 2019
  • Registration of point clouds using Least Squares Adjustment
    The goal of this thesis is to determine global transformation parameter for point cloud tiles or individual flight stripes using the information of local transformation parameters. The local transformation parameters should be derived using least square adjustment considering the different attributes of ALS and DIM point clouds. The quality of those local transformations should be used to weight the observations in a global alignment over a region, which will consequently return stable and uniform global registration parameters and thus will be able to support tiles with weak local transformation results.
    Team: Politz, Brenner
    Year: 2019
  • Registration of point clouds using segments
    The goal of this thesis is to develop different methods, which should register point clouds using segments. The registration on 2D- as well as on 3D-level should be investigated.
    Team: Politz, Brenner
    Year: 2019
  • Navigation and Field Robotics: Pedestrian Navigation – Obstacle Avoidance with Depth Cameras and Electrical Muscle Stimulation
    This is a topic offered by the Human-Computer Interaction Group. In previous projects the Human-Computer Interaction Group investigated a novel approach to control pedestrians' walking direction for navigation. We showed that controlling the direction with electrical muscle stimulation is possible in outdoornavigation scenarios. As a follow-up project we would like to explore - in a collaborative project with the Institute of Cartography and Geoinformatics (IKG) - how this approach can be used for obstacle avoidance in pedestrian navigation scenarios.
    Leaders: Busch
    Year: 2017

OPEN MASTER THESES

  • Crowdsourcing turning restrictions from OpenstreetMap
    Road intersections are locations where different movement patterns are observed: traffic participant go ahead, turn right or left, according both to their needs and most importantly to the traffic restrictions applied everytime at the current location (traffic signs). The aim of this thesis is the implementation of a method, where vehicles trajectories acquired from OpenstreetMap (OSM) are analysed in terms of the turning possibilities that drivers have at each intersection location. Final objective is to find out what kind of turning restrictions are found at those locations, like those shown on the figure right.
    Leaders: Zourlidou
    Year: 2019
  • Transformation of point clouds using Generative Adversarial Networks
    The goal of this thesis is to transform a DIM point cloud this way that it behaves like an ALS point cloud for the following processing steps. Firstly, both point clouds are rasterized, where each raster cell describes the distribution in height for all points within a raster cell. These rasterized images from both point clouds are then used to train a Generative Adversarial Network (GAN) such as the pix2pix network. The network outputs transformed height distributions, which can be back-projected to the original point clouds. Finally, those transformed point clouds can then be tested on different processing steps such as registration, change detection or classification.
    Team: Politz, Sester
    Year: 2019
  • Registration of point clouds using Least Squares Adjustment
    The goal of this thesis is to determine global transformation parameter for point cloud tiles or individual flight stripes using the information of local transformation parameters. The local transformation parameters should be derived using least square adjustment considering the different attributes of ALS and DIM point clouds. The quality of those local transformations should be used to weight the observations in a global alignment over a region, which will consequently return stable and uniform global registration parameters and thus will be able to support tiles with weak local transformation results.
    Team: Politz, Brenner
    Year: 2019
  • Registration of point clouds using segments
    The goal of this thesis is to develop different methods, which should register point clouds using segments. The registration on 2D- as well as on 3D-level should be investigated.
    Team: Politz, Brenner
    Year: 2019
  • Navigation and Field Robotics: Pedestrian Navigation – Obstacle Avoidance with Depth Cameras and Electrical Muscle Stimulation
    This is a topic offered by the Human-Computer Interaction Group. In previous projects the Human-Computer Interaction Group investigated a novel approach to control pedestrians' walking direction for navigation. We showed that controlling the direction with electrical muscle stimulation is possible in outdoornavigation scenarios. As a follow-up project we would like to explore - in a collaborative project with the Institute of Cartography and Geoinformatics (IKG) - how this approach can be used for obstacle avoidance in pedestrian navigation scenarios.
    Leaders: Busch
    Year: 2017
  • Deep Learning: Automatisierte Identifikation von Geländestrukturen am Beispiel von Burgenanlagen
    Mittels Airborne Laserscanning können flächendeckende hochaufgelöste digitale Geländemodelle erstellt werden. Anders als manuell aufgenommene Daten sind diese Daten bis auf eine einfache Klassifikation in Boden und Vegetationspunkte nicht weiter interpretiert. Eine gezielte Interpretation von künstlich-historischen Geländestrukturen muss manuell durchgeführt und mittels Feldbegehung verifiziert werden.
    Leaders: Schulze, Thiemann
    Year: 2017

CONTACT FOR GENERAL QUESTIONS ON THESES

Dipl.-Ing. Frank Thiemann
Address
Appelstraße 9A
30167 Hannover
Building
Room
606
Dipl.-Ing. Frank Thiemann
Address
Appelstraße 9A
30167 Hannover
Building
Room
606