Computer Science master's thesis

Important notice (February, 23rd 2019): Two papers have been accepted originating from this master thesis. They have been published now! Consequently, the master thesis document is also available on this website from now on.

Welcome on my website accompanying my master's thesis in the course Computer Science. My name is Adam Kalisz, I have finished my degree at the Friedrich-Alexander-Universität Erlangen-Nürnberg in July 2018.

For my thesis I chose to work on "Fusion of GPS and Visual SLAM to improve Localization of autonomous vehicles in urban environments". I make this work publicly available through this website. Please take a look in the "abstract" section for an overview.

You can download the master thesis via this link:
https://master.kalisz.co/MasterThesis_AdamKalisz_Online.pdf (120 MB)

Here is a video of one of the test sessions done with the Direct Sparse Odometry algorithm:

And here is a work in progress video (please keep in mind, that it is not yet finished) about the BSLAMSIM-Paper (see below the video):

Publications

  1. VISAPP 2019: "B-SLAM-SIM: A novel approach to evaluate the fusion of Visual SLAM and GPS by example of Direct Sparse Odometry and Blender" by Adam Kalisz, Florian Particke, Dominik Penk, Markus Hiller and Jörn Thielecke.
    Link (VISAPP technical program): http://insticc.org/node/TechnicalProgram/visigrapp/presentationDetails/73753
  2. DICTA 2018: "Systematic Analysis of Direct Sparse Odometry" by Florian Particke, Adam Kalisz, Christian Hofmann, Markus Hiller, Henrik Bey and Jörn Thielecke.
    Link (IEEEXPLORE): https://ieeexplore.ieee.org/document/8615807

Images

Illustrative image from the thesis
Illustrative image from the thesis
Illustrative image from the thesis
Illustrative image from the thesis
Illustrative image from the thesis
Illustrative image from the thesis
Illustrative image from the thesis

Sensor Recording Tool (HTML 5 App):

In order to record some additional sensor data together with the video, I have created a simple App to record sensor data from a phone. You can find it here:

Open the HTML 5 Sensor Recorder.

GPS Track Viewer (HTML 5 App):

To visualize the recorded GPS signal, I have created yet another simple App to show the GPS trajectory on a map. You can find it here:

Open the HTML 5 GPS Tracks.

Github repository:

The final research papers, additional tools, data or similar will be hosted on GitHub. You can find it here:

Open the GitHub page.

Presentations (aka Studentenrunde):

During my master thesis, I had to prepare a presentation about the current state each week. You can see a subset of them here:

Thank you for visiting my website.