Go to JKU Homepage
Institute of Computer Graphics
What's that?

Institutes, schools, other departments, and programs create their own web content and menus.

To help you better navigate the site, see here where you are at the moment.

Mistake-identification in League of Legends

Topics:             game analytics, detection, AI
Supervision:   Günter Wallner
Contact:          guenter.wallner@jku.at
Type:               MSc Practicum, MSc Thesis

Competitive games can be complicated to learn. As such training tools have emerged that help players understand gameplay mechanics and improve their skills. Such tools can benefit from AI-assisted methods that help identify common mistakes in the first place. This requires defining what these mistakes are in the first place (e.g., through reviewing game guides), translating these into measurable metrics, and then identify instances of these mistakes in telemetry data.

Mistake-identification in League of Legends ©Image Source: https://unsplash.com/photos/By-tZImt0Ms

Trajectory-based Playstyle Identification

Topics:             game analytics, profiling, AI
Supervision:   Günter Wallner
Contact:          guenter.wallner@jku.at
Type:               MSc Practicum, MSc Thesis

Player profiling aimed at creating models of player behavior is one of the key methods in games analytics. So far, profiling is often based on aggregated performance statistics which albeit sufficient for many purposed may miss behavioral subtleties such as in movement characteristics. The goal of the project is develop profiles and identify playstyles based on the trajectories of players. This includes finding appropriate trajectory features on different levels of detail.

Trajectory-based Playstyle Identification ©Image Source: https://www.pexels.com/photo/light-streaks-2131774/

Single and Integral Image Fusion

Topics: drones, image processing, object detection, signal processing, machine learning
Supervision: Oliver Bimber
Contact: oliver.bimber(at)jku.at
Type: BSc Practicum, MSc Practicum, BSc Thesis, MSc Thesis

Airborne Optical Sectioning (AOS) is a wide synthetic-aperture imaging technique that employs manned or unmanned aircraft, to sample images within large (synthetic aperture) areas from above occluded volumes, such as forests. Based on the poses of the aircraft during capturing, these images are computationally combined to integral images by light-field technology. These integral images suppress strong occlusion and reveal targets that remain hidden in single recordings.
These integral images have no occlusion, but also no image details on out-of-focus regions, such as the tree crowns. Furthermore, they are usually computed for the thermal channel while most visual information is contained in RGB images. The goal of this project is to investigate the fusion of integral images and single images, while both could contain different wavelengths. For example, a single RGB image with most visual details but remaining occlusion can be fused with a thermal integral image that has no occlusion but also no visual details.

Details on AOS:

https://github.com/JKU-ICG/AOS/, opens an external URL in a new window

Infrared and Visible Image Fusion using a Deep Learning:

https://github.com/hli1221/imagefusion_deeplearning, opens an external URL in a new window

AOS Object Detection ©Imperial College London

Application of Visualization and Machine Learning Techniques for Knowledge Graphs

Topics:            Knowledge Graphs, Information Visualization, Machine Learning
Supervision:   Christian Steinparz, Marc Streit
Contact:          christian.steinparz@jku.at
Type:               BSc Practicum, BSc Thesis, MSc Practicum, MSc Thesis

Knowledge graphs are widely used to explicitly model and represent knowledge in various domains including semantic web, natural language, and biomedical data. However, due to the potentially large number of nodes and edges, the visualization and navigation of knowledge graphs prove to be challenging. They require the use of advanced techniques such as user interactivity, aggregation, automated analysis, machine learning, and the combination thereof.

Projects in this area can address tasks such as:

  • prototyping a visualization workflow for the exploration of KGs
  • exploring the use of machine learning techniques to identify and extract relevant information from KGs
  • experimenting with advanced ways of positioning nodes and edges such as KG embedding and down-projection
  • visualizing constraint violation information in KGs
  • applying interpretable ML techniques to predict information in the KG and utilizing the model explanations
  • comparison of KGs by developing visual fingerprints or by applying ML-based similarity prediction
  • visualizing provenance data of how KGs have changed over time (due to update/insert/delete of triples)

Students are encouraged to propose their own ideas in relation to the topic.

Application of Visualization and Machine Learning Techniques for Knowledge Graphs