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.

Game Map Analytics – Developing Effective and Engaging Analytics

Topics: Game Analytics, mapping data, guidelines

Supervision: Claire Dormann, Günter Wallner, opens an external URL in a new window
Contact:  claire.dormann@jku.at guenter.wallner@jku.at
Type: BSc Practicum, BSc Thesis, MSc Practicum

Map-based analytics aim to reveal interesting patterns that would not be as effectively or efficiently portrayed using other approaches. The use of maps to visualize game analytics is very limited, in term of players data, and especially in term of formats used. In contrast, map-based data analytics use a multiplicity of formats, each one being better at representing some types of data. Examples include choropleth map, time space distribution map, or three-dimensional rectangular map. Moreover, looking at these analytics also show other limitations of game map analytics: they are seldom layered, annotated, animated or interactive. Last, but not least game map analytics are rarely considered in term of engagement.

Thus, in this project / thesis, after surveying briefly the use of game map analytics, and data maps, you will develop two case studies centred on different categories of players data. For your selected game analytics, you will experiment and produce different design solutions, annotating their strengths and weaknesses. After some preliminary evaluation, two designs would be implemented more fully for each case.  To strengthen their effectiveness, dimensions related to overlays, animations, etc., should be integrated to enhance the map functions. Finally, resulting game map analytics will be evaluated by users. The goal of the project is to advance knowledge about game analytics, and produce guidelines that will help game developers.

Map Image ©©© https://mein-mmo.de/fortnite-map-aenderungen-season-5/ ; https://gameanalytics.com/blog/balance-and-flow-maps/

Tools to Support Players and their Productions of Strategic RTS Maps

Topics: Players artefacts, strategic planning, tools, UI

Supervision: Claire Dormann, Günter Wallner, opens an external URL in a new window
Contactclaire.dormann@jku.at guenter.wallner@jku.at
Type: MSc Practicum, MSc thesis

In computer games like Real-time Strategy (RTS), maps help make planning and strategizing possible in ways, which would not be possible otherwise. During combats rounds, players can organise and visualize their tactical moves. To support players engagement and decision making, there is a need for tools that support mapping and strategy planning during gameplay session. Although a few examples might be found, we do know how effective they are, or to which extent they facilitate strategic planning. Moreover, mapping tools can fall short in complexity, oversimplification, or over-automation to be usable during gameplay sessions.

The first phase of this project consists in state of art review of existing players-generated maps for RTS. Then to gain an in-depth understanding of such maps, players would be asked to create maps during gameplay sessions and interviewed about their maps’ production. After analysing the data, players requirements will be extracted and defined. In the second phase of the project, a tool (UI) that supports players will be developed. A survey of related tools could inform its design.  Once the tool is implemented, it will be evaluated during gameplay sessions.

RTS Maps ©©© https://stratsketch.com/; https://www.gamedeveloper.com/disciplines/dynamic-map-elements-in-rts-games

Investigating Map Visualisation Techniques for Game Analytics

Topics: Game Analytics, visualization, cartography, game user research
Supervision: Claire Dormann, Günter Wallner, opens an external URL in a new window
Contactclaire.dormann@jku.at guenter.wallner@jku.at
Type: BSc Practicum, BSc Thesis, MSc Practicum, MSc thesis

Maps are one of the oldest forms of information architecture, they can show distributions and spatial relationships. However, the use of maps to visualize game analytics is very limited: in terms of visualization techniques as well as, data represented. Yet maps serve as visual interfaces to large amounts of data, such as those generated by gameplay.

The goal of this project / thesis is to investigate different visualization techniques and map designs to advance the development and uses of game map analytics. Basic research questions include: What game data are best represented in that format? Through which designs and techniques? Which genres of games? Game-related spatio-temporal data has mostly been discussed in relation to FPS or RTS games but what kind of game map analytics could be useful to RPG? Which design features would enhance these maps? 

This project is centred on the implementation of innovative game map analytics, but also relates to their evaluations and their context of uses. Note that for a MSc thesis, it is expected that elements of project “Game Map Analytics – Developing Effective and Engaging Analytics” would apply to this project as well.

   

Map Image ©©© Erangel, https://giters.com/rokkuran/pubg-analytics; https://gameanalytics.com/blog/playstyle-and-progression/; https://www.it-daily.net/it-management/big-data-analytics/26208-barc-technology-map-for-data-analytics-den-markt-ueberblicken

Developing Embodied Conversational Agents (ECAs) & Bots for Interfacing Game Analytics

Topics: ECAS, games analytics, HCI
Supervision: Claire Dormann, opens an external URL in a new window, Günter Wallner, opens an external URL in a new window
Contact:  claire.dormann@jku.at
Type:  BSc Practicum, MSc Practicum

High volumes of data are generated during game play sessions, especially in massively multiplayers on-line, or social games. Raw data are aggregated in various analytics and metrics that gameplayers and other users can inspect through dashboards. Dashboards’ interfaces can be quite complex and hard to manipulate. Moreover, dashboards do not always match the users needs. The goal of this project is to improve interaction with game analytics through the development of an interface agent. Besides modelling, visualization techniques, interface modalities, as well as, user testing are important aspects of such a project.

agent

Developing an Innovative Augmented Board Game and its Map

Topics: Augmented, Game Design, Map, Cartography

Supervision: Claire Dormann, Günter Wallner, opens an external URL in a new window
Contactclaire.dormann@jku.at, guenter.wallner@jku.at
Type:   BSc Practicum, BSc Thesis, MSc Practicum, MSc thesis

Maps are at the centre of a number of board games. Nowadays, these maps can be enhanced through additional digital components, from mobile App to Spatial Augmented Reality. Thus, complex maps can be produced with different overlays. Augmented maps can also enrich the game space, or allow for more playful game experiences. First a state of art review of augmented board games and augmented maps will be conducted, including software / hardware solutions. Then an innovative board game concept, centred on a map should be elaborated.

The project steps consist in:

  • Develop a board game concept and game brief
  • Design and develop the map
  • Implement the augmented component
  • Complete the game prototype
  • Evaluate the augmented board game

In conclusion, after completing the design document, the project’s implications for augmented board game design, and information visualisation, cartography, or videogame maps should be outlined.

Augmented Map ©©© Smartech group, Barcelona https://www.youtube.com/watch?v=9vF_T6FBivU; Stop thief https://www.engadget.com/

Accelerated MRI reconstruction
 

Topics: medical imaging, machine learning, magnetic resonance imaging
Supervision: Erich Kobler
Contacterich.kobler@jku.at
Type:  BSc Practicum, BSc Thesis, MSc Practicum, MSc Thesis

In the last decades, MR imaging has evolved into a routine imaging technique in clinical practice. The underlying temporal constraint of the acquisition process limits the broad accessibility and drives the operational costs, though. Therefore, numerous techniques (parallel imaging, compressed sensing, ...) have been develop to accelerate the scanning time while maintaining reconstruction quality. Recently, these approaches have been successfully combined with deep learning in various ways. The target of this project is to combine classical methods and deep learning by means of learning a generative model conditioned on the undersampled measurements.

mri_recon ©fastmri.org, https://fastmri.org/

Multi-View 3D Ultrasound Fetal Head Reconstruction

Topics: medical imaging, machine learning, ultrasound imaging
Supervision: Erich Kobler
Contacterich.kobler@jku.at
Type:  BSc Practicum, BSc Thesis, MSc Practicum, MSc Thesis

Among other medical imaging techniques, ultrasound (US) imaging is an inexpensive and widely used imaging technique. However, the quality of US images and their diagnostic value is frequently deteriorated by artifacts, which depend on the probe position and orientation. For instance, the probe orientation influences the image quality since tissue interfaces normal to the beam direction lead higher reflections. In addition, strong acoustic impedance differences between tissues, e.g. around bones, manifest as shadows that occlude the anatomy behind. To resolve these artifacts, the aim of this project is to combining multiple views each acquired with a distinct probe position and/or orientation.

us_recon ©© Wright et al. 2019, https://link.springer.com/chapter/10.1007/978-3-030-32248-9_43

Sampling to estimate Uncertainty in Optical Flow

Topics: computer vision, machine learning, uncertainty
Supervision: Erich Kobler
Contacterich.kobler@jku.at
Type:  BSc Practicum, BSc Thesis, MSc Practicum, MSc Thesis

Optical flow describes the apparent motion of pixels between a pair of images and is therefore an essential building block in numerous computer vision systems (video classification, video editing, temporal super-resolution, autonomous driving/flying, ...).
Currently, the most successful optical flow approaches use neural networks to extract and correlate local information to predict a spatially refined point-estimate of the displacement vector for each pixel.

However, the uncertainties of these predictions are hardly estimated, which is of course of high interest in safety critical scenarios such as autonomous driving.
The starting point of this project is to inspect different uncertainty estimation methods facilitated in machine learning (dropout inference, score-based generative modeling, energy based models, ...) for their applicability to optical flow estimation.
Then, these findings are condensed to develop a model and learning strategy suitable for optical flow estimation that yields results comparable to state-of-the-art while enabling an estimation of uncertainty.

Flow ©Hofinger et al. 2020, https://link.springer.com/chapter/10.1007/978-3-030-58604-1_46

Airborne Optical Sectioning

Topics: drones, image processing, robotics, object detection and classification, user front-end
Supervision: Indrajit Kurmi, opens an external URL in a new windowRakesh Nathan, Oliver Bimber, opens an external URL in a new window
Contactoliver.bimber@jku.at
Type:  BSc Practicum, MSc Practicum, BSc Thesis, MSc Thesis (multiple sub-projects available, see below)

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.

Many researchers and students have contributed to JKU’s innovative AOS framework to explore novel solutions as search and rescue, wildlife observation, and wildfire detection. Several high-impact publications in Nature and Science have covered our scientific findings. See https://github.com/JKU-ICG/AOS/, opens an external URL in a new window for details.

In the course of AOS research we offer the following sub-projects (details on request):

  1. Porting AOS to the newly released  DJI SDK (https://github.com/dji-sdk/Mobile-SDK-Android) and validate with a single DJI Mini 2 (different aspects: image-based rendering, image processing, and anomaly detection on Android platforms)
  2. Porting AOS to Stromkind's (https://www.stromkind.com/) long endurance drones (different aspects: image-based rendering, image processing, and anomaly detection on Raspberry Pi platforms)
  3. Helping to develop an AOS client-server architecture for controlling a drone swarm of 10 DJI Mini 2 (different aspects: video streaming, collision avoidance, sampling optimization, real-time image-based rendering and anomaly detection, etc.)
  4. Implement AOS on NVIDIA Jetson (https://developer.nvidia.com/embedded-computing) and test performance (different aspects: GPU parallelization of image-based rendering, classification, and image processing, such as anomaly detection)

 

We would like to point out that when playing the video, data may be transmitted to external parties. Learn more by reading our data privacy policy
Data protection information

Exploring Distortions in Embeddings by Connecting Points

Topics: dimensionality reduction, interpretable machine learning, visualization
Supervision: Andreas Hinterreiter, opens an external URL in a new window, Marc Streit, opens an external URL in a new window
Contact:  andreas.hinterreiter@jku.at
Type:  BSc Practicum, BSc Thesis, MSc Practicum, MSc Thesis

Modern dimensionality reduction (DR) techniques are useful for visualizing and exploring  complex, high-dimensional datasets. However, especially nonlinear DR techniques such as t-SNE and UMAP are prone to introducing distortions, which can make it difficult to interpret the low-dimensional space correctly.

The goal of this project is to let users explore these distortions by connecting points of interest in low-dimensional scatterplots of projected data. The connecting lines could be calculated in a variety of ways, based on either the low- or the high-dimensional data representations. By exploring such line connections and perhaps comparing different line-connection strategies, users should get a better understanding of the severity of distortions as well as a better intuition for the meaning of sparse regions in the embeddings.

Concept sketch for exploring distortions in embeddings by connecting points

Dashboard Onboarding

Topics: graph traversal, user interface, visualization
Supervision: Vaishali Dhanoa, opens an external URL in a new window, Marc Streit, opens an external URL in a new window
Contact:  vaishali.dhanoa@pro2future.at
Type:  BSc Practicum, BSc Thesis, MSc Practicum, MSc Thesis

The use of dashboards containing multiple interlinked visualizations is quite prevalent these days. However, they often lack a clearly defined way of onboarding a user about their intent and use. Standard procedure often involves a textual description or a human narration.

In this project, we aim at implementing an onboarding strategy as a custom application which enlists the dashboard components as a graph and applies a traversal strategy to onboard the user. The custom application needs to be implemented as a client-side application which also takes user input(s) into account and adapts the graph traversal accordingly.

Dashboard Onboarding

Real-time Training Visualization for League of Legends

Topics: games user research, visualization, analytics
Supervision: , opens an external URL in a new window Günter Wallner
Contact: guenter.wallner@jku.at
Type: MSc Thesis

Training visualizations for players are getting increasingly important in the competitive gaming scene to learn and improve in-game skills. League of Legends (LoL) has emerged as a popular but at the same time difficult to learn game. The goal of this topic is to develop and evaluate solutions (e.g., visualizations, tools) that help players learn and reflect upon in-game activity in real-time by utilizing the Live Client API offered by LoL. The topic can be approached from different perspectives and interested students are encouraged to propose their own ideas in relation to it. Other games than LoL could be focused on as well.

Tasks

The overall goal is to develop visual solutions that can be used in a live setting for training purposes. Overall the steps include 1) requirement analysis with players, 2) develop a solution, and 3) evaluate the solution with players.

Requirements

  • Knowledge analytics or related domains
  • Knowledge of information visualization
  • Good programming skills
  • Interest in exploration of novel solutions
  • Knowledge of League of Legends is of advantage
  • Knowledge of English language (source code comments/documentation should be in English)

Encounter Visualization for DOTA 2

Topics: games user research, visualization, analytics
Supervision: , opens an external URL in a new window Günter Wallner
Contact: guenter.wallner@jku.at
Type: MSc Thesis

Dota2, a multiplayer online battle arena game, is enjoying wide popularity in the competitive gaming scene. The goal of this thesis is to develop a visualization based on the concept of battle maps to convey information of encounters/events happening within Dota2 matches. Battle maps have long been used by historians to concisely convey the course of a battle. This includes 1) detecting interesting events and encounters and 2) condensing movement patterns and contextual information into battle maps. The work can draw upon previous work on encounter detection and battle maps.

Tasks

Work will include developing or including existing encounter detection algorithms to extract events of interest and develop a visualization front-end which conveys information surrounding these events. This can initially happen post-play but extension to real-time detection and visualization should be accounted for. Developed solutions need to be evaluated with the target audience to assess its usefulness.

Requirements

  • Background in analytics or related domains
  • Knowledge of information visualization
  • Good programming skills
  • Willingness to crack problems and to show self-initiative
  • Knowledge of Dota2 is of advantage
  • Knowledge of English language (source code comments/documentation should be in English)