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.

Understanding Mission 2030 Measures

Topics:             Climate Change, Information Visualization, Interactive Articles, Explorable Examples
Supervision:    Christina Humer, opens an external URL in a new window, Marc Streit
Contact:           vds-lab(at)jku.at
Type:                BSc Practicum

JKU aims to become a climate-neutral university by 2030. To reach this goal, JKU employs a range of measures that help with reducing energy consumption. Some of the measures are centrally administered for the entire university, like reducing room heating in winter and room cooling in summer or reducing the building lights. Other measures aim to raise awareness among people and help to reduce energy consumption on an individual level. The latter is, for example, done with posters that show how to optimize people’s individual energy consumption.

In this project, we would like to enhance people’s understanding of the measures described on these posters with an interactive article. The interactive article should help people understand, how much energy can be saved when following these recommendations, and why the measure is meaningful (e.g., why is it useful to disconnect fully charged devices). The article should contain overall information about the topic addressed by a poster and include visualizations that aid the understanding of the provided information. Readers should also be able to interactively change parameters to see how energy consumption changes (e.g., the energy consumption of taking the elevator alone vs. with several people).

JKU Mission 2030

Examples of interactive articles

Explorable Examples

 

Mission 2030 Posters © Image adapted from: https://www.jku.at/en/campus/the-jku-campus/sustainability/the-energy-saving-campaign/

Changes over time when transitioning to commercial dashboarding systems

Topics: visualization, dashboarding systems, qualitative study
Supervision: Conny Walchshofer, Marc Streit
Contact:  vds-lab@jku.at
Type:  BSc Practical Work, and possibly a subsequent BSc Thesis


Many long-established, traditional manufacturing businesses are becoming more digital and data-driven to improve their production. These companies are embracing visual analytics in these transitions through their adoption of commercial dashboarding systems such as Tableau and MS Power BI.

However, transitioning work practices to a new software environment, is often confronted with technical but also socio-technical challenges [Walchshofer et al. 2023, opens an external URL in a new window]. Walchshofer et al. conducted an interview study with 17 workers from an industrial manufacturing company and reported on observations such as hidden/underappreciated labor or a visualization knowledge gap leading to discomfort with interaction in dashboards. As this study represents just a snapshot of time during a lengthy transition process, this student topic focuses on a follow-up study to understand how these challenges change over time.

The goal of this project is to contribute to the design and execution of a qualitative study. No programming knowledge is required. In collaboration with Linköping University (Sweden), we will develop questions for an interview series and conduct the interviews. Audio recordings of these interviews then need to be transcribed and analyzed. The findings need to be compared with the study's results by Walchshofer et al.

Changes of observations when transitioning to a commercial dashboarding system

Lost my Way

Topics: game development, educational games, web programming
Supervision: Günter Wallner
Contact: guenter.wallner@jku.at
Type: MSc Thesis, MSc Practicum

Description

Games have shown to be engaging and valuable tools for education. As such many educational games have been developed to date for a variety of educational topic ranging from language learning to mathematics. At the same time educational games are challenging to design as they need to effectively communicate educational content while being entertaining to play. The goal of this work is to a) convert a previously in Adobe Flash developed game for geometry learning to HTML 5 and deploy it and b) conduct a user study to ascertain its value.

Tasks

Work will include converting the game from Adobe Flash (source code and assets will be provided) into HTML5. The game needs to include logging facilities to be able to reconstruct the solutions to the levels. The converted game needs to be deployed on a web server (space will be provided) and subsequently evaluated with players (e.g., via an online study).

Requirements

  • Good programming skills
  • Knowledge of HTML 5 and web development
  • Knowledge of Adobe Flash is of advantage
  • Interest in game development and design
An image of the game lost my way, showing a grid, a road, and sheeps

Replay Viewer with Event Visualization

Topics: replay analysis, information visualization
Supervision: Günter Wallner
Contact: guenter.wallner@jku.at
Type: BSc Thesis, MSc Practicum, MSc Thesis

Description

Replays are an important part in competitive gaming to review game performance and help in training. Replays are presenting highly detailed information but are time consuming to review as interesting events need to be searched for in the first place. The goal of this work is to developed a replay viewer that uses visualization/event detection to help identify times of interest within the replay. The viewer should be developed for League of Legends matches, for instance, with the help of Open Broadcasting Software but other games could be considered as well.

Tasks

The overall goal is to develop a replay viewer that eases the identification of interesting time intervals. This entails detecting interesting events and providing a timeline-based visualization that assists in jumping to these time periods. The final viewer should be evaluated with players of the game.

Requirements

  • Good programming skills
  • Interest in user studies
  • Knowledge of League of Legends is preferable
A woman playing League of Legends on three screens

Multi-Spectral AOS

Topics: drones, multi-spectral imaging, system communication
Supervision: Oliver Bimber, Mohamed Youssef
Contact: oliver.bimber(at)jku.at
Type: BSc Practicum, BSc 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.

So far, AOS has been applied to the visible spectrum (RGB) and the far-infrared spectrum (thermal) to address many different applications, such as search and rescue, wildfire detection, wild-life observation, and archeology. In this project, we now want to apply a new multi-spectral camera system (Parrot Sequoia+) that simultaneously captures red, green, blue, near-infrared and red edge spectral channels that are useful for other applications, such as agriculture and forestry. In particular the communication between the camera and the ground station should be implemented and evaluated (via PTP / HTTP protocol interfaces).   

Details on AOS:

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

Parrot Sequoia+:

https://www.parrot.com/en/support/documentation/sequoia, opens an external URL in a new window

Multi-Spectral AOS

AOS Waypoint-Flight Module

Topics: drones, drone control, way-point flights
Supervision: Oliver Bimber, Nurullah Özkhan
Contact: oliver.bimber(at)jku.at
Type: BSc Practicum, BSc 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.

In the past year, we have implemented a client-server architecture that enables the control of drones and swarms from the ground. Several students already contributed modules, such as real-time map visualization of drone data. In this project, we want to implement another client module (Python) that allows to interactively define waypoints on a map (i.e., in common ways as it is normally supported by other drone software) that are then executed by our server. Images sampled at the waypoints are then transmitted and can be rendered. Flying drones based on predefined way-points is the common procedure for blue-light organizations. Here, a GUI front-end has to be implemented that control.       

Details on AOS:

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

Current Client-Server Architecture (see bottom of page):

https://github.com/JKU-ICG/AOS/tree/stable_release/AOS%20for%20Drone%20Swarms, opens an external URL in a new window

AOS Waypoint-Flight Module

Drone-Based Wildfire Detection

Topics: drones, image processing, classification, machine learning
Supervision: Oliver BimberMohamed Youssef
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.

In this project we want to extend our AOS simulator to simulate wildfire in an as realistic as possible way. The simulation data can then be used for training classifiers that detect wildfire early and under densely occluded condition.

Details on AOS:

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

wildfire ©Image Source: https://www.thomasnet.com/insights/3-ways-technology-can-fight-the-australian-wildfires/

Volumetric Reconstruction of Occluded Targets

Topics: drones, image processing, volumetric 3D reconstruction, 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.

Computing integral images for multiple distances above the ground leads to a 3D focal stack which contains depth information. Occlusion, however, makes this focal stack very noisy and incomplete. In this project, we want to explore learning-based approaches for volumetric 3D reconstruction and see if they lead to more complete and better results. Using our AOS simulation system, we already have created a database of approx. 500.000 images that can be used for training. 

Details on AOS:

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

3D AOS

Visualization and Explanation of ML-Based Indiciation Expansion in Knowledge Graphs

Topics: visualization, explainable AI, knowledge graphs, healthcare
Supervision: Christian Steinparz, Marc Streit
Contact:  vds-lab@jku.at
Type:  MSc Practical Work, MSc Thesis

Indication expansion involves identifying new potential uses or "indications" for existing drugs. One way to find new indications is to analyze the connections and relationships within pharmaceutical data, including experimental data and literature. Our collaboration partner employs a machine learning model to predict new links in their knowledge graphs, intending to discover relationships between current drugs and diseases for which they have not been previously used. The project focuses on effectively visualizing and explaining these newly predicted links, enabling domain experts to determine the potential of further research into each drug's new possible uses.

Relevant Paper: Knowledge Graphs for Indication Expansion: An Explainable Target-Disease Prediction Method, Gurbuz et al. 2022, opens an external URL in a new window

Indication Expansion Image adapted from the presentation of Knowledge Graphs for Indication Expansion: An Explainable Target-Disease Prediction Method (Gurbuz et al. 2022): https://www.youtube.com/watch?v=ADszHqJhr2Y&ab_channel=BiorelateLtd.