Abstract: Real-time maps provide first responders with up-to-date situational awareness, enabling them to quickly identify hazards, blocked routes, and other critical information necessary for rapid decision-making. They also enhance coordination among emergency teams by offering live data that supports effective resource allocation and safe navigation in dynamic crisis environments.
High-quality remote sensing data, derived from precise instruments and advanced camera optics, is crucial because it provides detailed, accurate imagery that underpins effective situational awareness for emergency response teams. Therefore, precise measurement methods need to be in place ensuring the best possible image quality.
This talk aims at presenting the real-time mapping solution developed by the German Aerospace Center, Institute of Optical Sensor Systems, Department Security Research and Applications. Furthermore, the image calibration and quality measurement approach will be outlined and demonstrated.

About the Speaker: Henry Meißner is Professor for Geoinformatics at the Technical University of Applied Science Amberg-Weiden and senior researcher at the German Aerospace Center (DLR, opens an external URL in a new window), Institute of Optical Sensor Systems and the Department Security Research and Applications (OS-SEC, opens an external URL in a new window). His academic journey began with foundational studies in Engineering Informatics at TU Ilmenau, opens an external URL in a new window (2000–2004), followed by a diploma (M.Sc. equivalent) in Technical Computer Science from TU Berlin, opens an external URL in a new window (2004–2007) with a focus on Computer Vision and Neuroinformatics/Artificial Intelligence. He then earned a PhD in Computer Science from Humboldt University, opens an external URL in a new window in Berlin (2017–2020). His research is focused on (real-time) Geo-Visualization, 3D-Reconstruction as well as quality measurement and assurance for remote sensing data and products.

Abstract: Gadolinium-based contrast agent (GBCA) dosage reduction in brain MRI is crucial for minimizing adverse side effects, lowering healthcare costs, and reducing environmental impact. Recently, deep learning (DL)-based methods have been proposed to achieve this goal while preserving diagnostic value. However, two key challenges remain: accurately predicting contrast enhancement and synthesizing realistic images. In this talk, we introduce a novel differential contrast-based approach that utilizes subtraction images from pre- and post-contrast MRI scans to enhance low-dose GBCA imaging. By predicting the contrast enhancement signal alone, our method enables image synthesis beyond standard dosage levels. We further incorporate recent diffusion-based embedding techniques to condition our model on physical parameters affecting contrast behavior. Additionally, we apply advanced denoising strategies using pre-trained 2D models or a 3D CNN trained on synthetically degraded subtraction images. Extensive evaluations on synthetic and real datasets across different scanners, field strengths, and contrast agents demonstrate that our approach outperforms state-of-the-art methods. Training and inference code, along with model weights, will be released upon acceptance.

About the Speaker: Erich Kobler received his BSc (2009–2013) and MSc (2013–2015) in Information and Computer Engineering, followed by a PhD in Computer Science (2016–2020, sub auspiciis Praesidentis), all from Graz University of Technology. After a PostDoc position at Graz University of Technology and a role as a senior lecturer at Johannes Kepler University Linz, he co-led the Imaging Lab at the Department of Neurology, University Hospital Bonn. In 2024, he returned to Johannes Kepler University Linz as an Assistant Professor for Machine/Deep Learning in Medical Imaging. In recognition of his PhD research on combining variational methods and deep learning, he received the Award of Excellence in 2021. His research interests include machine learning, medical imaging, and inverse problems.

Abstract:  In the future, humans will cooperate with a wide range of AI-based systems in both working (i.e., decision and recommender systems, language models, or industry robots) and private (i.e., fully- or semi-automated vehicles, smart home applications, or ubiquitous computing systems) environments. Cooperation with these systems involves shared (i.e., concurrent multitasking) and traded (i.e., task switching) interaction. As it is known that frequently changing attention can yield decreased performance as well as higher error rates and stress, future systems must consider human attention as a limited resource to be perceived as valuable and trustworthy. This talk addresses the emerging problems that occur when users frequently switch their attention between multiple systems or activities and proposes to develop a new class of AI-based interactive systems that integrally manage user attention. Therefore, we designed a software architecture that utilizes reinforcement learning and principles of computational rationality to optimize task switching. While computational rationality allows the system to simulate and adapt to different types of users, reinforcement learning does not require labeled training data so that the concept can be applied to a wide range of tasks. The architecture has demonstrated its potential in laboratory studies and is currently extended to support various multitasking situations. The talk concludes with a critical assessment of the underlying concepts while providing a research agenda to improve cooperation with computer systems.

About the Speaker: Philipp Wintersberger is a Full Professor of Intelligent User Interfaces at IT:U Linz, as well as an external lecturer at TU Wien and FH Hagenberg. He leads an interdisciplinary team of scientists on FWF, FFG, and industry-funded research projects focusing on human-machine cooperation in safety-critical AI-based systems. He has (co)authored various works published at major journals and conferences (such as ACM CHI, IUI, AutomotiveUI, or Human Factors), and his contributions have won several awards. Further, he is a member of the ACM AutomotiveUI steering committee, has contributed to HCI conferences in various roles in the past (Technical Program Chair AutomotiveUI’21, Workshop Chair MuM’23, Diversity and Inclusion Chair Muc’22), and is one of the main organizers of the CHI workshop on Explainable Artificial Intelligence (XAI).