Fakultät IV

AI-powered systems navigating everyday human environments can pose challenges to individual’s ethical and social values, presenting particular issues, when systems act upon their own initiative without strong oversight. In my talk, I will focus on research in two distinct areas of technological development where system design has been shaped by human values. Firstly, I will present research in the area of semi-automated driving investigating how distributive fairness principles can be applied to “normal” driving behavior selection, aiming to ensure equitable outcomes for all road users. Secondly, I will present research in the field of robotic mediators where robots take a pro-active role in facilitating interactions among humans. To be accepted in human spaces, they need to be trusted to handle personal information adequately, not only adhering to security and data protection laws, but also aligning with contextual norms. I will discuss user expectation and to what extent robots are capable to comprehend informational norms and act accordingly.

Prof Dr Onofre Martorell (University of the Balearic Islands): Joint fusion and denoising for multi-exposure sequences

29 April 2024, 16-18 h in PB-H 0103

Sequences of images taken with different exposure time can be combined by both multi-exposure fusion (MEF) or high dynamic range (HDR) techniques. In both cases, information from all images of a sequence is combined in order to get an image with a higher amount of details on all areas of the selected reference image. This combination of information can also be used in combination with techniques so as to remove the existing noise on the images. In this presentation we will present two different techniques for joint multi-exposure sequence and denoising which exploit the redundancy of similar patches. The first one is a MEF technique for static images and the second one is a HDR technique applied on RAW data which is able to deal with ghosting artifacts.

Aktualisiert via XIMS am 18.4.2024 von J. Söhlke