Speaker: Guilherme Holsbach Costa (University of Caxias do Sul), visiting professor
Title: On the Super-Resolution Image Reconstruction and Phase Correlation Image Registration: methods, insights, and challenges
Abstract:
In this seminar, we will explore classical methods in image processing, focusing on two key topics. First, we will discuss the methodology of analytical approaches applied to the Least Mean Squares (LMS) algorithm for super-resolution image reconstruction. We will highlight how this analysis framework could also be extended to study LMS applications in image registration. In the second part, we will present an ongoing application in autonomous vehicles, where we employ Phase Correlation for image registration. This method was chosen due to its well-established position in the literature and its potential for straightforward analytical evaluation. We will talk about recent challenges we have encountered in our implementation and our ongoing efforts to overcome them.
Place: Seminar room on the 4th floor of the Henri Poincare (1er cycle) building.