• June 10, 2022 at 14:30

    Invited speaker : Prof. Csaba Benedek , SZTAKI , Budapest, Hungary
    Title: Multi-sensorial Urban Environment Perception
    Abstract: In the past decade we have witnessed an explosion of new technologies for acquisition and understanding of environmental information. 3D vision systems of self-driving vehicles can be used for -apart from safe navigation- real time mapping of the environment, detecting and analyzing static (traffic signs, power lines, vegetation, street furniture), and dynamic (traffic flow, crowd gathering, unusual events) scene elements. On the other hand, new generation geo-information systems (GIS) store extremely detailed 3D maps about the cities, consisting of dense 3D point clouds, registered camera images and semantic metadata. In this talk, I present new techniques to facilitate the joint exploitation of the measurements of car mounted online sensing platforms, and offline 3D environmental data obtained by Mobile Laser Scanning (MLS) technology in urban environment. First RangeMRF, a Lidar based real time and accurate self-localization and change detection approach is presented for self-driving vehicles, using as reference high resolution 3D point cloud maps of the environment obtained through Mobile Laser Scanning (MLS). Second, we propose an end-to-end, fully automatic, online camera- Lidar calibration approach, for application in self driving vehicle navigation. Finally, ChangeGAN, a novel deep neural network-based change detection approach is introduced, which can robustly extract changes between sparse and weakly registered point clouds obtained in a complex street-level environment, tolerating up to 1m translation and 10 degrees rotation misalignment between the corresponding 3D point cloud frames.
    Bio: Dr. Csaba Benedek is a scientific advisor (D.Sc.) with the Machine Perception Research Laboratory of the Institute for Computer Science and Control (SZTAKI) in Budapest, where he is the head of the Research Group on Geo-Information Computing. He also works as a full professor with the Faculty of Information Technology and Bionics of the Péter Pázmány Catholic University. Between 2008 and 2009 he was a postdoctoral researcher at INRIA Sophia-Antipolis, working in the Ariana Project Team. Dr. Benedek is the current president of the Hungarian Image Processing and Pattern Recognition Society (Képaf), the vice chairman of the John von Neumann Computer Society, and the Hungarian Governing Board Member of the International Association for Pattern Recognition (IAPR). He is a Senior Member of IEEE, and an Associate Editor of Digital Signal Processing (Elsevier) journal. He received various awards including the Bolyai plaquette from the Hungarian Academy of Sciences (HAS) 2019 , Imreh Csanád supervisor plaquette from the Hungarian National Scientific Student Conference (OTDK) (2019), and the Michelberger Master Award from the Hungarian Academy of Engineering (2020). He has been the manager of various national and international research projects in the recent years. His research interests include Bayesian image and point cloud segmentation, object extraction, change detection, machine learning applications and GIS data analysis.
    Location: Euler bleu


  • March 25, 2020 at 14:30  “postponed due to COVID19”

    Invited speaker : Dr. Igor Rizaev, Bristol University, Dept. EEE, UK
    Title: Simulating SAR images: A numerical analysis of sea waves and ship wakes
    Abstract: In the last decades in oceanic engineering and remote sensing of the ocean, many studies have focused on the SAR imaging mechanisms for maritime applications.

    Indeed, SAR images of the ocean and sea surface provide useful information about meteorological conditions, environmental protection, wave structure, ship monitoring, energy generation, and other fields. Despite solid experience in SAR ocean studies, the understanding of radar ocean scenes is still in its infancy. Since the availability of real SAR images is limited, more attention is being paid to SAR simulation. Methods for ship wake detection are mostly based on real SAR images. This is due to SAR imaging having achieved considerable maturity and becoming particularly effective for their visualization, in particular through Bragg resonance scattering. However, in different environmental conditions, it is often difficult, sometimes impossible, to consider all possible factors that can dramatically change ship wake visualization. SAR image simulations allow the analysis of different factors, such as the wind speed and direction, fetch length (sea state factors), ship parameters, platform parameters (airborne and satellite SAR platforms), SAR scanning parameters, which make a significant contribution in visualization of sea waves and ship wakes in SAR images.

    On the other hand, in order to better understand the simulation approach, it is necessary to consider the features of real SAR image formation. Key parameters for the simulation (wind speed and direction) can be extracted from the real SAR images using an image spectral analysis and geophysical model functions.

    This seminar will help provide a better understanding of the multiple contributing factors that influence SAR image simulation such as sea state, wind condition, SAR systems parameters, spatial resolution, etc.

    Bio: TBD
    Location: Euler bleu