This tutorial overviews the trend of visual content perception from the visual quality assessment: introduction of the achievements of visual quality assessment during the past decade and presentation of some of new visual quality assessment application driven methods. Some open problems in visual quality assessment are also discussed for the potential research in the future. In particular, we will present ongoing challenges to deal with uncertainty of ground truth data when developing visual quality assessment models at the age of deep learning.
Patrick Le Callet (IEEE fellow) received both an M.Sc. and a PhD degree in image processing from Ecole polytechnique de l’Université de Nantes. He was also a student at the Ecole Normale Superieure de Cachan where he sat the “Aggrégation” (credentialing exam) in electronics of the French National Education. He worked as an Assistant Professor from 1997 to 1999 and as a full time lecturer from 1999 to 2003 at the Department of Electrical Engineering of Technical Institute of the University of Nantes (IUT). Since 2003, he teaches at Ecole polytechnique de l’Université de Nantes (Engineering School) in the Electrical Engineering and the Computer Science departments where is now a Full Professor. He led for ten years (2006-16) the Image and Video Communication lab at CNRS IRCCyN and was one of the five members (2013-16) of the Steering Board of CNRS IRCCyN (250 researchers). Since January 2017, he is one of the seven members of the steering Board the CNRS LS2N lab (450 researchers), as representative of Polytech Nantes. He is also since 2015 the scientific director of the cluster “Ouest Industries Créatives”, a five year program gathering more than 10 institutions (including 3 universities). “Ouest Industries Créatives” aims to strengthen Research, Education & Innovation of the Region Pays de Loire in the field of Creative Industries. He is mostly engaged in research dealing cognitive computing. His current centers of interest are Quality of Experiences assessment, Visual Attention modeling and applications, Perceptual Video Coding and Immersive Media Processing. He is co-author of more than 250 publications and communications and co-inventor of 16 international patents on these topics. He serves or has been served as associate editor or guest editor for several Journals such as IEEE TIP, IEEE STSP, IEEE TCSVT, SPRINGER EURASIP Journal on Image and Video Processing, and SPIE JEI. He is serving in IEEE IVMSP-TC (2015- to present) and IEEE MMSP-TC (2015-to present)and one the founding member of EURASIP SAT (Special Areas Team) on Image and Video Processing.
The last years have witnessed a growing evolution and diversification of Augmented and Virtual Reality technologies to such an extent that the definition of Extended Reality (XR) is nowadays used to gather all of them. Such development has been fostered by the recent technical improvements of wearable AR devices and the availability of highly-effective computer vision algorithms. Modern platforms integrate effective 3D acquisition sensors with engaging displays and highly-accurate classification strategies. These have enabled a seamless integration of both virtual and real objects allowing the user to relate with them in a natural way and access a huge set of additional information. The tutorial will offer an overview of the latest signal processing applications employed in XR systems that have been designed for portable and wearable devices. In detail, the focus will be on 1) modeling the surrounding reality; 2) enabling an accurate Human-Computer interaction via gesture and voice interfaces; 3) providing a reliable visual and aural feedback to the user. The talk will overview some emerging applications in medical and industrial fields where the adoption of wearable XR technology has brought some significant breakthroughs. In the final part, the talk will be concerned with the compression, transmission, and visualization of 3D models focusing on low complexity processing strategies for point cloud data and highlighting the new challenges that are posed to their implementation on wearable devices.
Simone Milani received his Laurea Degree (5 years course) from the University of Padova, Italy, on December 2002. On March 2007 he received a Ph.D. title in Electronic and Telecommunications Engineering by the same institution. From January 2007 until April 2014, he was Post-Doc researcher at the University of Padova, University of Udine, and at Politecnico di Milano. Since May 2014 he has been Assistant Professor at the Department of Information Engineering of the University of Padova, teaching “Source Coding”, “Computer vision and 3D Graphics”, “3D Augmented Reality”, and "Digital Forensics".
His main research topics
are digital signal processing, image and video compression, 3D acquisition and coding, virtual and augmented reality applications. He is also active in the fields of multimedia forensics and security.
He is
also a IEEE member of Information Theory and Signal Processing Societies and he has also been a reviewer for many international magazines and conferences.
He has also served as international scientific expert for the Agence Nationale de la Recherce (ANR). Since 2018, he is member of the IEEE SPS Regional Committee (Region 8).
In autonomous systems, self-awareness capabilities are useful to allow artificial agents to detect abnormal situations based on previous experiences. Self-learning abilities are essential to improve autonomous systems' situational awareness and detection of normal/abnormal situations. This tutorial presents methods for incremental learning of new models by an autonomous agent. Available learned models can dynamically generate probabilistic predictions as well as evaluate their mismatch from current observations. Observed mismatches are grouped through an unsupervised learning strategy into different classes, each of them corresponding to a dynamic model in a given region of the state space. Such clusters define switching Dynamic Bayesian Networks (DBNs) employed for predicting future instances and detect anomalies. Inferences generated by several DBNs that use different sensorial data are compared quantitatively. Moreover, in the second part of the tutorial, a graph matching technique for activity detection in autonomous agents by using the Gromov-Wasserstein framework will be described. A clustering approach is used to discretize continuous agents' states related to a specific task into a set of nodes with similar objectives. Additionally, a probabilistic transition matrix between nodes is used as edges weights to build a graph. An abnormal area is extracted, based on a sub-graph that encodes the differences between coupled of activities. Such sub-graph is obtained by applying a threshold on the optimal transport matrix, which is obtained through the graph matching procedure. For testing the proposed approach, it is considered the multisensory data generated by a robot performing various tasks in a controlled environment and a real autonomous vehicle moving at a University Campus.
Lucio Marcenaro enjoys over 20 years experience in image and video sequence analysis, and authored about 120 technical papers related to signal and video processing for computer vision. An Electronic Engineering graduate from Genova University in 1999, he received his PhD in Computer Science and Electronic Engineering from the same University in 2003. From 2003 to 2010 he was CEO and development manager at TechnoAware srl. From March 2011, he became Assistant Professor in Telecommunications for the Faculty of Engineering at the Department of Electrical, Electronic, Telecommunications Engineering and Naval Architecture (DITEN) at the University of Genova where he teaches the courses of Pervasive Electronics and Computer Programming and Telematics. He is the principal scientific and technical coordinator of the Ambient Awareness Lab (A2Lab), with TechnoAware srl. His main current research interests are: video processing for event recognition, detection and localization of objects in complex scenes, distributed heterogeneous sensors ambient awareness systems, ambient intelligence and bio-inspired cognitive systems. Lucio Marcenaro is Technical Program Co-Chair for 13th International Conference on Distributed Smart Cameras (ICDSC) and co-organizer for the 2019 Summer School on Signal Processing (S3P), General Chair of the Symposium on Signal Processing for Understanding Crowd Dynamics organized within the 2016 IEEE GlobalSIP, and Steering Committee Member of the IEEE Advanced Video and Signal Based Surveillance (AVSS) since 2014. He is active within the IEEE Signal Processing Italy Chapter (Secretary and Treasurer from 2011 to 2016) that is organizing meetings and events in Italy for promoting the IEEE Signal Processing Society activities in Italy. He is Director of Student Services Committee (2018-2020) of the IEEE SPS, organizing yearly SPCup and VIPCup. He is Associate Editor for IEEE Transactions on Image Processing and IEEE Transactions on Circuits and Systems for Video Technology since 2018 and 2019, respectively.