Bruno Zatt & Marcelo Porto
Universidade Federal de Pelotas (Brazil)
Princípios de Codificação de Vídeo
Language: Portuguese
Date: October 27th / 09h00 – 11h00
Abstract
Digital videos have become omnipresent along the last few decades. Besides the many applications adopting video technologies, entertainment has grown rapidly due to the massive adoption of streaming services such as Netflix, Amazon Prime, Disney+, Globoplay, and many others. The COVID-19 pandemic further pushed the demand for video services related to home office and remote education. On top of that, users’ demand for ever-increasing video quality and immersion lead to higher resolutions (4K and 8K UHD), frame rates (60 fps, 120 fps), and color depth (HDR). The huge amount of data necessary to represent such contents brings a series of challenges related to video transmission and storage. In this scenario, efficient video compression becomes mandatory. This talk will present the basic concepts of video compression used in current video encoders, as H.264/AVC, HEVC, VP9, VVC, and AV1. The main algorithms and techniques to efficiently compress a video will be presented, as well as a generic video encoder and the complete process from an input video (uncompressed) to an encoded video stream. A brief introduction to the main encoding tools of the state-of-the-art video encoders will be discussed.
Biography
Bruno Zatt received his B.S. and M.S. in Computer Engineering from the Federal University of Rio Grande do Sul (UFRGS), in 2006 and 2008, respectively. He received his Ph.D. degree in Microelectronics from the same university in 2012 with “summa cum laude” distinction. Currently, Bruno Zatt is a Professor at the Federal University of Pelotas (UFPel), Pelotas, Brazil, and a member of the Group of Architectures and Integrated Circuits (GACI) and the Video Technology Research Group (ViTech). He has 16+ years research experience on algorithms and hardware architectures for video processing including 3 years as an intern researcher at the Karlsruhe Institute of Technology (KIT), Karlsruhe, Germany, and experience as a visiting professor at the University of California, Irvine (UCI), USA. Prof. Zatt is a Senior Member of IEEE, member of the IEEE CASS Visual Signal Processing and Communications Technical Committee (VSPCTC), and Associate Editor for the IEEE Transaction on Circuits and Systems for Video Technology (TCSVT). Since 2017, Prof. Zatt holds the status of CNPq productivity research fellow.
Marcelo Schiavon Porto received the M.S. and Ph.D. degrees in computer science from Federal University of Rio Grande do Sul (UFRGS), Brazil, in 2008 and 2012, respectively. He is currently a Professor with the Federal University of Pelotas (UFPel), Brazil, and a member of the Video Technology Research Group (ViTech) and the Group of Architectures and Integrated Circuits (GACI). He is currently a permanent member of the Postgraduate Program in Computing (PPGC) of UFPel. Dr. Porto is a Senior Member of IEEE, and a Member of SBC and SBMicro Brazilian societies. He also has been holding the status of CNPq (National Council for Scientific and Technological Development) Productivity Research Fellow, since 2016. His research interests include video coding, motion estimation algorithms, point cloud compression, coding complexity reduction, and energy-efficient VLSI design for video coding.