Point Cloud Compression and Communication
题目：Point Cloud Compression and Communication
报告人：Zhu Li Kong University of Missouri, Kansas City
时 间：2019 年 12 月6 日（周五二）14:00 —16:00
Abstract: Point cloud data arise from depth sensing and capturing for both auto driving/navigation/smart city, as well as immersive content capture and VR/AR playback applications. Recent advances in sensor technology and algorithms, especially 77Ghz MIMO radar systems, and high resolution structured light in conjunction with very high resolution RGB camera arrays, have made point cloud capture getting closer to real world applications. In this talk I will overview the related research at the Multimedia Computing & Communication Lab at UMKC, discuss the main technical challenges and solutions in point cloud capture, compression and communication for auto driving and smart city applications, especially the scalable geometry compression, as well as the video based attributes compression problems, we will introduce our recent results in advanced 3D motion model, occupancy map driven rate-distortion optimization and multi-attribute compression that significantly advanced the state of art in video based PCC.
Short Bio: Zhu Li is an associated professor with the Dept of CSEE, University of Missouri, Kansas City, USA, directs the NSF I/UCRC Center for Big Learning at UMKC. He received his PhD from Electrical & Computer Engineering from Northwestern University in 2004, and was the AFRL Summer Faculty at the US Air Force Academy, UAV Research Center, 2016, 2017 and 2018. He was Sr. Staff Researcher/Sr. Manager with Samsung Research America's Multimedia Core Standards Research Lab in Dallas, from 2012-2015, Assistant Professor with the Dept of Computing, The HongKong Polytechnic University from 2008 to 2010, and a Principal Staff Research Engineer with the Multimedia Research Lab (MRL), Motorola Labs, Schaumburg, Illinois, from 2000 to 2008. His research interests include image/video analysis, compression, and communication and associated optimization and machine learning tools. He has 46 issued or pending patents, 100+ publications in book chapters, journals, conference proceedings and standards contributions in these areas. He served and serving as Associated Editor for IEEE Trans on Image Processing (2019~), IEEE Trans on Multimedia (2015-19), and IEEE Trans on Circuits & System for Video Tech (2016~19). He received a Best Paper Award from IEEE Int'l Conf on Multimedia & Expo (ICME) at Toronto, 2006, and a Best Paper Award from IEEE Int'l Conf on Image Processing (ICIP) at San Antonio, 2007.