ECE Distinguished Seminar: Guohong Cao
Wednesday, October 25, 2023 - 11 a.m.
Guohong Cao
Distinguished Professor
Computer Science and Engineering
Pennsylvania State University
"Deep Learning Video Analytics with Edge Computing"
ECE 530 | Zoom link
Abstract
The widespread adoption of IoT cameras including surveillance cameras, dash-mounted cameras, Google glass, and phone cameras, along with recent advancements in video analytics, has enabled many practical applications in traffic control, surveillance, security, digital assistants, and more. Many of these applications rely on computationally intensive deep learning techniques. To meet the stringent requirements for low latency and substantial computational resources in these applications, we advocate for supporting video analytics with edge computing. In this talk, I will present our TargetFinder project, which leverages video analytics and IoT cameras to locate targets while preserving user privacy. To address the resource limitations of mobile devices, we have developed techniques to determine which part of the computation should be offloaded to edge servers. Additionally, with the increasing integration of neural processing units (NPUs) into mobile devices, I will discuss our approaches to accelerate deep learning through edge computing and NPUs on mobile devices.
BIO
Guohong Cao is a distinguished professor in the Department of Computer Science and Engineering at Pennsylvania State University. His research interests include wireless networks, mobile computing, machine learning, wireless security and privacy, and Internet of Things. He has published more than 200 papers which have been cited over 25,000 times, with an h-index of 87. He has served on the editorial board of IEEE Transactions on Mobile Computing, IEEE Transactions on Wireless Communications, and IEEE Transactions on Vehicular Technology, and has served on the organizing and technical program committees of many conferences, including the TPC Chair/Co-Chair of IEEE SRDS, MASS, and INFOCOM. He has received several best paper awards, the IEEE INFOCOM Test of Time award, and the NSF CAREER award. He is a Fellow of the AAAS and a Fellow of the IEEE.