BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Practical Edge Computing for Mobile X Reality - Pan (Ben) Hui\, HK
 UST
DTSTART:20210128T150000Z
DTEND:20210128T160000Z
UID:TALK156304@talks.cam.ac.uk
CONTACT:Srinivasan Keshav
DESCRIPTION:Smartphone is now a necessity of people's daily life\, and we 
 are enjoying various services on it with numerous mobile applications. How
 ever\, the resource and communication limitations of a single mobile devic
 e make it insufficient in satisfying the real-time and interactive constra
 ints of some computation intensive applications\, such as mobile Augmented
  Reality (AR) and mobile Virtual Reality (VR). To bridge the gap\, we util
 ize the processing power of edge servers via task offloading and build pra
 ctical mobile systems which significantly outperforms state-of-the-art mob
 ile systems in terms of latency\, scalability\, quality of experience (QoE
 )\, and many other aspects.\n\nIn the case of mobile Augmented Reality\, l
 arge-scale object recognition is an essential but time-consuming task. To 
 offload the object recognition task and enhance the system performance\, w
 e explore how the GPU and the multi-core architecture on the edge servers 
 would accelerate the large-scale object recognition process. With the care
 fully designed offloading pipeline and edge acceleration\, we are able to 
 finish the whole AR pipeline within one camera frame interval while mainta
 ining high recognition accuracy with large-scale datasets. In the case of 
 mobile Virtual Reality\, existing 360 degree video streaming systems are s
 uffering from insufficient pixel density\, as the video resolution falling
  within the user's field of view (FoV) is relatively low. We utilize the e
 dge server for ultra-high resolution video transcoding and implement a sys
 tem which streams tile-based viewport adaptive 360 degree videos onto the 
 mobile client. With this edge proxy\, we successfully achieve 16K 360 degr
 ee video streaming onto off-the-shelf smartphones\, achieving high frame q
 uality and fluent playback without overwhelming the processing capacity of
  the smartphones.\n\nShort Biography:\n\nPan Hui received his PhD from Com
 puter Laboratory\, University of Cambridge under the supervision of Jon Cr
 owcroft\, and both his Bachelor and MPhil degrees from the University of H
 ong Kong. He is the Nokia Chair in Data Science\, elected by Nokia Bell La
 bs\, at the University of Helsinki and the director of the HKUST-DT System
  and Media Lab at the Hong Kong University of Science and Technology. He w
 as a senior research scientist and then a Distinguished Scientist for Tele
 kom Innovation Laboratories (T-labs) Germany. He is an International Fello
 w of the Royal Academy of Engineering\, a Fellow of the Institute of Elect
 rical and Electronics Engineers\, a Member of the Academia Europaea\, and 
 a Distinguished Scientist of the Association for Computing Machinery.\n\n
LOCATION:https://meet.google.com/ehj-dwaz-rea
END:VEVENT
END:VCALENDAR