Understanding the Potential of Server-Driven Edge Video Analytics

Qizheng Zhang, Kuntai Du, Neil Agarwal, Ravi Netravali, Junchen Jiang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Scopus citations

Abstract

The proliferation of edge video analytics applications has given rise to a new breed of streaming protocols which stream aggressively compressed videos to remote servers for compute-intensive DNN inference. One popular design paradigm of such protocols is to leverage the server-side DNN to extract useful feedback (e.g. based on a low-quality-encoded stream sent to the server) and use the feedback to inform how the camera should encode and stream the video in the future. In this server-driven approach, an ideal form of feedback should (1) be derived from minimum information from the video sensor (2) incur minimum bandwidth usage to obtain (3) indicate the optimal video streaming/encoding scheme (e.g. the minimum frames/regions that require high encoding quality). However, our preliminary study shows that these idealized requirements are far from being met. Using object detection as an example use case, we demonstrate significant yet untapped room for improvement by considering a broader design space, in terms of how the feedback should be derived from the DNN, how often it should be extracted, and how to determine the encoding quality of the video on which we extract the feedback.

Original languageEnglish (US)
Title of host publicationHotMobile 2022 - Proceedings of the 23rd Annual International Workshop on Mobile Computing Systems and Applications
PublisherAssociation for Computing Machinery, Inc
Pages8-14
Number of pages7
ISBN (Electronic)9781450392181
DOIs
StatePublished - Mar 9 2022
Event23rd Annual International Workshop on Mobile Computing Systems and Applications, HotMobile 2022 - Virtual, Online, United States
Duration: Mar 9 2022Mar 10 2022

Publication series

NameHotMobile 2022 - Proceedings of the 23rd Annual International Workshop on Mobile Computing Systems and Applications

Conference

Conference23rd Annual International Workshop on Mobile Computing Systems and Applications, HotMobile 2022
Country/TerritoryUnited States
CityVirtual, Online
Period3/9/223/10/22

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Computer Science Applications
  • Human-Computer Interaction
  • Software

Keywords

  • deep neural networks
  • egde video analytics
  • saliency
  • server-driven

Fingerprint

Dive into the research topics of 'Understanding the Potential of Server-Driven Edge Video Analytics'. Together they form a unique fingerprint.

Cite this