Data-driven windows to accelerate video stream content extraction in complex event processing

Research output: Chapter in Book or Conference Publication/ProceedingConference Publicationpeer-review

2 Citations (Scopus)

Abstract

This work presents a data-driven adaptive windowing approach to accelerate video content extraction in DNN-based Complex Event Processing (CEP) systems. The CEP windows continuously monitor low-level content of incoming video frames and exploit interframe correlations to accelerate the overall DNN content extraction process. The two main contributions are: 1) technique to create micro-batches of similar frames within the window by measuring dissimilarities among them, and 2) optimal frame resolution within micro-batches under specified accuracy thresholds for fast model processing. The initial experimental results show that our adaptive micro-batching approach improves 3.75X model throughput execution while maintaining application-level latency bounds under required accuracy constraints.

Original languageEnglish
Title of host publicationMiddleware Demos and Posters 2019 - Proceedings of the 2019 20th International Middleware Conference Demos and Posters, Part of Middleware 2019
PublisherAssociation for Computing Machinery, Inc
Pages15-16
Number of pages2
ISBN (Electronic)9781450370424
DOIs
Publication statusPublished - 9 Dec 2019
Event20th International Middleware Conference Demos and Posters, Middleware 2019 - Davis, United States
Duration: 9 Dec 201913 Dec 2019

Publication series

NameMiddleware Demos and Posters 2019 - Proceedings of the 2019 20th International Middleware Conference Demos and Posters, Part of Middleware 2019

Conference

Conference20th International Middleware Conference Demos and Posters, Middleware 2019
Country/TerritoryUnited States
CityDavis
Period9/12/1913/12/19

Keywords

  • Complex Event Processing
  • Deep Neural Network
  • High Throughput
  • Video Processing
  • Windows

Fingerprint

Dive into the research topics of 'Data-driven windows to accelerate video stream content extraction in complex event processing'. Together they form a unique fingerprint.

Cite this