Scalable and Adaptive Video Analysis System for Multiple Video Streams

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We propose an efficient scalable and adaptive video analysis system for multiple video streams. Our scalable video analysis solution handles large amounts of video analysis efficiently, and the adaptive video analysis approach ensures high performance and reliability while responding to specific requirements and conditions in various application fields. To achieve these goals, we adopt a unified, lightweight, and scalable object detection and feature embedding networks and develop a video analysis system architecture to analyze multiple video streams. The experimental results show that the proposed networks achieve competitive accuracy and the system enables online video analysis for 16 cameras.

Original languageEnglish
Title of host publication2024 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798331530839
DOIs
StatePublished - 2024
Event2024 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2024 - Danang, Viet Nam
Duration: 3 Nov 20246 Nov 2024

Publication series

Name2024 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2024

Conference

Conference2024 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2024
Country/TerritoryViet Nam
CityDanang
Period3/11/246/11/24

Bibliographical note

Publisher Copyright:
© 2024 IEEE.

Keywords

  • feature embedding
  • multi-object tracking
  • object detection
  • Scalable video analysis system
  • unified network

Fingerprint

Dive into the research topics of 'Scalable and Adaptive Video Analysis System for Multiple Video Streams'. Together they form a unique fingerprint.

Cite this