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 language | English |
|---|---|
| Title of host publication | 2024 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2024 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| ISBN (Electronic) | 9798331530839 |
| DOIs | |
| State | Published - 2024 |
| Event | 2024 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2024 - Danang, Viet Nam Duration: 3 Nov 2024 → 6 Nov 2024 |
Publication series
| Name | 2024 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2024 |
|---|
Conference
| Conference | 2024 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2024 |
|---|---|
| Country/Territory | Viet Nam |
| City | Danang |
| Period | 3/11/24 → 6/11/24 |
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
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver