VaBUS: Edge-Cloud Real-Time Video Analytics via Background Understanding and Subtraction

Edge-cloud collaborative video analytics is transforming the way data is being handled, processed, and transmitted from the ever-growing number of surveillance cameras around the world. To avoid wasting limited bandwidth on unrelated content transmission, existing video analytics solutions usually p...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal on selected areas in communications 2023-01, Vol.41 (1), p.90-106
Main Authors: Wang, Hanling, Li, Qing, Sun, Heyang, Chen, Zuozhou, Hao, Yingqian, Peng, Junkun, Yuan, Zhenhui, Fu, Junsheng, Jiang, Yong
Format: Article
Language:English
Subjects:
Bandwidth
Bandwidths
Cameras
Clouds
Collaboration
Communications systems
Consumption
Context
Edge-cloud collaborative computing
Image compression
Image edge detection
Mathematical analysis
Object recognition
Real time
Real-time systems
semantic compression
Spatial filtering
Streaming media
Subtraction
Surveillance
task-oriented communication system
video analytics
Video transmission
Visual analytics
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Edge-cloud collaborative video analytics is transforming the way data is being handled, processed, and transmitted from the ever-growing number of surveillance cameras around the world. To avoid wasting limited bandwidth on unrelated content transmission, existing video analytics solutions usually perform temporal or spatial filtering to realize aggressive compression of irrelevant pixels. However, most of them work in a context-agnostic way while being oblivious to the circumstances where the video content is happening and the context-dependent characteristics under the hood. In this work, we propose VaBUS, a real-time video analytics system that leverages the rich contextual information of surveillance cameras to reduce bandwidth consumption for semantic compression. As a task-oriented communication system, VaBUS dynamically maintains the background image of the video on the edge with minimal system overhead and sends only highly confident Region of Interests (RoIs) to the cloud through adaptive weighting and encoding. With a lightweight experience-driven learning module, VaBUS is able to achieve high offline inference accuracy even when network congestion occurs. Experimental results show that VaBUS reduces bandwidth consumption by 25.0%-76.9% while achieving 90.7% accuracy for both the object detection and human keypoint detection tasks.
ISSN:0733-8716
1558-0008
DOI:10.1109/JSAC.2022.3221995