EdgeMA: Model Adaptation System for Real-Time Video Analytics on Edge Devices

Real-time video analytics on edge devices for changing scenes remains a difficult task. As edge devices are usually resource-constrained, edge deep neural networks (DNNs) have fewer weights and shallower architectures than general DNNs. As a result, they only perform well in limited scenarios and ar...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-08
Main Authors: Wang, Liang, Zhang, Nan, Qu, Xiaoyang, Wang, Jianzong, Wan, Jiguang, Li, Guokuan, Hu, Kaiyu, Jiang, Guilin, Xiao, Jing
Format: Article
Language:English
Subjects:
Adaptation
Artificial neural networks
Drift
Mathematical analysis
Real time
Video data
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Real-time video analytics on edge devices for changing scenes remains a difficult task. As edge devices are usually resource-constrained, edge deep neural networks (DNNs) have fewer weights and shallower architectures than general DNNs. As a result, they only perform well in limited scenarios and are sensitive to data drift. In this paper, we introduce EdgeMA, a practical and efficient video analytics system designed to adapt models to shifts in real-world video streams over time, addressing the data drift problem. EdgeMA extracts the gray level co-occurrence matrix based statistical texture feature and uses the Random Forest classifier to detect the domain shift. Moreover, we have incorporated a method of model adaptation based on importance weighting, specifically designed to update models to cope with the label distribution shift. Through rigorous evaluation of EdgeMA on a real-world dataset, our results illustrate that EdgeMA significantly improves inference accuracy.
ISSN:2331-8422