.png){kind=icon}
返回
Large-scale Video Analytics with Cloud-Edge Collaborative Continuous Learning
.png){kind=icon}
OA
AI
DOI：10.1145/3624478.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep learning-based video analytics demands high network bandwidth to ferry the large volume of data when deployed on the cloud. When incorporated at the edge side, only lightweight deep neural network (DNN) models are affordable due to computational constraint. In this article, a cloud-edge collaborative architecture is proposed combining edge-based inference with cloud-assisted continuous learning. Lightweight DNNmodels are maintained at the edge servers and continuously retrainedwith a more comprehensive model on the cloud to achieve high video analytics performance while reducing the amount of data transmitted between edge servers and the cloud. The proposed design faces the challenge of constraints of both computation resources at the edge servers and network bandwidth of the edge-cloud links. An accuracy gradient-based resource allocation algorithm is proposed to allocate the limited computation and network resources across different video streams to achieve the maximum overall performance. A prototype system is implemented and experiment results demonstrate the effectiveness of our system with up to 28.6% absolute mean average precision gain compared with alternative designs.
Keyword:
Edge computing
video analytics
distributed system
continuous learning
期刊
IF:
4.7
论文数:
1.0K
被引数:
2.0K
机构
引用论文
A Longitudinal Study: Changes in Cortical Thickness and Surface Area during Pubertal Maturation.png)
PLOS ONE
OAAI
PLOS ONEIF0
OAAI分享收藏
查看更多内容