Streaming Video Analytics On The Edge With Asynchronous Cloud Support

TL;DR

This paper introduces REACT, a framework that combines edge and cloud computing to enhance video object detection accuracy while maintaining low latency in IoT and mobile applications.

Contribution

The paper proposes a novel edge-cloud fusion algorithm and a framework that significantly improves DNN-based video analytics accuracy by leveraging cloud resources.

Findings

Fusion approach outperforms edge-only and cloud-only methods by up to 50% in accuracy.

REACT maintains low latency while achieving high accuracy across various system constraints.

The framework adapts to different network bandwidths and GPU availability for optimized performance.

Abstract

Emerging Internet of Things (IoT) and mobile computing applications are expected to support latency-sensitive deep neural network (DNN) workloads. To realize this vision, the Internet is evolving towards an edge-computing architecture, where computing infrastructure is located closer to the end device to help achieve low latency. However, edge computing may have limited resources compared to cloud environments and thus, cannot run large DNN models that often have high accuracy. In this work, we develop REACT, a framework that leverages cloud resources to execute large DNN models with higher accuracy to improve the accuracy of models running on edge devices. To do so, we propose a novel edge-cloud fusion algorithm that fuses edge and cloud predictions, achieving low latency and high accuracy. We extensively evaluate our approach and show that our approach can significantly improve the accuracy compared to baseline approaches. We focus specifically on object detection in videos (applicable in many video analytics scenarios) and show that the fused edge-cloud predictions can outperform the accuracy of edge-only and cloud-only scenarios by as much as 50%. We also show that REACT can achieve good performance across tradeoff points by choosing a wide range of system parameters to satisfy use-case specific constraints, such as limited network bandwidth or GPU cycles.