CloudEye: A New Paradigm of Video Analysis System for Mobile Visual Scenarios

TL;DR

CloudEye is a real-time mobile visual perception system that leverages edge and cloud computing to significantly reduce bandwidth, increase inference speed, and improve detection accuracy in resource-constrained environments.

Contribution

It introduces a novel system architecture with modules for fast inference, feature mining, and quality encoding tailored for mobile vision scenarios.

Findings

Reduces network bandwidth by 69.50%

Increases inference speed by 24.55%

Improves detection accuracy by 67.30%

Abstract

Mobile deep vision systems play a vital role in numerous scenarios. However, deep learning applications in mobile vision scenarios face problems such as tight computing resources. With the development of edge computing, the architecture of edge clouds has mitigated some of the issues related to limited computing resources. However, it has introduced increased latency. To address these challenges, we designed CloudEye which consists of Fast Inference Module, Feature Mining Module and Quality Encode Module. CloudEye is a real-time, efficient mobile visual perception system that leverages content information mining on edge servers in a mobile vision system environment equipped with edge servers and coordinated with cloud servers. Proven by sufficient experiments, we develop a prototype system that reduces network bandwidth usage by 69.50%, increases inference speed by 24.55%, and improves detection accuracy by 67.30%