SurveilEdge: Real-time Video Query based on Collaborative Cloud-Edge Deep Learning

TL;DR

SurveilEdge is a collaborative cloud-edge system that enables real-time surveillance video queries with reduced bandwidth, faster response times, and improved accuracy through optimized CNN training and intelligent task allocation.

Contribution

It introduces a novel collaborative framework combining cloud and edge computing with optimized CNN training and task allocation for efficient real-time video querying.

Findings

Achieves up to 7x less bandwidth cost compared to cloud-only solutions.

Provides 5.4x faster query response times than cloud-only approaches.

Improves query accuracy by up to 43.9% over edge-only methods.

Abstract

The real-time query of massive surveillance video data plays a fundamental role in various smart urban applications such as public safety and intelligent transportation. Traditional cloud-based approaches are not applicable because of high transmission latency and prohibitive bandwidth cost, while edge devices are often incapable of executing complex vision algorithms with low latency and high accuracy due to restricted resources. Given the infeasibility of both cloud-only and edge-only solutions, we present SurveilEdge, a collaborative cloud-edge system for real-time queries of large-scale surveillance video streams. Specifically, we design a convolutional neural network (CNN) training scheme to reduce the training time with high accuracy, and an intelligent task allocator to balance the load among different computing nodes and to achieve the latency-accuracy tradeoff for real-time queries. We implement SurveilEdge on a prototype with multiple edge devices and a public Cloud, and conduct extensive experiments using realworld surveillance video datasets. Evaluation results demonstrate that SurveilEdge manages to achieve up to 7x less bandwidth cost and 5.4x faster query response time than the cloud-only solution; and can improve query accuracy by up to 43.9% and achieve 15.8x speedup respectively, in comparison with edge-only approaches.