ECCVideo: A Scalable Edge Cloud Collaborative Video Analysis System

Video analysis drives a wide range of applications in the fields of public safety, autonomous vehicles, etc. , with the great potential to impact society. Traditional cloud-based approaches are not applicable because of prohibitive bandwidth consumption and high response latency, while simply edge-based video analysis suffers from large computation delay, considering the restricted computing capacity of edge servers. Therefore, in this article, we focus on low-latency edge-cloud collaborative video analytic applications (ECCVApps) by making full use of resources at both the edge and cloud. Particularly, we present an edge-cloud collaborative video analysis system called ECCVideo, to support the unified management of heterogeneous servers and facilitate the development and deployment of large-scale ECCVApps. Under ECCVideo, we design the application architecture of ECCVApps, including presentation paradigm, transparent communication services, and full lifecycle management. To validate the proposed system, a real-time object detection application is deployed on the ECCVideo prototype.

Authors

• Qing Han
• Xuebin Ren Xi'an Jiaotong University
• Peng Zhao Nanjing University
• Yimeng Wang College of Computer Science and Technology, Jilin University, China
• Luhui Wang
• Cong Zhao Xi'an Jiaotong University
• Xinyu Yang Nankai University

Keywords

• Image edge detection
• Servers
• Collaboration
• Cloud computing
• Cameras
• Streaming media
• Computer architecture
• Video Analysis
• Edge Computing
• Collaborative Analysis
• Video Analysis System
• Cloud-edge Collaboration
• Collaborative Video
• Deep Neural Network
• Rational Design
• Object Detection
• Autonomous Vehicles
• Video Data
• Network Resources
• Communication Services
• Operation And Maintenance
• Development Of Artificial Intelligence
• Unified Manner
• Video Surveillance
• Unique Platform
• Storage Resources
• Edge Server
• Edge Devices
• Software Development Kit
• Raspberry Pi
• Market System
• Lightweight Convolutional Neural Network
• Mapping Relationship
• Storage Services
• User Requirements
• Target Image
• Communication Design