A framework for scalable cloud video recorder system in surveillance environment 2012 9th International Conference on Ubiquitous Intelligence and Computing.

A framework for scalable cloud video recorder system in surveillance environment

2012 9th International Conference on Ubiquitous Intelligence and Computing and 9th International Conference on Autonomic and Trusted Computing

Speaker: 劉源蔁

Introduction

Evolution for IP based Video Survellance The codec, H.264

could even make over one hundred compression ratio for video data

Trend from DVR to NVR部署規劃 與 擴充延展

佈線

隨插即用

超高清畫質錄影

錄影儲存

Hybrid DVR/NVR

Trend From NVR to CVRMost deployment architecture for

large scale video recording solution are fix connection model.

Each NVR responsible for 64 camera sources, and ten NVR can support 640 camera sources.

Fix connection NVR environment

Cloud computing and Virtualization

Video SurveillanceBuild a central cluster for large

wide area, large scale camera network in campus under Hadoop distributed file system.

Existing Video Recording systemsCurrently, high level hardware based

network based video recorder device may support 64 channels of concurrent streaming source.

Geovision’s IP surveillance software and NUUO’s Central Management System .

Scenario for Cloud Video Recorder System

System ArchitectureVirtualizationStream CollectorStreaming

ServerHadoop File

SystemPolicy controllerIntelligent

AnalysisWeb server

Deployment design for Public cloud

Deployment design for Private/hybrid cloud

EXPERIMENT DESIGN &DISCUSSIONExperiment setupBandwidth usageBackup issueVideo Analysis using Mapreduce

technologyUser monitoring

Backup issue

Video Analysis using Map Reduce technology

User monitoringReal time Transcending

Streaming technology

CONCLUSION AND FUTURE WORKSMore experiments in proposed

system, such as deploy one thousand real time source and observe its outcome.

Intelligent and Real-time Motion detection: apply Map/Reduce framework to make real time patent recognition using replica data on backup node.