A Deep-Intelligence Framework for Online Video Processing

A Deep-Intelligence Framework for Online Video Processing

big data

Big data

cloud computing

Cloud computing

Computer architecture

deep learning

Deep learning

fault tolerance

Fault tolerance

Hadoop

Machine learning

MapReduce

Real-time systems

Scalability

software development

Software development

software engineering

Software engineering

Storm

Streaming media

video processing

Video data has become the largest source of big data. Owing to video data's complexities, velocity, and volume, public security and other surveillance applications require efficient, intelligent runtime video processing. To address these challenges, a proposed framework combines two cloud-computing technologies: Storm stream processing and Hadoop batch processing. It uses deep learning to realize deep intelligence that can help reveal knowledge hidden in video data. An implementation of this framework combines five architecture styles: service-oriented architecture, publish-subscribe, the Shared Data pattern, MapReduce, and a layered architecture. Evaluations of performance, scalability, and fault tolerance showed the framework's effectiveness. This article is part of a special issue on Software Engineering for Big Data Systems.

44-51

W. Zhang

L. Xu

Z. Li

Q. Lu

Y. Liu

IEEE Software

2016

journalArticle

1937-4194

10.1109/MS.2016.31