A Deep-Intelligence Framework for Online Video Processing
A Deep-Intelligence Framework for Online Video Processing
复制标题
DOI：
10.1109/ms.2016.31
复制
发表时间：
2016-03
期刊：
影响因子：
3.3
通讯作者：
Weishan Zhang;Liang Xu;Zhongwei Li;Q. Lu;Yan Liu
中科院分区：
文献类型：
--
作者：
Weishan Zhang;Liang Xu;Zhongwei Li;Q. Lu;Yan Liu
视频数据已经成为大数据的最大来源。由于视频数据的复杂性、速度和体积，公共安全和其他监控应用需要高效、智能的运行时视频处理。为了应对这些挑战，一个拟议的框架结合了两种云计算技术：Storm流处理和Hadoop批处理。它使用深度学习来实现深度智能，可以帮助揭示隐藏在视频数据中的知识。该框架的实现结合了五种架构风格：面向服务的架构，订阅，共享数据模式，MapReduce和分层架构。性能、可扩展性和容错性的评估表明了该框架的有效性。本文是关于大数据系统软件工程的特刊的一部分。
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.