Video Stream Analysis in Clouds: An Object Detection and Classification Framework for High Performance Video Analytics
Video Stream Analysis in Clouds: An Object Detection and Classification Framework for High Performance Video Analytics
复制标题
DOI：
10.1109/tcc.2016.2517653
复制
发表时间：
2019-10-01
影响因子：
6.5
通讯作者：
Antonopoulos, Nick
中科院分区：
文献类型：
--
作者：
Anjum, Ashiq;Abdullah, Tariq;Antonopoulos, Nick
目标检测和分类是视频分析的基本任务，也是其他复杂应用的起点。传统的视频分析方法是手动且耗时的。由于人为因素的介入，这些都是主观的。我们提出了一个基于云的视频分析框架，用于可扩展和健壮的视频流分析。该框架通过从录制的视频流中自动检测和分类过程来授权操作员。操作员只指定要分析的视频流的分析标准和持续时间。然后从云存储中提取流，在云上解码和分析。该框架将分析的计算密集型部分执行到云中的GPU服务器上。车辆和人脸检测作为评估框架的两个案例研究，使用一个月的数据和15个节点的云。该框架在6.52小时内对21600个视频流和175gb的数据进行了可靠的目标检测和分类。支持GPU的框架部署对相同数量的视频流执行分析需要3个小时，因此比没有GPU的云部署至少快两倍。
Object detection and classification are the basic tasks in video analytics and become the starting point for other complex applications. Traditional video analytics approaches are manual and time consuming. These are subjective due to the very involvement of human factor. We present a cloud based video analytics framework for scalable and robust analysis of video streams. The framework empowers an operator by automating the object detection and classification process from recorded video streams. An operator only specifies an analysis criteria and duration of video streams to analyse. The streams are then fetched from a cloud storage, decoded and analysed on the cloud. The framework executes compute intensive parts of the analysis to GPU powered servers in the cloud. Vehicle and face detection are presented as two case studies for evaluating the framework, with one month of data and a 15 node cloud. The framework reliably performed object detection and classification on the data, comprising of 21,600 video streams and 175 GB in size, in 6.52 hours. The GPU enabled deployment of the framework took 3 hours to perform analysis on the same number of video streams, thus making it at least twice as fast than the cloud deployment without GPUs.