标题：Real-time video copy detection based on Hadoop
作者：Li, Jing ;Wu, Qiang ;Lian, Xuquan ;Sun, Jiande
作者机构：[Li, Jing ] School of Mechanical and Electrical Engineering, Shandong Management University, Jinan, China;[Lian, Xuquan ] Jd.com, Beijing, China;[Li, 更多
会议名称：6th International Conference on Information Science and Technology, ICIST 2016
会议日期：6 May 2016 through 8 May 2016
来源：6th International Conference on Information Science and Technology, ICIST 2016
关键词：Hadoop; MapReduce; video copy detection; video hash
摘要：With the development of multimedia technology and Internet, the amount of videos in the Internet is increasing quickly. Among the large amount of videos in the Internet, a considerable number of them are copies of original videos, which are simply revised versions of the original ones. The purpose of video copy detection technology is to detect copy videos, which has important applications in video tracking, video content retrieval, video copyright protection and other aspects. The current problem is that real-time video copy detection is often difficult to achieve due to the large amount of video data. Hadoop is a distributed computing platform which is designed for deployment in inexpensive hardware and suitable for those applications with a large data set. All of these characteristics could just meet the requirements of real-time video copy detection technology. In this paper, an attempt is done to develop a real-time video copy detection system based on Hadoop platform, and two video copy detection algorithms are implemented on Hadoop platform, which are the method based on brightness sequence and the method based on TIRI-DCT respectively, and their performances are compared. Experiments show that the use of Hadoop platform can significantly improve the efficiency of video copy detection, which has important practical significance for video tracking and real-time video content retrieval application. © 2016 IEEE.