基于深度学习的视频检索系统设计与实现  

Design and Implementation of Video Retrieval System Based on Deep Learning

作　　者：姚锦江 程允权 Yao Jinjiang;Cheng Yunquan(Guangzhou College,South China University of Technology,Guangzhou 510800,China;Guangzhou Jingzhuan Information Technology Co.,Ltd.,Guangzhou 511400,China)

机构地区：[1]华南理工大学广州学院,广州510800 [2]广东经传多赢投资咨询有限公司,广州510800

出　　处：《计算机测量与控制》2019年第6期231-235,共5页Computer Measurement &Control

基　　金：华南理工大学广州学院教育教学改革项目

摘　　要：针对摄像头产生的海量视频信息,检索工作需要花费大量的人力、物力以及时间成本问题,分析发现传统检索的功能大多都基于文本关键词,对视频内容的覆盖率低且容易依赖于相关工作人员的主观性;提出如何应用传统的机器视觉技术以及深度学习技术去构建一个高效的视频检索系统;创新点在于从视频帧图像内容的角度去充分发掘其中的信息,其信息挖掘的过程无需人工干预,从而提高了信息利用率。In view of the huge amount of video information generated by the camera,the retrieval work needs a lot of manpower,material resources and time cost.The analysis shows that most of the traditional retrieval functions are based on text keywords,and the coverage of video content is low and easy to rely on the subjectivity of the relevant staff.This paper proposes how to use traditional machine vision technology and deep learning technology to build an efficient video retrieval system.The innovation lies in fully exploring the information from the perspective of video frame image content.The process of information mining does not need manual intervention,thus improving the utilization rate of information.

关 键 词：视频信息 视频检索 机器视觉 深度学习 信息挖掘 

分 类 号：TP391.3[自动化与计算机技术—计算机应用技术]