基于互信息量的视频关键帧提取方法  

Research on video key frame extraction method based on mutual information

作　　者：王志强[1] 樊景峰 WANG Zhiqiang;FAN Jingfeng(Department of Information Engineering,Jiyuan Vocational and Technical College,Jiyuan 459000,China;The Personnel Department,Henan Health Cadre Institute,Zhengzhou 450000,China)

机构地区：[1]济源职业技术学院信息工程系,河南济源459000 [2]河南卫生健康干部学院人事处,河南郑州450000

出　　处：《河南工程学院学报（自然科学版）》2021年第4期67-69,共3页Journal of Henan University of Engineering：Natural Science Edition

摘　　要：关键帧提取技术是实现视频数据有效存储与应用的重要手段,它能够快速检测出视频中运动目标的起始帧和结束帧。因此,结合监控视频的特点提出了一种基于互信息量的视频关键帧提取方法。以运动车辆的视频为检测对象,在MATLAB软件平台利用背景差分法对视频数据运动目标帧进行检测,同时对关键视频段进行关键帧提取。实验结果表明,背景差分法能够有效检测出视频文件的关键视频段,关键帧提取方法能够快速捕捉视频数据的关键帧,大大减少了监控视频的冗余数据,实现了较好的提取效果。The key frame extraction technology is an important way to realize the effective storage and application of video data.It can quickly check the start frame and end frame of the moving target in the video.Based on the characteristics of surveillance video,this paper proposes a key frame extraction method for surveillance video based on mutual information as a feature parameter.Taking the moving vehicle video as the detection object,under the MATLAB software platform,the background difference method is used to detect the moving target frame of the video data,and the key frame of the key video segment is extracted at the same time.The experimental results show that the background difference method can effectively detect the key video segments of the video file,and the key frame extraction method can quickly capture the key frames of the video data,greatly reduce the redundant data of the surveillance video,and achieve a better extraction effect.

关 键 词：监控视频 运动目标检测 MATLAB 关键帧 

分 类 号：G633.67[文化科学—教育学]