基于帧间相关测量的视频帧运动程度分类  

Frame Motion Classification Based on Inter-Frame Correlation Measurement

作　　者：岳宇辰 YUE Yuchen(Department of Armament and Control,Army Academy of Armored Forces,Beijing 100072,China)

机构地区：[1]陆军装甲兵学院兵器与控制系,北京100072

出　　处：《通信电源技术》2021年第7期104-106,共3页Telecom Power Technology

摘　　要：针对现有的逐帧测量-逐帧重建类视频压缩感知重建算法对视频信号帧间相关性利用效果不强的问题,利用视频信号中各视频帧中不同区域帧间相关性不同的特性,提出一种视频帧运动程度分类方法。该方法能在不产生额外计算复杂度的前提下,在重建端实现视频帧运动程度的分类。实验结果表明,所提出方法的分类准确率高,能达到应用要求。Aiming at the problem that the existing frame by frame measurement frame by frame reconstruction video compressed sensing reconstruction algorithms can not make good use of the inter frame correlation of video signals,this paper proposes a video frame motion degree classification method based on the different inter frame correlation characteristics of different regions in each video frame,This method can classify the motion degree of video frames at the reconstruction end without extra computational complexity.Experimental results show that the proposed method has high classification accuracy and can meet the application requirements.

关 键 词：视频压缩感知 帧间相关性 运动程度 

分 类 号：TN9[电子电信—信息与通信工程]