移动AR+VR支持下跨媒体视频关键帧还原仿真  

Simulation of Cross-media Video Key Frame Restoration under the Support of Mobile AR+VR

作　　者：杨盼盼 马凌飞 平阳 索雅丽 YANG Panpan;MA Lingfei;PING Yang;SUO Yali(Institute of Data Science and Agricultural Economy,Beijing Academy of Agricultural and Forestry Sciences,Beijing 100097,China)

机构地区：[1]北京市农林科学院,数据科学与农业经济研究所,北京100097

出　　处：《微型电脑应用》2024年第3期32-36,共5页Microcomputer Applications

基　　金：北京市农林科学院青年基金(QNJJ202213)。

摘　　要：为了准确还原视频信息,针对跨媒体视频帧间保真度以及压缩比较低的问题,设计一个移动AR+VR支持下的跨媒体视频关键帧还原方法。采用SIFT方法提取跨媒体视频关键帧特征点,反复提取关键帧,构成一个关键帧集合,采用AR+VR技术按照属性与特征建立全景画面AR预测模型,校正全景图,建立匹配矩阵,匹配VR视频帧间序列,实现移动AR+VR支持下跨媒体视频关键帧还原。实验结果表明,应用该方法后,准确性、保真度以及压缩比较高,具有较好的关键帧还原效果。In order to restore video information accurately,aimed at the problems of low inter frame fidelity and compression of cross media video,a cross media video key frame restoration method supported by mobile AR+VR is designed.The feature points of cross media video key frames are extracted by the SIFT method,and the key frames are extracted repeatedly to form a key frame set.The AR+VR technology is used to establish the panorama AR prediction model according to the attributes and features,correct the panorama,establish the matching matrix,match the VR video inter frame sequence,and realize the restoration of cross media video key frames supported by mobile AR+VR.Experimental results show that this method has high accuracy,fidelity and compression ratio,and has good key frame restoration effect.

关 键 词：跨媒体视频 关键帧还原 校正特征点 匹配矩阵 

分 类 号：TN911[电子电信—通信与信息系统]