摘要
传统的运动教学视频压缩算法压缩帧数少,信噪比低。为了解决上述问题,提出基于人工智能技术的运动教学视频压缩算法,利用多线性子空间KL变换技术进行运动教学视频编码,引用人工智能技术中的钻石搜索法构建视频压缩算法,分析视频图像运动中矢量的基本规律来检测算法的有效性,确定多个子空间的数据,将视频帧数进行分辩,分辨出新的变量进行XL变换处理来完成教学视频编码,编码后采用钻石搜索法的两种模式进行互补,从而确定出最小误差点,利用SAD算法算出最佳匹配矢量,完成运动教学视频的压缩。与传统算法进行实验对比,结果表明,基于人工智能技术的运动教学视频压缩算法压缩帧数多、信噪比高、清晰度高,具有很好的压缩效果。
As the traditional sports teaching video compression algorithm has fewer compressed frames and lower signal⁃to⁃noise ratio,a new sports teaching video compression algorithm based on artificial intelligence technology is proposed.The multi⁃line subspace KL transform technology is used for sports teaching video coding.The diamond search method in artificial intelligence technology is used to construct video compression algorithm.The basic law of vector in video image motion is analyzed.In order to check the validity of the algorithm,the data of several subspaces is determined,and then the number of video frames is discriminated to get new variables and perform XL transform processing,so as to complete the teaching video encoding.The two modes of diamond search method are adopted for complementary after encoding,so as to determine the minimum error point.The SAD algorithm is used to calculate the best matching vector to complete the compression of the sports teaching video.The results of comparison experiment show that,in comparison with the traditional algorithm,the sports teaching video compression algorithm based on artificial intelligence technology can get many frames compressed,and has high signal⁃to⁃noise ratio,high definition and good compression effect.
作者
姜龙
骆勇
JIANG Long;LUO Yong(Jiangsu Normal University,Xuzhou 221116,China;Lianyungang Technical College,Lianyungang 222000,China)
出处
《现代电子技术》
北大核心
2020年第21期55-58,63,共5页
Modern Electronics Technique
基金
江苏省教育科学“十三五”规划2018年度重点资助课题(B-a/2018/03/28)。
关键词
人工智能技术
运动教学视频
视频压缩
压缩算法
视频编码
最小误差点确定
artificial intelligence technology
sports teaching video
video compression
compression algorithm
video coding
minimum error point determination
