摘要
为及时获取视频质量,提出海量数字媒体视频无损转码重压缩的轻量化检测算法。该方法根据高性能视频编码将视频编码帧划分成若干编码树块,并在通过视频率失真优化保障划分过程中的视频质量的同时,尽量减少计算和存储的开销,实现一定程度上的轻量化;再以此为基础,对视频中各图像帧开展像素值、色彩空间以及运动矢量的提取,并将提取结果与初始视频像素值、色彩特征以及运动矢量展开比较分析,从而确定重压缩视频质量是否受到损伤,实现重压缩视频的轻量化检测。实验结果表明:利用本文方法开展压缩视频质量检测时,压缩视频图像的颜色分量提取结果与实际压缩视频图像颜色分量相一致,且当视频数量达到5000个时,视频检测误报数量检测结果为3个,进一步说明本文方法的检测性能高、效果好。
To timely obtain video quality,a lightweight detection algorithm for lossless transcoding andheavy compression of massive digital media videos is proposed.This method divides video encoded framesinto several encoding tree blocks based on high-performance video encoding,and optimizes video ratedistortion to ensure video quality during the partitioning process while minimizing computational andstorage costs,achieving a certain degree of lightweighting;Based on this,pixel values,color space,andmotion vectors are extracted from each image frame in the video,and the extracted results are comparedand analyzed with the initial video pixel values,color features,and motion vectors to determine whetherthe quality of the re compressed video is damaged,achieving lightweight detection of the re compressedvideo.The experimental results show that when using the proposed method for compressed video quality detection,the color component extraction results of the compressed video image are consistent with the actual color component of the compressed video image.Moreover,when the number of videos reaches 5000,the detection result of the number of false positives in video detection is 3,further demonstrating the high detection performance and good effect of the proposed method.
作者
董华松
连远锋
DONG Hua-song;LIAN Yuan-feng(College of Artificial Intelligence,China University of Petroleum(Beijing),Beijing 102249,China)
出处
《吉林大学学报(工学版)》
北大核心
2025年第2期741-747,共7页
Journal of Jilin University:Engineering and Technology Edition
基金
国家自然科学基金项目(61972353)
中国石油天然气集团有限公司-中国石油大学(北京)战略合作科技专项项目(ZLZX2020-05)。
关键词
数字媒体视频
无损转码重压缩
轻量化检测
视频帧划分
色彩特征提取
digital media video
lossless transcoding and recompression
lightweight testing
video frame division
color feature extraction
