吉林大学学报(工学版) ›› 2025, Vol. 55 ›› Issue (2): 741-747.doi: 10.13229/j.cnki.jdxbgxb.20240037

• 计算机科学与技术 • 上一篇    

海量数字媒体视频无损转码重压缩的轻量化检测算法

董华松(),连远锋   

  1. 中国石油大学（北京） 人工智能学院，北京 102249
  • 收稿日期:2024-01-11 出版日期:2025-02-01 发布日期:2025-04-16
  • 作者简介:董华松（1977-），女，讲师，博士.研究方向：嵌入式系统，数字媒体技术，机器人与机器视觉.E-mail：ogreyelisha@sina.com
  • 基金资助:
    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)

Lightweight detection algorithm for lossless transcoding and heavy compression of massive digital media videos

Hua-song DONG(),Yuan-feng LIAN   

  1. College of Artificial Intelligence，China University of Petroleum （Beijing），Beijing 102249，China
  • Received:2024-01-11 Online:2025-02-01 Published:2025-04-16

RICH HTML

 2   

PDF (PC)

47

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5 000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。

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

Abstract:

To timely obtain video quality， a lightweight detection algorithm for lossless transcoding and heavy compression of massive digital media videos is proposed. This method divides video encoded frames into several encoding tree blocks based on high-performance video encoding， and optimizes video rate distortion to ensure video quality during the partitioning process while minimizing computational and storage costs， achieving a certain degree of lightweighting； Based on this， pixel values， color space， and motion vectors are extracted from each image frame in the video， and the extracted results are compared and analyzed with the initial video pixel values， color features， and motion vectors to determine whether the quality of the re compressed video is damaged， achieving lightweight detection of the re compressed video. 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.

Key words: digital media video, lossless transcoding and recompression, lightweight testing, video frame division, color feature extraction

中图分类号: 

  • TP306

图1

压缩视频中某一视频帧的编码树单元划分图"

图2

图像帧"

图3

编码树单元对应四叉树"

图4

压缩视频图像像素分布测试结果"

图5

不同方法视频图像帧全局颜色分量测试结果"

表1

不同方法的压缩视频实际检测效果测试"

视频数量/个视频检测误报数量检测结果/个
本文方法文献［4］方法文献［5］方法
1 000000
2 000001
3 000123
4 000156
5 0003810
1 马彦博, 李琳, 陈缘, 等. 基于时空融合的多帧压缩视频增强方法[J]. 图学学报, 2022, 43(4): 651-658.
Ma Yan-bo, Li Lin, Chen Yuan, et al. Multi-frame compressed video enhancement based on spatio-temporal fusion[J]. Journal of Graphics, 2022, 43(4): 651-658
2 肖尚武, 胡瑞敏, 肖晶. NB-IoT环境下基于混合分辨率人脸监控视频压缩方法[J]. 计算机应用与软件, 2022, 39(2): 150-156.
Xiao Shang-wu, Hu Rui-min, Xiao Jing. Face-oriented surveillance video compression method based on hybrid resolution in nb-iot environment[J]. Computer Applications and Software,2022,39(2):150-156.
3 王金伟, 胡冰涛, 张家伟, 等. 基于解压缩模块的JPEG同步重压缩检测[J].电子学报, 2023, 51(4):850-859.
Wang Jin-wei, Hu Bing-tao, Zhang Jia-wei, et al. Jpeg synchronous double compression detection based on decompression module[J]. Acta Electronica Sinica, 2023,51(4): 850-859.
4 孙磊, 张洪蒙, 毛秀青, 等.基于超分辨率重建的强压缩深度伪造视频检测[J].电子与信息学报, 2021,43(10): 2967-2975.
Sun Lei, Zhang Hong-meng, Mao Xiu-qing, et al. Super-resolution reconstruction detection method for deepfake hard compressed videos[J]. Journal of Electronics & Information Technology, 2021, 43(10): 2967-2975.
5 Paulraj R J, Vimala M, Govindamoorthi P. An optimal weighted HEVC coding for video compression[J]. Multimedia Tools and Applications, 2021, 80(17): 25389-25409.
6 Naveen C V R. Blind quality scalable video compression algorithm for low bit-rate coding[J]. Multimedia Tools and Applications, 2022, 81(23): 33715-33730.
7 惠超, 蒋林, 朱筠, 等. HEVC中分像素插值算法的动态可重构实现[J]. 计算机工程与设计, 2022, 43(3): 764-770.
Hui Chao, Jiang Lin, Zhu Yun, et al. Dynamic reconfigurable implementation of sub-pixel interpolation algorithm in HEVC[J]. Computer Engineering and Design,2022,43(3):764-770.
8 宋宇波, 马文豪, 胡爱群, 等. 一种基于像素值偏移编解码技术的屏摄隐通道研究[J]. 信息网络安全, 2021, 21(4): 31-38.
Song Yu-bo, Ma Wen-hao, Hu Ai-qun, et al. A covert channel communication method based on pixel offset encoding and decoding technique[J]. Netinfo Security, 2021,21 (4): 31-38.
9 张霞, 向军, 张宁, 等. 采用改进的小波和颜色矩的色纺面料图像检索[J].丝绸, 2021, 58(12): 34-39.
Zhang Xia, Xiang Jun, Zhang Ning, et al. Image retrieval of colored spun fabrics using modified wavelet transform method and color moments[J]. Journal of Silk, 2021,58(12): 34-39.
10 张梓婷, 韩金玉, 张东辉, 等. 基于颜色矩的土豆、玉米、苹果叶片病害异常检测[J].浙江农业学报,2022,34(10): 2230-2239.
Zhang Zi-ting, Han Jin-yu, Zhang Dong-hui, et al. Anomaly detection of potato,maize and apple leaf diseases based on color moments[J]. Zhejiang Agricultural journal, 2022, 34(10): 2230-2239.
11 叶裴雷, 张大斌. 高速运动目标特征关联检测模型仿真[J]. 计算机仿真,2023,40(4):208-212.
Ye Pei-lei, Zhang Da-bin. Simulation of feature association detection model for high-speed moving targets[J]. Computer Simulation, 2023, 40(4): 208-212.
[1] 欧阳丹彤,孙睿,田新亮,张立明,刘萍萍. 基于部分最大可满足性问题的动态系统中最小故障检测隔离集求解方法[J]. 吉林大学学报(工学版), 2023, 53(4): 1163-1173.
[2] 欧阳丹彤,孙睿,田新亮,高博涵. 基于集合阻塞的不确定系统中传感器选择方法[J]. 吉林大学学报(工学版), 2023, 53(2): 547-554.
[3] 黄永平, 常鹏飞, 郭凯, 金玉善. 基于事件注入机制的软件调试方法与实现[J]. 吉林大学学报(工学版), 2012, 42(增刊1): 373-376.
[4] 赵相福，欧阳丹彤 . 基于模型的诊断中产生所有极小冲突集的新方法[J]. 吉林大学学报(工学版), 2007, 37(02): 413-0418.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 《吉林大学学报(工学版)》编辑部
地址：长春市人民大街5988号　电话：+86-431-85095297　传真：+86-431-85094074　E-mail: xbgxb@jlu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发