摘要
针对多视觉任务中传输成本高、解码端计算压力大的问题,提出一种自适应可伸缩视频编码(adaptive scalable video coding,ASVC)传输框架,将视频分为语义层和背景层,分别传输语义和背景信息。此外,提出一种自适应压缩算法,构建了C4.5决策树模型分析网络环境对视频进行压缩的决策判定,并对帧序列进行光流分析,在保留变化显著的帧基础上引入插值机制保持图像的平滑性。仿真结果表明,ASVC方法在不同码率环境下表现更高的识别精准率,视频质量和传输效率的显著提升。
To address high transmission costs and the computational burden of multi-visual tasks at the decoding end,an adaptive scalable video coding(ASVC)transmission framework is proposed.The framework divides video into semantic and background layers,transmitting these separately.Additionally,an adaptive compression algorithm is proposed,utilizing a C4.5 decision tree model to analyze the network environment and make compression decisions.Optical flow analysis is employed to retain frames with significant changes,while an interpolation mechanism ensures image smoothness.Simulation results demonstrate that the ASVC method achieves higher recognition accuracy,improved video quality,and transmission efficiency across various bitrate environments.
作者
李晓辉
杨雯
吕思婷
毛亮
LI Xiaohui;YANG Wen;LYU Siting;MAO Liang(Guangzhou Institute of Technology,Xidian University,Guangzhou 510555,China;School of Teleommunications Engineering,Xidian University,Xi’an 710071,China;Guangzhou Tozed Kangwei Intelligent Technology Co.,Ltd.,Guangzhou 511458,China)
出处
《系统工程与电子技术》
北大核心
2025年第8期2737-2743,共7页
Systems Engineering and Electronics
基金
国家自然科学基金(NSFC 62376204)资助课题。
关键词
自适应压缩算法
C4.5决策树
光流检测
多视觉任务
adaptive compression algorithm
C4.5 decision tree
optical flow detection
multi-visual task
