基于上下文的自适应二进制算术编码——一种适用于视频压缩的新型熵编码  

作　　者：董洁[1] 楼剑[1] 陆亮[1] 虞露[1] 

机构地区：[1]浙江大学信息与通信工程研究所,浙江杭州310027

出　　处：《电视技术》2003年第8期9-11,共3页Video Engineering

摘　　要：CABAC是一种适用于视频压缩的高效熵编码技术。它采用上下文建模来降低符号间的冗余度;采用递归的二进制算术编码使输出码字的信息量逼近符号的熵率,并有利于实时视频编码;采用自适应机制对视频流进行实时统计特性的跟踪。实验表明,CABAC与UVLC相比,能非常有效地节省码率,但是其复杂度要高一些。Context-based Adaptive Binary Arithmetic Coding(CA BA C)is a highly efficient scheme of entropy coding for video compression.Conte xt Modeling is utilized to reduce the redundancy between symbols.Recursive Bina ry Arithmetic Coding makes symbols to be coded almost at their entropy rate and is also beneficial to real-time video coding.The adapta-tion is also employe d to keep track of the real-time statistics of different video streams.Based on the results of the experi-ment,it can be concluded that CABAC effectively reduces the bit rate compared with Universal Variable Length Coding(U-VLC)at the expense of higher complexity.

关 键 词：算术编码 熵编码 上下文建模 自适应 视频压缩 二进制算术编码 

分 类 号：TN919.81[电子电信—通信与信息系统]