Multimedia applications, such as video decoding, always take heavy computational complexity and cause huge energy consumption. To save energy, existing hardware platforms tend to adjust their resources according to the actual decoding computational demand. The effectiveness of such methods depends on the prediction accuracy of decoding complexity. Based on the linear relationship between frame length and the decoding complexity of each frame, this paper proposes a linear modeling and online predicting method which utilize State-Variable Analysis (SVA) for video decoding complexity prediction. The state equation of decoding system is established as follows. The semantic meanings of state variables which directly affect the linear relationship between frame length and decoding complexity are exploited through analysis on decoding procedure. Then combined with the semantic correlation between neighboring frames in compressed streams, the state equation is established as a piecewise function which can reflect the variation of video content. Considering the different characteristics of state trajectory between intra-frame and inter-frame, we provide online decoding complexity predicting methods for them respectively. The mean values of state variables for intra-frame are obtained through offline statistical analysis and then utilized directly during online process to predict decoding complexity. For inter-frame, the values of state variables are calculated using state equation in the online process and then the decoding complexity can be predicted. The proposed method is implemented on both software-based simulation platform and DSP-based hardware platform, the decoding complexity of compressed streams which use either H. 264 or MPEG-4 coding standards is predicted. The experimental results show the proposed method can give fairly accurate prediction for decoding complexity. The average prediction errors are less than 7%. Moreover, since the state equation can update the state variable at a very low cost, the runtime overhead of the method is very small. It is very useful for those resource-limited mobile devices.%视频解码是一类最典型的多媒体应用,其计算量大、耗能高.现代多媒体计算平台可利用视频解码计算复杂度固有的动态变化特征来自适应地调整所需计算资源,从而节省能耗,其前提是对视频解码计算复杂度进行准确估计.作者基于解码计算复杂度与帧长之间的线性关系,提出了一种利用状态变量法对解码计算复杂度进行理论建模和在线估计的方法.与传统的直接对帧长和计算复杂度之间的输入-输出依赖关系进行建模所不同,这里将视频解码系统表征为由视频内容特征的状态变化所驱动的系统.首先从语义层面对解码器各模块的解码复杂度进行分析,并导出各模块计算复杂度与语义参数间的依赖关系模型,总解码复杂度为各子模块的复杂度之和.经过化简得到解码计算复杂度与帧长之间的线性模型,其中模型系数为上述语义参数的函数,表征了视频内容特征的状态变化,被定义为状态变量.再结合压缩视频流中相邻帧语义参数之间的相关性,将系统状态方程定义为反映视频内容变化程度的分段线性函数.根据Ⅰ帧和P帧状态轨迹特性及其在压缩码流中位置属性的不同,分别进行计算复杂度在线估计:对于I帧,采用统计分析方法获得其状态变量的均值并进行在线估计；而对P帧,则是在运行过程中利用状态方程对状态变量进行实时更新和计算复杂度估计.在基于SimpleScalar的软件仿真平台和基于DSP的嵌入式硬件平台上分别对H.264、MPEG-4压缩码流的解码计算复杂度进行在线估计,实验结果表明:对解码计算复杂度的平均估计误差在7％以内,预测精度非常高,而且状态方程更新过程简单,在线运行复杂度低,特别适用于嵌入式移动设备.
展开▼
