基于量化步长的视频编码能量率失真模型

Power-rate-distortion Video Coding Model Based on Quantization Step Size

针对移动手语视频通信中存在的功率和码率约束问题,提出一种能量感知的视频编码能量率失真(P-R-D)模型。在H.264视频编码软件平台JM8.6上进行模型参数选择,确定以量化步长作为模型参数。根据移动设备的电池剩余能量划分3个能量状态,在不同状态下分别建立相应的功耗、码率及失真模型。实验结果表明,对于典型的手语视频,P-R-D模型能够准确反映视频编码功耗、码率和质量之间的关系,其中功耗模型和码率模型精确度较高,最大预测误差仅为-1.1795%和-7.9268%。

For power and rate constraints problem that exists in mobile sign language video communication,this paper proposes a Power-rate-distortion（ P-R-D） model. It chooses the quantization step size as the model parameter by the experiments on the software platform JM8. 6 of H. 264 video coding, then defines three energy states according to the remaining amount of battery energy of mobile devices. With quantization step size as the model parameter,it establishes the power consumption model, coding rate model and distortion model under the three different energy levels. Experimental results show that the established P-R-D model for sign language video coding can accurately reflect the relationship among power consumption. The maximum prediction error of power consumption model and coding rate model respectively are -1. 179 5% and -7. 926 8% .