论文部分内容阅读
通用视频编码系统一般基于标准视频压缩算法, 比如 MPEG4 和 H.264。但这些标准算法包括如离散余弦变换和运动估计等高复杂度的计算,所以为了实现实时通信,编码系统通常采用以硬件为基础的实现方法。然而以硬件为基础的视频编码系统具有实施周期长、成本高、灵活性差等不足。文章介绍了一种基于低计算复杂度自适应块截短编码方案的数据驱动并行视频编码系统,实验结果验证了编码系统的有效性。
Common video coding systems are generally based on standard video compression algorithms, such as MPEG4 and H.264. However, these standard algorithms include computations of high complexity such as discrete cosine transform and motion estimation. Therefore, in order to realize real-time communication, the coding system generally adopts a hardware-based implementation method. However, the hardware-based video coding system has the disadvantages of long implementation period, high cost and poor flexibility. This paper introduces a data-driven parallel video coding system based on low-complexity adaptive block truncation coding scheme. The experimental results verify the effectiveness of the coding system.