基于Cortex嵌入式多处理器系统的图像中值滤波算法并行化的研究

嵌入式系统在图像处理、空间计算等领域越来越广泛，如何在功耗、成本和计算能力三个主要方面取得平衡，利用多核和多处理器系统以并行计算方式提高嵌入式系统计算能力是一种有效的解决方案.讨论了基于Cortex嵌入式多处理器系统的基本结构，并在该系统上进行图像中值滤波算法的并行化研究.实验结果分析表明，在该嵌入式多处理器平台上配合并行算法能够成倍提高图像中值滤波的运行性能.

Research on Parallel Image Median Filtering Algorithm for Multi Processor Embedded System Based on Cortex

Embedded system has become more and more popular in image processing, spatial computing and other fields. In order to achieve a balance in three major aspects of power consumption, cost and computing power, it is an effective solution to improve the computing ability of embedded system, using the multi-core and multi processor system based on parallel computing method. This paper discusses the basic structure of embedded multi processor system based on Cortex, and has a research on parallel image median filtering algorithm on this system. Experimental results show that the parallel algorithm can improve the performance of image median filtering exponentially on the embedded multi processor platform.