基于MPI和OpenCV遥感图像匹配的并行实现

Parallel implementation of remote sensing image matching based on MPI and OpenCV

灰度匹配是遥感图像处理中一项重要技术,匹配方法虽然精度高,但计算量大,时间长。针对这一问题,介绍了遥感图像灰度匹配的并行策略,基于消息传递接口(MPI)和开源计算机视觉库(OpenCV)实现了归一化积相关灰度匹配并行算法,并依此算法来验证遥感灰度匹配的并行性能。实验结果表明,该算法能获得良好的加速比且并行效率大于1,说明基于该算法的遥感图像匹配可以显著提高遥感图像处理的效率。

Gray matching is an important technology in remote sensing image processing. Although this method has high precision, it requires a long computation time because of computation-intensiveness. To solve this problem, this paper introduced the parallel strategy of image gray matching. It implemented the normalized product correlation algorithm based on MPI and OpenCV to validate the performance of parallism . The experimental results show that it obtains good speedup and parallel efficiency of greater than l, indicating that the proposed method can significantly improve the efficiency of remote sensing image processing.