基于流水线的增强型植被指数快速提取算法

Fast extraction algorithm of enhanced vegetation index based on pipeline

针对传统的并行方法难以对增强型植被指数(enhanced vegetation index,EVI)提取链进行加速的问题,结合EVI提取算法的特点,依靠流水线在遥感影像多级连续处理方面的优势,提出一种基于流水线模型的EVI快速提取算法。为了解决相邻处理阶段吞吐率的差异问题,在流水线相邻节点间加入双缓冲队列来存储节点处理的中间结果,进一步提高EVI提取算法各步骤并行度。实验结果表明,提出的EVI快速提取算法的提取效率要高于传统的EVI多线程提取算法。

According to the question that difficult to accelerate the EVI extraction chain for traditional parallelism methods,combined with the characteristics of EVI extraction algorithm,depended on the advantages of pipeline in multi-level continuous processing of remote sensing images,this paper proposed an EVI fast extraction algorithm based on pipeline model.In order to solve the problem of the difference in throughput between adjacent processing stages,it added a double buffer queue between adjacent nodes of the pipeline to store the intermediate result of the node processing,and further improved the parallelism of the steps of EVI extraction algorithm.Experimental results show,the EVI fast extraction algorithm is more efficient than the traditional EVI multi-thread extraction algorithm.