基于异构加速的动目标检测算法的实现方法  

Implementation Method of Moving Target Detection Algorithm Based on Heterogeneous Acceleration

作　　者：陈莹莹 胡善清[1,2] 李兴明 王策[1,2] CHEN Yingying;HU Shanqing;LI Xingming;WANG Ce(Radar Research Lab,School of Information and Electronics,Beijing Institute of Technology,Beijing 100081,China;Beijing Key Laboratory of Embedded Real-time Information Processing Technology,Beijing Institute of Technology,Beijing 100081,China;Beijing Racobit Electronic Information Technology Co.Ltd,Beijing 100081,China)

机构地区：[1]北京理工大学信息与电子学院雷达技术研究所,北京100081 [2]嵌入式实时信息处理技术北京市重点实验室(北京理工大学),北京100081 [3]北京理工雷科电子信息技术有限公司,北京100081

出　　处：《信号处理》2022年第2期410-416,共7页Journal of Signal Processing

基　　金：国家自然科学基金(31727901,91738302)。

摘　　要：大数据的不断深化应用和信号处理算法的不断迭代升级,推进了雷达目标检测的不断革新,实现对动目标的检测的同时,实时性的保证成了一个问题。目前研究对动目标的检测多在理论和仿真阶段,针对提高实时性的加速处理方法研究较少。本文针对当前普遍的动目标检测算法流程,设计CPU(Central Processing Unit,中央处理器)+GPU(Graphics Processing Unit,图形处理器)的异构加速,利用GPU的并行处理能力,通过对算法进行并行加速和流水加速处理来替代传统的串行处理方式,实现了高速实时目标检测信号处理,并通过仿真数据验证分析进而证明准确性和实时性。The continuous expansion of big data applications and the continuous upgrade of signal processing algorithms have promoted the continuous innovation of radar target detection.For detecting of moving targets,real-time guarantees have become a problem.At present,the research on the detection of moving targets is mostly in the theory and simulation stage,and there are few studies on accelerated processing methods to improve real-time performance.Based on current moving target detection algorithm flow.This paper designs the heterogeneous acceleration of CPU(Central Processing Unit)+GPU(Graphics Processing Unit).In this paper,the algorithm performs parallel acceleration and pipeline acceleration processing to replace the traditional serial processing method.And then this paper verifies the accuracy and real-time performance through simulation data verification and analysis.

关 键 词：异构 动目标 实时检测 CPU+GPU 

分 类 号：TN957.51[电子电信—信号与信息处理]