【摘要】 在高速天文图像数据的并行处理时,传统的图像分割方法往往不能满足实时、多通道、同步分割的要求。提出一种基于流水线技术的动态数据流图像分割的方法,利用FPGA构建得一个片上系统进行了实现。通过设计与验证,表明该方法可以完成10路同步分割高速天文图像(600 MB/s)的预定目标,满足后续DSP阵列并行处理的要求。更多还原

【Abstract】 Parallel processing of high-speed astronomical image data,existing image segmentation methods often can not meet the needs of real-time,multi-channel,synchronous segmentation.A method based on pipelining,using FPGA to build a SOC is presented.Through design and verification shows that the method can achieve high-speed(600 MB/s) 10-channel clock synchronization astronomical image segmentation.The requirements of DSP parallel computing on the next level.更多还原