摘要
针对导弹末制导红外图像处理实时性要求,分析了红外图像并行实时处理算法及其集群计算机的实现,建立了适应于实时处理的BSP改进模型和集群并行处理软件系统,并给出了红外图像并行处理算法的实现方法。研究了应用提升小波实现图像并行处理算法及实现,进而分析了算法性能,推导出了加速比模型。实验验证了其有效性。
Considering the real-time requirement of processing infrared images on missile flight in end-game, this paper makes an analysis on parallel algorithms for the real-time processing of infrared images and on the realization of cluster computers. The BSP algorithm model for real-time processing and the cluster software system for parallel processing have been set up, with the suggested means of realization of parallel algorithms for processing infrared images. Meanwhile, it also makes a research on the parallel algorithms by application of Lifting Wavelet Transform as well as .their realization, analyzing hence the performance of the Lifting Scheme with derivation of the speedup-ratio model. In addition, the model＇s validity has been verified by experiments.
出处
《红外技术》
CSCD
北大核心
2009年第11期654-658,共5页
Infrared Technology
基金
国家自然科学基金资助项目(编号:60575013)
航空支撑科技基金资助项目(编号:5C53005)
关键词
BSP模型
并行计算
集群计算机
小波变换
提升小波
BSPmodel
parallel computing
cluster-computer
wavelet transforrn
lifting wavelet
