红外海面小目标检测的并行实现技术  

Parallel Implementation for Detecting Small Targets on Infrared Sea Surface

作　　者：曹治国[1] 左峥嵘[1] 桑农[1] 张天序[1] 

机构地区：[1]华中科技大学图像识别与人工智能研究所图像信息处理与智能控制教育部重点实验室

出　　处：《华中科技大学学报（自然科学版）》2001年第12期52-54,共3页Journal of Huazhong University of Science and Technology(Natural Science Edition)

基　　金：国家自然科学基金资助项目 ( 69875 0 0 5 )

摘　　要：提出了红外海面小目标检测的并行实现方案 ,该方案采用了基于多级滤波的小目标检测方法 ,能在自行设计的多总线多DSP实时图像处理系统上运行 .详细讨论了该方案的优化问题 ,以获得成本最优、并行效率最高的系统并行处理方式 .实验结果表明 ,算法是可行的 。In this paper, parallel implementation for detecting small targets on infrared sea surface is provided, which a small detection algorithm is adopted based on multi level filters and real time image processing system is operated based on multiple bus and multi DSPs designed Optimization of this scheme is carefully discussed to get an optimal parallel implementation in cost and parallel efficiency. The experiment results show the parallel algorithm is feasible and the analysis about the optimization is correct.

关 键 词：图像处理 小目标检测 并行处理 DSP 红外成像 多级滤波 图像切割 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]