圆形结构形态学滤波器优化设计及应用  

The Optimized Design and Application of Circular Morphological Filter

作　　者：车宏[1] 孙隆和[1] 

机构地区：[1]西北工业大学电子信息学院,西安710072

出　　处：《南京航空航天大学学报》2011年第4期486-490,共5页Journal of Nanjing University of Aeronautics & Astronautics

基　　金：航空科学基金(2007157007)资助项目

摘　　要：形态学滤波是红外弱小点目标检测研究中一个有效方法,其滤波器结构将直接影响检测性能。基于目标在实测红外图像上所呈现的凸包结构特点,首先设计了圆形形态学滤波器结构。在此基础上,引入神经网络进行圆形形态学滤波器结构元素优化设计。实测数据的处理结果表明:针对低信噪比图像(SNR≈2),在虚警概率小于等于1%情况下,优化的圆形形态学滤波器算子对的复杂红外弱小目标图像检测概率大于等于98%,优于固定结构元素的形态学滤波器和方形结构的优化形态学滤波器。With the optimized structure,morphological filter is effective to detect moving spot target in infrared image sequences.Based on the real convex figure,the circular structure of morphological filter is designed.The neural network is introduced to optimize the filter element.The adaptive detection threshold is built based on the statistical characters.Experimental results from real data show that the detection probability of images（SNR≈2） can reach more than 98% with 1% false alarm by the optimized circular morphological filter,which is better than that by fixed element morphological filter and square morphological filter.

关 键 词：形态学滤波器 圆形结构元素 神经网络 

分 类 号：TN215[电子电信—物理电子学]