摘要
针对单帧红外小目标具有能量值高于背景和噪声的特点,提出了一种基于局部特征的单帧红外小目标检测算法。该方法首先分析了单帧红外图像各部分的高低频关系,利用单帧红外小目标与背景在频率上的不同,采用二阶巴特沃斯低通滤波器滤除背景干扰;然后设定能量与灰度阈值进行自适应阈值分割,保留疑似目标点;最后通过改进的拉普拉斯算子突出红外小目标轮廓。经过红外图像仿真实验验证,该方法能够在复杂空域快速而准确地检测出单帧红外小目标。
Because energy value of single frame infrared small target is higher than that of the background and noise,a detection algorithm of single frame infrared small target based on local features is proposed. The frequency relationship in the single frame infrared image was analyzed firstly. According to frequency difference of the infrared small target and the background,background interference was filtered out by a second-order Butterworth low-pass filter.Then adaptive threshold segmentation was done by setting the energy and the gray,and the suspected targets were kept. Finally,the infrared small target contour was highlighted by the improved Laplacian operator. Through infrared image simulation experiment,the method can detect the single frame infrared small target in the complex airspace quickly and accurately.
出处
《激光与红外》
CAS
CSCD
北大核心
2016年第3期368-371,共4页
Laser & Infrared
关键词
单帧
红外小目标
频率
阈值
single frame
infrared small target
frequency
threshold
