基于非下采样方向滤波器组的红外复杂地面背景抑制

Nonsubsampled Directional Filter Banks for Infrared Complex Ground Background Suppression

针对弱小目标检测技术的难点,根据红外图像中目标和背景杂波的特性,提出了一种基于非下采样方向滤波器组的红外地面背景抑制方法。首先,采用非下采样方向滤波器组对图像进行多方向分解,提取图像方向细节特征,然后,根据目标和背景杂波信号的差异,通过将基于傅里叶变换域的频域调整策略应在于分解后各方向子带,从而将红外图像中弱小目标和背景杂波分离,达到抑制背景的目的,最后采用经典的自适应阈值分割技术得到目标点,最终实现对目标的检测。实验结果显示,与最大中值滤波和局部去均值滤波方法相比较,该方法能有效地检测出信杂比较低的目标。

In view of the detection features for weak and small targets, a method based on nonsubsampled directional filter banks is proposed for infrared complex ground background suppression. Firstly, directional filter banks are adapted to decompose the input infrared image, which extracts directional detail features of the image. Then, according to the difference between the target and background clutter signal, and frequency-domain adjustment is introduced to suppress the background details and enhance target information. Finally, the target image is obtained by using adaptive thresholding method. Experimental results demonstrate that, compared with classical infrared image segmentation methods, such as Max-Median （Mined） and local means remove （LMR） methods, the presented method can detect the infrared targets with low signal to clutter ratio effectively.