基于双边滤波的弱小目标背景抑制

Dim and small target background suppression using bilateral filtering

为解决红外弱小目标检测技术中结构化背景抑制的难题,利用双边滤波集成了图像几何、光度和局部结构相似性等信息并以非迭代、局部操作的优点,提出了一种基于双边滤波的红外弱小目标背景抑制算法,并引入了局部梯度的统计特性来抑制背景细节、增强目标信息,从而达到更好抑制图像中的背景,突出目标图像,提高图像整体对比度、信噪比的目的。实验结果显示,与小波滤波算法比较,该算法对含有弱小目标的复杂背景从主观视觉和数值指标都具有良好抑制效果。

Structured background suppression is difficult for dim and small targets detection, bilateral filtering could get information of image geometric, photometric and local structure similarites, and is non-iterative, local and simple, a background suppression algorithm based on bilateral filtering wa presented to solve the problem, and local gradient statistics was introduced to suppress background details and enhance target information for improving entire image contrast and signal to noise ratio （SNR）. When compared with wavelet filtering algorithm through subject inspection and value index, several groups of experimental results demonstrate that the presented algorithm can suppress complicated background in the dim and small target image effectively.