基于分形和模糊滤波的红外烟幕背景中人造目标的识别

Man - made Target Detection in Infra - smoke Background Based on Fractal and Vague Filter

文章分析了红外烟幕图像中背景与目标特征的差别,采用分形维教和分形拟合误差作为烟幕背景与人造 目标的区分特征,用模糊滤波的方法确定分割门限,实现了分形识别算法并对目标图像进行了处理,结果表明能够 较好地从烟幕背景中检测出人造目标。

This paper analyzes the difference between background and man - made target in the infrared image of smoke screen, adopts fractal dimension and fractal error as the feature to distinguish the targets from background, determines the dividing limits by using vague filter method and realizes the fractal - detecting algorithm. Target images are processed at the end of this paper. The result shows this algorithm can distinguish the target from smokescreen background perfectly.