改进alpha-matting算法及其在军事红外目标提取中的应用

An improved alpha-matting algorithm and its application in military targets

针对红外图像的成像特点,为了更加精细准确的获得红外目标,提出基于通道抠图(alpha-matting)的红外目标提取方法.利用目标监测的连续帧变化特性,将相邻帧进行差分运算,从而获得目标前景(即目标)、背景、不确定区域;采用二次方贝塞尔曲线(Quadratic BézierCurve)拟合法建立动态调整曲线方程,计算出精确的前景透明度值(也即通道alpha值),实现alpha值的自动选择。仿真结果表明,改进算法能有效的提取红外目标(尤其红外小目标),准确率高,实时性好,具有很好的应用前景.

A new infrared target extracting method by alpha-matting is proposed,which considers the infrared image characteristics,so as to obtain the more subtle and accurate infrared target.Utilizing varying characteristics of successive frames of the target monitoring,and by difference computing of adjacent frames,the target prospect（i.e.target）,background,area of uncertainty can be obtained.Adopting Quadratic Bézier Curve fitting method to establish the dynamic adjustment curve equation,the accurate transparency value of prospect（i.e.alpha value） was calculated,so the automatic selection of alpha value can be realized.Simulation results show that the improved algorithm has widely application prospects by extracting infrared targets（especially the small infrared target） effectively,high accuracy and good real-time performance.