海空复杂背景下红外弱点目标检测新算法

New detection algorithm for dim IR point targets under complicated sea and sky background

为解决海空复杂背景下红外弱点目标的检测,提出了多量级多向梯度表决融合检测算法。算法依据目标红外辐射特征是像素灰度在水平和垂直方向上梯度变化,将弱点目标特性转化为对图像奇异性的分析。算法用多个量级的梯度步长对图像目标进行检测,并对检测的结果进行表决融合。实验结果表明,红外阈值系数选取2.0-2.4时,算法可对信杂比为1的点目标实现高于95%的检测概率及较低的虚警率。

In order to solve the detection problems of dim IR point targets under complicated sea and sky background, a detection algorithm integrating with multi-degree and multi-orientation gradient fusion is proposed. Based on the principle of ER radiation property of target, i.e., the gradient variations of pixel gray scale in horizontal and vertical directions, the algorithm handles the property of dim point target into analysis of image singularity and detects targets by means of multi-degree gradient step length. Then the detected results will be processed by voting fusion. Experimental results show that when IR threshold coefficient is 2.0-2.4, more than 95% of the detection probability and lower false-alarm probability for targets with signal-clutter-ratio of 1 can be obtained by the algorithm.