一种新的弱小目标检测方法

A New Method of Small Dim Target Detection

基于对红外图像中目标和背景特性的分析,提出了一种新的基于标记信息和梯度信息相融合的弱小目标检测方法。在红外图像空间,根据目标的特性,利用双重窗进行可能目标的搜索,并进行标记;同时并行的对原始图像进行梯度计算。对标记信息和梯度信息进行融合,进行目标的初次确定。再利用自适应门限对融合后的图像进行目标分割。实验结果证明了该方法能有效的检测出弱小目标。

According to analysis of targets and background in IR images, a method of small dim targets detection based on fusion of the mark information and gradient information was proposed. Have analyzed targets＇ characteristic in IR image space, dual-window was used to search and mark possible targets. The gradient of originality IR image was calculated simultaneously. The information of the mark and gradient was fused. Adaptive gate was used to get targets by segment the fused image. The experimental results show that the method presented was valid.