基于双层局部对比度的红外弱小目标检测方法

Infrared Small Target Detection Based on Double-layer Local Contrast Measure

针对传统基于人类视觉系统的检测方法在复杂背景下容易造成检测虚警的问题,提出一种基于双层局部对比度的红外弱小目标检测方法.首先,通过双层对角灰度差对比度分析机制,充分利用小目标局部对比度的先验信息,提高目标对比度的同时抑制背景杂波及噪声;之后,利用自适应阈值分割法获取待检测的真实目标.实验结果表明,与主流基于人类视觉系统的检测方法相比,所提方法的背景抑制因子平均提高9.3倍以上,信杂比率增益平均提高7.8倍以上,在不同的复杂场景下均具有更好的检测性能.

Traditional infrared small target detection methods based on the human visual system can easily cause false alarm detection in complex backgrounds.Therefore,to address this issue,an accurate and robust infrared small target detection method called Double-layer Local Contrast Measure(DLCM)was proposed.First,a double-layer-diagonal gray difference contrast was proposed to enhance the visual saliency of the target and alleviate the impact on background clutter and noise.After that,an adaptive threshold segmentation was used to obtain the real target.The experimental results show that,compared with the mainstream detection methods based on human vision system,the background suppression factor of the proposed method is increased by an average of 9.3 times and the signal to clutter ratio gain is increased by an average of 7.8 times,which have better detection performance in different complex scenarios.