基于视觉对比机制的红外弱小目标检测方法

为解决复杂背景下红外弱小目标检测精度低的问题,本文提出一种基于视觉对比机制的红外弱小目标检测方法,算法主要模拟了人眼对目标对比度敏感这一机制。首先利用8向梯度方程提取红外图像的梯度显著图并二值化处理；根据小目标的尺寸大小特征对梯度显著图进行优化处理,剔除孤立的噪声点和尺寸较大的背景梯度显著区域；利用视觉对比机制对优化后的显著图进行局部对比度计算,通过阈值处理剔除虚警目标,完成红外弱小目标检测。仿真实验表明,该算法在低信噪比情况下对红外弱小目标的检测率较高,且虚警率低,单帧检测时间较小。

Infrared dim target detection based on visual contrast mechanism

In order to solve the problem of low detection accuracy of infrared dim targets under complex background,a method of infrared dim target detection based on visual contrast mechanism was presented.Firstly,the gradient saliency map of the infrared image is extracted by the 8 direction gradient equation,and binarization processing is carried out for them.According to the size characteristics of small targets,the gradient saliency map is optimized to eliminate the isolated noise points and the larger saliency area of the background gradient.The visual contrast mechanism is used to calculate the local contrast of the optimized saliency map,and then the false target is eliminated by the threshold processing to achieve the infrared dim target detection.The simulation results show that the proposed algorithm has higher detection rate,lower false alarm rate and short single frame detection time in the case of low SNR.