论文部分内容阅读
提出了一种用于检测不同类型复杂背景下红外弱小运动目标的新方法。该方法能够根据图像信息自动选择背景预测算子;同时,针对不同类型复杂背景中目标和背景特性的差异,提出了“局部小目标可辨识度”的概念,并定义了一种有效的方法将其量化。在此基础上,采用蒙特卡罗实验方法构造了一种新的阈值函数,实现了单帧目标的检测,然后采用移动加权管道滤波提取目标的运动轨迹。实验结果表明,该方法对不同类型复杂背景的红外弱小运动目标具有很好的检测性能。
A new method is proposed for the detection of small and weak infrared moving targets with different types of complex background. The method can automatically select the background prediction operator according to the image information. At the same time, the concept of “local small target identifiability” is proposed for the differences of the target and background features in different types of complex backgrounds, and an effective Method to quantify it. On this basis, a new threshold function is constructed by using Monte Carlo experimental method, the detection of single-frame target is realized, and the moving track of target is extracted by moving weighted pipe filter. Experimental results show that the proposed method has good performance in detecting infrared weak moving targets with different types of complex background.