遗传算法优化结构元素的红外小目标检测方法

摘要

提出了一种基于遗传算法优化结构元素,从而对红外小目标进行检测的方法.数学形态学中结构元素选取的正确与否,决定着小目标检测的好坏.利用遗传算法可以在全局范围内搜索到最优值的特点,对结构元素进行优化选取,而无需根据先验知识来确定结构元素.实验表明,该方法不仅可以准确地检测出红外小目标,方法简单,而且自适应强,不用人为的干预,完全可以实现自动的对小目标进行检测.%In this paper, in order to detect the small target in the IR grey image, a new method based on genetic algorithms (GA) to optimize the structuring element is proposed.The structuring element is very important in mathematical morphology, so that it can decide the quality of the detected small target.Since GA can find suitable approximated solutions treating the problem as a global optimization technique, the structuring element can be created and optimized by GA.Therefore, even if the characteristic of the detected small target is not known, the optimal structuring element can also be confirmed, and the small target can be detected.The experiments show that this method is simple, accurate, and adaptive.