基于多向差异度的红外弱小目标检测算法

摘要

在分析红外图像中弱小目标的特征后,针对目前经典的红外弱小目标检测算法性能不足的问题,提出了一种基于多向差异度的红外弱小目标检测算法.该算法利用待检测像素点在各方向上的差异度来判决其是否为目标,无需背景预测、图像增强等处理,因此其构造简单,计算量小,易于实现,并能有效改善复杂背景环境下红外弱小目标的检测性能.通过大量的仿真实验证明了该算法的有效性和优越性.%After analyzing the characteristics of dim infrared target, in view of the shortcomings of the classic detection algorithms, a detection algorithm for dim infrared target base on multi-difference factor is proposed in this paper. This algorithm detects target by identify an unknown pixel based on the value of the difference factor in. As this method needn't to estimate the background of infrared image or enhance the infrared image, so this algorithm is a very simple construction with small calculating works, and this algorithm is easy to be realized. This algorithm can improve detection chance in infrared image of complex background. At last this algorithm is proved to be effective and superior through a lot of stimulation.