基于RBF神经网络的背景估计及红外小目标检测

Background Estimation and the Infrared Small Target Detection Based on RBF Neural Network

利用RBF神经网络的函数逼近特性,得到了一种红外图像背景估计算法,进而提出了一种检测红外小目标的方法。利用有目标和没有目标的真实红外图像对此算法进行检测,背景估计效果理想,小目标检测效果理想,证明该算法是可行有效的。

Using the function approximation characteristic of RBF-neural network, a new algorithm of estimating the background is proposed. Based this algorithm, a new means to detect the infrared small target is found. Here, two kinds of infrared images, one with a small target in it and the other without the target, are tested in the simulated experiments. The result of the experiments proves the good performance of the proposed algorithm.