摘要
针对红外小目标检测问题,提出一种基于BP(back propagation)神经网络的小目标检测算法。该算法利用BP神经网络的函数逼近特性对红外图像进行背景估计,然后根据背景对消原理消去背景噪声,从而检测到潜在的红外小目标。通过仿真实验证明该算法的有效性。
In view of the problem to detect small infrared trargets, a new algorithm based on BP neural network is proposed. The algorithm, using the function approximation characteristic of BP neural network, estimates the background of infrared images, then based on the background eliminating principle, clears up background the noise thus detecting the latent small infrared targets. The simulation results proves the good performance of the proposed algorithm.
出处
《系统工程与电子技术》
EI
CSCD
北大核心
2004年第12期1901-1904,共4页
Systems Engineering and Electronics
关键词
小目标检测
BP神经网络
背景估计
背景对消
small target detection
BP neural network
background estimating
background eliminating
