摘要： 针对复杂背景下红外弱小目标检测难题，提出一种基于自适应形态滤波和Markov随机场(MRF)模型的小目标检测算法。设计基于图像局部熵优化的自适应形态滤波器，采用该滤波器进行背景杂波抑制和目标增强，利用MRF理论描述图像像素间关系，构造新的势函数和能量函数，建立目标检测识别模型，通过模型计算自动识别出红外图像中的小目标。理论分析和实验结果表明，该算法可在复杂背景下自适应地抑制背景杂波，成功检测出红外小目标。

关键词: Markov随机场模型, 势函数, 形态滤波, 图像熵, 红外小目标

Abstract: Aiming at the difficulty in detecting infrared dim small target under strong background clutter, a novel detecting infrared dim small target algorithm based on adaptive morphological filtering and Markov Random Field(MRF) model is proposed. In the algorithm, an adaptive morphological filter optimized by image local entropy is designed to the background clutter suppression and target enhancement. New potential function and energy function are introduced according to MRF theory to describe the relationship between pixels and a small infrared target detection model is built to confirm automatically the location and size of the target. Simulation results show that the algorithm is effective.

Key words: Markov Random Field(MRF) model, potential function, morphological filtering, image entropy, infrared small target

中图分类号: 

• TP391.41