基于神经网络的改进型红外图像自适应非均匀校正算法  

Improved Adaptive IR Image Non-uniformity Correction Algorithm Based on Neural Network

作　　者：聂瑞杰[1] 李丽娟[1] 王朝林[1] 

机构地区：[1]中国空空导弹研究院,河南洛阳471009

出　　处：《红外》2015年第9期10-14,共5页Infrared

基　　金：总装探索项目(7131466);科技创新基金项目(CJK1416)

摘　　要：针对传统的基于神经网络的自适应非均匀性校正(Nearal-Network-based NonUniformity Correction,NN-NUC)算法在实际应用中存在校正能力有限和容易产生鬼影的问题,深入分析了NN-NUC算法中的鬼影产生过程,并给出了抑制鬼影的一般性方法;然后结合实际红外成像系统的特点,提出了一种改进型NN-NUC算法。仿真实验结果表明,该算法可以最大限度地抑制场景鬼影的产生,并可有效减小系统输出图像的非均匀性噪声。此外,本文算法计算量小,且易于用硬件实现,因此具有很好的工程应用价值。In practical applications, the traditional adaptive nonuniformity correction algorithm based on Neural Network （NN-NUC） has a limited correction capability and is easy to generate ghosting ar- tifacts. To solve this problem, the ghosting artifact generating process in the NN-NUC algorithm is analyzed in detail and the common methods for removing ghosting artifacts are given. Then, by incorpo- rating the characteristics of actual infrared imagers, an improved NN-NUC algorithm is proposed. The simulation experimental results show that the proposed method can suppress the generation of ghosting artifacts in a scene extremely and can reduce the nonuniformity noise of the image effectively. Moreover, the proposed algorithm has a small calculation amount and is easy to be implemented by hardware. So it is of good value to practical applications.

关 键 词：自适应非均匀性校正 红外图像 神经网络 鬼影 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]