基于朴素贝叶斯分类器的空中红外目标抗干扰识别方法研究

红外诱饵对抗技术的发展使得空战环境日益复杂化，对红外成像制导空空导弹抗干扰目标识别技术提出了更高的要求。红外诱饵的投放使得目标特征的完整性、显著性及稳定性遭到破坏，基于特征融合匹配的统计模式识别方法无法准确识别目标。提出了一种基于朴素贝叶斯分类器的抗干扰目标识别方法，该方法对空战对抗仿真图像数据集进行了特征挖掘，利用实验拟合方法构建了典型特征的概率密度函数模型，构造了朴素贝叶斯分类器，实现了飞机目标和干扰的分类识别。仿真实验结果表明，该方法在已测试的弹道图像数据集下的平均识别正确率达到了81.82%，且能够解决假目标、目标遮挡等抗干扰目标的识别难题。

Research on Anti-jamming Recognition Method of Aerial Infrared Target Based on Naive Bayes Classifier

The development of infrared decoy confrontation technology has made the air combat environment increasingly complicated, and put forward higher requirements for the anti-jamming target recognition technology of infrared imaging guide air-to-air missiles. The infrared decoy is placed to destroy the integrity, significance and stability of the target features. The statistical pattern recognition method based on feature fusion matching cannot accurately identify the target. For performance requirements, this paper proposes a method for applying Naive Bayes Classifier to anti-interference target recognition. The method based on the feature mining simulated combat against the image dataset, wherein the method is typically constructed probabilistic experiment fitting distribution function models, Naive Bayes Classifier configured to classify the target aircraft identification and interference. The simulation results show that the average recognition accuracy of the proposed method is 81.82% under the tested ballistic image dataset, and it can adapt to a large number of decoy and target occlusion.