中文摘要：

利用大多数武器装备含有铁磁材料的特性，提出一种基于磁异信号的地面机动目标分类算法。根据不同类型目标对地磁产生相应影响的原理，探测目标存在和识别目标类型。磁传感器用于采集目标产生的地磁场扰动信号，通过统计样本集训练和设计分类器，检验目标信号特征的类型最佳匹配模式，并对常见的3类目标进行试验研究。结果表明这种分类算法计算量小，分类正确率高，可以适用于地面侦察和目标入侵检测。

英文摘要：

A novel classification algorithm was proposed for ground mobile targets based on magnetoresistive signals, as most of weapons have a character made from much steel or iron. According to the principle of different earth magnetic influence produced by diverse vehicles, a mobile target can be detected and classified with a simple computation method by a magnetic sensor. The detection sensor is used for collecting a disturbed signal of earth magnetic field from a mobile target. After some statistical samples are trained and a classification machine is designed, the target signal feature is tested for category pattern match. Three common targets were experimented. The experimented results are shown that the algorithm has a low computation cost and a better sorting accuracy, and can be applied to ground reconnaissance and target intrusion detection.