基于ARM的嵌入式直升机目标识别系统  

Embedded helicopter target recognition system based on ARM

作　　者：张芳[1] 许学忠[1] 梁旭斌[1] 何斌[1] 

机构地区：[1]西北核技术研究所,陕西西安710024

出　　处：《电子技术应用》2009年第4期30-32,共3页Application of Electronic Technique

摘　　要：设计了一种用于声探测预警的嵌入式直升机目标识别系统。采用嵌入式微处理器S3C44B0X作为系统CPU完成了目标识别平台的设计,在小波包分析法提取直升机特征向量的基础上,训练BP神经网络分类器进行目标分类。实验结果表明,该识别系统对直升机类目标有较高的识别率。An embedded helicopter target recognition system is designed for battlefield forewarning. S3C44BOX embedded micro-processor is used as the CPU of the system in target recognition platform designing. On the basis of extracting helicopter＇s charac-teristic vector using wavelet pack analysis, judge the target identification by training the BP neural network classifier. Experimental results show that this system can achieve high target recognition rate to helicopter.

关 键 词：嵌入式 小波包分析 特征提取 BP神经网络 目标识别 

分 类 号：TN492[电子电信—微电子学与固体电子学]