基于DSP的低分辨率红外目标特征提取及识别  

Low-resolution IR Target Feature Extraction and Recognition Based on DSP

作　　者：罗来邦[1] 常本康[1] 张力 王述琪[2] 杨郁伟[2] 

机构地区：[1]南京理工大学电光学院,江苏南京210094 [2]西安机电信息研究所,陕西西安710065

出　　处：《探测与控制学报》2004年第3期9-12,共4页Journal of Detection & Control

摘　　要：针对末敏子弹试验样机在某试验靶场的高塔上扫描,所获得的低分辨率红外目标图像,介绍了目标特征提取及识别方法。研究指出目标波形携带了与目标密切相关的信息,利用参数方法对目标波形进行分析并选取某些参数作为目标特征向量,可对目标进行粗略分类和识别。在对目标波形进行特征分析的基础上,用抽取的特征向量构造了目标模板。用以DSP为图像微处理器的试验样机进行现场试验表明:该方法对低分辨率红外目标的识别有好的效果。The approach of target feature extraction and recognition for the low-resolution IR target image is studied in this paper. The methods of target classification and recognition are proposed according to the information of target waveforms .The feature extracted by target waveforms is analyzed and acted as the feature of classification and recognition. By use these extracted features, we construct several target modules. And this method has been applied in the test prototype with TMS320F240 as its microprocessor. The experiment result indicates that this recognition method is fine to recognize the low-resolution IR target image.

关 键 词：DSP 波形 目标识别 特征提取 灵巧弹药 

分 类 号：TN911.7[电子电信—通信与信息系统]