%0 Journal Article %T Research on GPR Multi-object Recognition
探地雷达多目标识别方法的研究 %A Hu Jin-feng %A Zhou Zheng-ou %A Kong Ling-jiang %A
胡进峰 %A 周正欧 %A 孔令讲 %J 电子与信息学报 %D 2006 %I %X With limited samples, SVM has stronger ability of generalization in comparison with machine learning algorithm. In this paper, the SVM is combined with the Ground Penetrating Radar(GPR) multi-object recognition, and a GPR multi-object recognition method is proposed based on the one against one SVM. The proposed method includes the GPR multi-object recognition method based on one against one SVM, the parameter selection method based on the cross-validation and the multichannel recognition method. The contrast analysis between the proposed method and the conventional neural network method is given. The proposed method can be combined with object-feature extraction methods. It is shown that the method is effective in the experimental analysis. The conclusion can direct the research on GPR object recognition. %K GPR %K Multi-object recognition %K SVM %K Non-linear mapping %K Neural network
探地雷达 %K 多目标识别 %K 支撑矢量机 %K 非线性映射 %K 神经网络 %U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=1319827C0C74AAE8D654BEA21B7F54D3&jid=EFC0377B03BD8D0EF4BBB548AC5F739A&aid=5A1101596F3A3A94&yid=37904DC365DD7266&vid=D3E34374A0D77D7F&iid=CA4FD0336C81A37A&sid=96C778EE049EE47D&eid=340AC2BF8E7AB4FD&journal_id=1009-5896&journal_name=电子与信息学报&referenced_num=0&reference_num=15