Radar high resolution range profile recognition via Dual-SVDD classifier

To identify the out-of-database targets in the process of radar ground target recognition with high resolution range profile, this paper proposes an improved radar ground target classifier based on the covariance distribution of the space of training features, namely Dual-SVDD classifier. In the training phase, a double correlate SVDD structure is constructed in feature space and a multi-region data description is obtained based on the covariance of target training database. The new classifier separates the training sets into several regions, which are independent identically uniform distributed. Then, the category determination of testing target data is based on the support vectors and the region radial of the SVDD method with the multi-region data description. This method can work without the template of out-of-database samples, which improves the effectiveness of target identification. Finally, the experiment based on the measured data verifies its excellent performance of identification.