A novel sense-through-foliage target recognition system based on sparse representation and improved particle swarm optimization-based support vector machine

作者：Zhai Shijun^*; Jiang Ting

来源：Measurement, 2013, 46(10): 3994-4004.

DOI：10.1016/j.measurement.2013.08.018

• Target recognition
• Sparse representation
• Support vector machine
• Improved particle swarm optimization
• UWB bistatic radar

A new recognition system of improved particle swarm optimization-based support vector machine (SVM) combined with sparse representation-based feature extraction is proposed for recognize targets obscured by foliage. Real data sets of four kinds of samples are acquired using a bistatic ultra-wideband (UWB) radar system. Sparse representation (SR) theory is applied to analyzing the components of received target echo signals and sparse coefficients are used to describe target features, the dimension of the sparse coefficients is reduced using principal component analysis (PCA). Support vector machine is a powerful tool for solving the recognition problem with small sampling, nonlinearity and high dimension. Improved particle swarm optimization (IPSO) is developed in this study to determine the optimal parameters for SVM with the highest accuracy and generalization ability. The experiment results indicate that the method of feature extraction using SR can effectively represent the original data better. The recognition result of the proposed method is also compared with SVM, k-nearest neighbor (KNN) and BP neural network (BPNN). The effectiveness of the proposed approach is verified by experiments taken in the forest environment. Our findings show that the proposed method combined with bistatic UWB radar technology provides a good access to achieve the aim of automatic sense through foliage target recognition.

• 出版日期2013-12
• 单位北京大学