DopNet: A Deep Convolution Neural Network to recognize armed and unarmed human targets

The work presented in this paper aims to distinguish between armed or unarmed personnel using multi-static radar data and advanced Doppler processing. We propose two modified Deep Convolutional Neural Networks (DCNN) termed SCDopNet and MC-DopNet for mono-static and multi-static micro- Doppler signature (μ-DS) classification. Differentiating armed and unarmed walking personnel is challenging due to the effect of aspect angle and channel diversity in real-world scenarios. In addition, DCNN easily overfits the relatively small-scale μ-DS dataset. To address these problems, the work carried out in this paper makes three key contributions: first, two effective schemes including data augmentation operation and a regularization term are proposed to train SC-DopNet from scratch. Next, a factor analysis of the SC-DopNet are conducted based on various operating parameters in both the processing and radar operations. Thirdly, to solve the problem of aspect angle diversity for μ-DS classification, we design MC-DopNet for multi-static μ- DS which is embedded with two new fusion schemes termed as Greedy Importance Reweighting (GIR) and `21-Norm. These two schemes are based on two different strategies and have been evaluated experimentally: GIR uses a “win by sacrificing worst case” whilst `21-Norm adopts a “win by sacrificing best case” approach. The SC-DopNet outperforms the non-deep methods by 12.5% in average and the proposed MC-DopNet with two fusion methods outperforms the conventional binary voting by 1.2% in average. Note that we also argue and discuss how to utilize the statistics of SC-DopNet results to infer the selection of fusion strategies for MC-DopNet under different experimental scenarios