Efficient deep convolutional neural networks using CReLU for ATR with limited SAR images

Abstract

The computational cost of many deep convolutional neural networks (CNNs) for the automatic target recognition proposed in the area of synthetic aperture radar (SAR) imagery recently is huge, and the limited SAR images are always insufficient for training the deep CNNs. To improve the computational efficiency, a new light but very efficient convolutional network architecture is designed using some novel techniques to get the better results. The authors apply the batch normalisation before each convolutional layer in order to reduce ‘internal covariate shift’ and use the drop-out strategy in the fully layer to avoid over-fitting. Additionally, concatenated ReLU is used as activation scheme specially instead of ReLU for preserving the negative phase information to get the double feature maps of the previous layer rather than to increase the depth of the filters that can lessen the parameters of the networks. The results of the experimental demonstrate that the authors’ CNNs can both achieve a state-of-the-art classification accuracy of 99.53% of the SAR target classification in the Moving and Stationary Target Acquisition and Recognition ten classes public dataset and perform well even when the training data is sparse.

Keywords

• radar target recognition
• learning (artificial intelligence)
• synthetic aperture radar
• image recognition
• feature extraction
• convolution
• neural nets
• image classification
• radar imaging
• efficient deep convolutional neural networks
• sar images
• computational cost
• automatic target recognition
• synthetic aperture radar imagery
• deep cnns
• computational efficiency
• efficient convolutional network architecture
• convolutional layer
• internal covariate shift
• fully layer
• authors
• sar target classification