Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Mar 19;20(6):1724.
doi: 10.3390/s20061724.

TAI-SARNET: Deep Transferred Atrous-Inception CNN for Small Samples SAR ATR

Zilu Ying  1 , Chen Xuan  1 , Yikui Zhai  1 , Bing Sun  2 , Jingwen Li  2 , Wenbo Deng  1 , Chaoyun Mai  1 , Faguan Wang  1 , Ruggero Donida Labati  3 , Vincenzo Piuri  3 , Fabio Scotti  3
Affiliations

TAI-SARNET: Deep Transferred Atrous-Inception CNN for Small Samples SAR ATR

Zilu Ying et al. Sensors (Basel). .

Abstract

Since Synthetic Aperture Radar (SAR) targets are full of coherent speckle noise, the traditional deep learning models are difficult to effectively extract key features of the targets and share high computational complexity. To solve the problem, an effective lightweight Convolutional Neural Network (CNN) model incorporating transfer learning is proposed for better handling SAR targets recognition tasks. In this work, firstly we propose the Atrous-Inception module, which combines both atrous convolution and inception module to obtain rich global receptive fields, while strictly controlling the parameter amount and realizing lightweight network architecture. Secondly, the transfer learning strategy is used to effectively transfer the prior knowledge of the optical, non-optical, hybrid optical and non-optical domains to the SAR target recognition tasks, thereby improving the model's recognition performance on small sample SAR target datasets. Finally, the model constructed in this paper is verified to be 97.97% on ten types of MSTAR datasets under standard operating conditions, reaching a mainstream target recognition rate. Meanwhile, the method presented in this paper shows strong robustness and generalization performance on a small number of randomly sampled SAR target datasets.

Keywords: Atrous-Inception module; Convolutional Neural Network (CNN); Synthetic Aperture Radar (SAR); lightweight network; small sample; transfer learning.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
The structure of the proposed network.
Figure 2
Figure 2
Atrous Convolution.
Figure 3
Figure 3
Structure of the Atrous-Inception module.
Figure 4
Figure 4
Transfer prior knowledge of optical images.
Figure 5
Figure 5
Transfer prior knowledge of non-optical images.
Figure 6
Figure 6
MSTAR dataset image example.
Figure 7
Figure 7
Visualization graphs for training and validation.
Figure 8
Figure 8
Result on state-of-the-art model on small samples.
See this image and copyright information in PMC

References

    1. Tait P. Introduction to Radar Target Recognition. Volume 18. The Institution of Engineering and Technology (IET); Stevenage, UK: 2005. - DOI
    1. Abdi H., Williams L.J. Principal component analysis. Wiley Interdiscip. Rev. Comput. Stat. 2010;2:433–459. doi: 10.1002/wics.101. - DOI
    1. Bartlett M.S., Movellan J.R., Sejnowski T.J. Face recognition by independent component analysis. IEEE Trans. Neural Netw. 2002;13:1450–1464. doi: 10.1109/TNN.2002.804287. - DOI - PMC - PubMed
    1. Hall-Beyer M. Practical guidelines for choosing GLCM textures to use in landscape classification tasks over a range of moderate spatial scales. Int. J. Remote Sens. 2017;38:1312–1338. doi: 10.1080/01431161.2016.1278314. - DOI
    1. Kar N.B., Babu K.S., Jena S.K. Face expression recognition using histograms of oriented gradients with reduced features; Proceedings of the International Conference on Computer Vision and Image Processing; IIT Roorkee, India. 26–28 February 2016; Singapore: Springer; 2017. pp. 209–219. - DOI