Journal of the Korea Institute of Military Science and Technology (한국군사과학기술학회지)

The Korea Institute of Military Science and Technology (한국군사과학기술학회)
권호 표지
DOI QR코드

DOI QR Code

Channel Attention Module in Convolutional Neural Network and Its Application to SAR Target Recognition Under Limited Angular Diversity Condition

합성곱 신경망의 Channel Attention 모듈 및 제한적인 각도 다양성 조건에서의 SAR 표적영상 식별로의 적용

  • Park, Ji-Hoon (The 3rd Research and Development Institute, Agency for Defense Development) ;
  • Seo, Seung-Mo (The 3rd Research and Development Institute, Agency for Defense Development) ;
  • Yoo, Ji Hee (The 3rd Research and Development Institute, Agency for Defense Development)
  • 박지훈 (국방과학연구소 제3기술연구본부) ;
  • 서승모 (국방과학연구소 제3기술연구본부) ;
  • 유지희 (국방과학연구소 제3기술연구본부)
  • Received : 2020.09.04
  • Accepted : 2021.01.14
  • Published : 2021.04.05
Download PDF
⟨ Previous Next ⟩

Abstract

In the field of automatic target recognition(ATR) with synthetic aperture radar(SAR) imagery, it is usually impractical to obtain SAR target images covering a full range of aspect views. When the database consists of SAR target images with limited angular diversity, it can lead to performance degradation of the SAR-ATR system. To address this problem, this paper proposes a deep learning-based method where channel attention modules(CAMs) are inserted to a convolutional neural network(CNN). Motivated by the idea of the squeeze-and-excitation(SE) network, the CAM is considered to help improve recognition performance by selectively emphasizing discriminative features and suppressing ones with less information. After testing various CAM types included in the ResNet18-type base network, the SE CAM and its modified forms are applied to SAR target recognition using MSTAR dataset with different reduction ratios in order to validate recognition performance improvement under the limited angular diversity condition.

Keywords

References

  1. K. El-Darymli, et al., "Automatic Target Recognition in Synthetic Aperture Radar Imagery: A State-of-the-Art Review," IEEE Access, Vol. 6, pp. 6014-6058, 2016. https://doi.org/10.1109/ACCESS.2016.2611492
  2. M. David, "Deep Convolutional Neural Networks for ATR from SAR Imagery," Proc. SPIE, Algorithms for Synthetic Aperture Radar Imagery XXII, Vol. 9475, 2015.
  3. J. Ding, et al., "Convolutional Neural Network with Data Augmentation for SAR Target Recognition," IEEE Geoscience and Remote Sensing Letters, Vol. 13, No. 3, pp. 364-368, 2016. https://doi.org/10.1109/LGRS.2015.2513754
  4. S. Chen, et al., "Target Classification Using the Deep Convolutional Networks for SAR Images," IEEE Trans. Geoscience and Remote Sensing, Vol. 54, No. 8, pp. 4806-4817, 2016. https://doi.org/10.1109/TGRS.2016.2551720
  5. S. Wagner, "SAR ATR by Combination of Convolutional Neural Network and Support Vector Machine," IEEE Trans. Aerospace and Electronic Systems, Vol. 52, No. 6, pp. 2861-2872, 2016. https://doi.org/10.1109/TAES.2016.160061
  6. O. Kechagias-Stamatis et al., "Fusing Deep Learning and Sparse Coding for SAR ATR," IEEE Trans. Aerospace and Electronic Systems, Vol. 55, No. 2, pp. 785-797, 2019. https://doi.org/10.1109/taes.2018.2864809
  7. J. H. Cho, et al., "Multiple Feature Aggregation Using Convolutional Neural Networks for SAR Image-Based Automatic Target Recognition," IEEE Geoscience and Remote Sensing Letters, Vol. 15, No. 12, pp. 1882-1886, 2018. https://doi.org/10.1109/lgrs.2018.2865608
  8. Q. Yu, et al., "High-Performance SAR ATR Under Limited Data Condition Based on a Deep Feature Fusion Network," IEEE Access, Vol. 7, pp. 165646-165658, 2019. https://doi.org/10.1109/access.2019.2952928
  9. Z. Lin, et al., "Deep Convolutional Highway Unit Network for SAR Target Classification with Limited Labeled Training Data," IEEE Geoscience and Remote Sensing Letters, Vol. 14, No. 7, pp. 1091-1095, 2017. https://doi.org/10.1109/LGRS.2017.2698213
  10. F. Zhou, et al., "SAR ATR of Ground Vehicles Based on LM-BN-CNN," IEEE Trans. Geoscience and Remote Sensing, Vol. 56, No. 12, pp. 7282-7293, 2018. https://doi.org/10.1109/tgrs.2018.2849967
  11. L. Wang, et al., "SAR ATR of Ground Vehicles Based on ESENet," Remote Sensing, Vol. 11, No. 11, pp. 1316-1331, 2019. https://doi.org/10.3390/rs11111316
  12. G. Huang, et al., "A Novel Group Squeeze Excitation Sparsely Connected Convolutional Networks for SAR Target Classification," International Journal of Remote Sensing, Vol. 40, No. 11, pp. 4346-4360, 2019. https://doi.org/10.1080/01431161.2018.1562586
  13. F. Zhang, et al., "Multi-Aspect-Aware Bidirectional LSTM Networks for Synthetic Aperture Radar Target Recognition," IEEE Access, Vol. 5, pp. 26880-26891, 2017. https://doi.org/10.1109/ACCESS.2017.2773363
  14. J. Pei, et al., "SAR Automatic Target Recognition Based on Multiview Deep Learning Framework," IEEE Trans. Geoscience and Remote Sensing, Vol. 56, No. 4, pp. 2196-2210, 2018. https://doi.org/10.1109/tgrs.2017.2776357
  15. P. Zhao, et al., "Multi-Stream Convolutional Neural Network for SAR Automatic Target Recognition," Remote Sensing Vol. 10, No. 9, pp. 1473-1494, 2018. https://doi.org/10.3390/rs10091473
  16. J. Hu, et al., "Squeeze-and-Excitation Networks," Proc. IEEE Conference on Computer Vision and Pattern Recognition(CVPR 2018), pp. 7132-7141, 2018.
  17. K. He, et al., "Deep Residual Learning for Image Recognition," Proc. IEEE Conference on Computer Vision and Pattern Recognition(CVPR 2016), pp. 770-778, 2016.
  18. K. He, et al., "Identity Mappings in Deep Residual Networks," Proc. European Conference in Computer Vision(ECCV 2016), pp. 630-645, 2016.
  19. A. Bochkovskiy, et al., "YOLOv4 : Optimal Sped and Accuracy of Object Detection," arXiv 2020, Available Online:Arxiv.org/abs/2004.10934.
  20. S. Woo, et al., "CBAM : Convolutional Block Attention Module," Proc. European Conference in Computer Vision(ECCV 2018), pp. 3-9, 2018.