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

A Complex Valued ResNet Network Based Object Detection Algorithm in SAR Images

복소수 ResNet 네트워크 기반의 SAR 영상 물체 인식 알고리즘

  • Hwang, Insu (The Intelligence & Information Technology Directorate, Agency for Defense Development)
  • 황인수 (국방과학연구소 국방첨단기술연구원)
  • Received : 2021.03.30
  • Accepted : 2021.06.18
  • Published : 2021.08.05
Download PDF
⟨ Previous Next ⟩

Abstract

Unlike optical equipment, SAR(Synthetic Aperture Radar) has the advantage of obtaining images in all weather, and object detection in SAR images is an important issue. Generally, deep learning-based object detection was mainly performed in real-valued network using only amplitude of SAR image. Since the SAR image is complex data consist of amplitude and phase data, a complex-valued network is required. In this paper, a complex-valued ResNet network is proposed. SAR image object detection was performed by combining the ROI transformer detector specialized for aerial image detection and the proposed complex-valued ResNet. It was confirmed that higher accuracy was obtained in complex-valued network than in existing real-valued network.

Keywords

References

  1. G. R. Benitz, "Synthetic Aperture Radar(SAR) Tutorial," MTI Lincoln Laboratory, 2009.
  2. W. Li, J. Chen, X. Shi, A. Liu, "An Optimization Beam-position Selection Method Based on Genetic Algorithm for Distributed Satellite-borne SAR System," Procedings of IEEE CIE International Conference on Radar, pp. 895-898, 2011.
  3. T. Zhang, X. Zhang, J. Shi, S. Wei, J. Wang, J. Li, "Balanced Feature Pyramid Network for Ship Detection in Synthetic Aperture Radar Images," IEEE Radar Conference, pp. 1-5, 2020.
  4. L. Liu, G. Chen, Z. Pan, B. Lei, Q. An, "Inshore Ship Detection in SAR Images Based on Deep Neural Networks," IEEE Geoscience and Remote Sensing Symposium, pp. 25-28, 2018.
  5. M. Kang, X. Leng, Z. Lin, K. Li, "A Modified Faster R-CNN Based on CFAR Algorithm for SAR Ship Detection," International Workshop on Remote Sensing with Intelligent Processing, pp. 1-4, 2017.
  6. Y. Li, Z. Ding, Y. Wang, J. Chen, "SAR Ship Detection Based on ResNet and Transfer Learning," IEEE International Geoscience and Remote Sensing Symposium, pp. 1188-1191, 2019.
  7. J. Ding, B. Chen, H. Liu, M. Huang, "Convolutional Neural Network with Data Augmentation for SAR Target Recognition," IEEE Geoscience and Remote Sensing Letters, pp. 364-368, 2016.
  8. T. Yang, J. Zhu, J. Liu, "SAR Image Target Detection and Recognition Based on Deep Network," SAR in Big Data Era, pp.1-4, 2019.
  9. Y. Wang, Y. Zhang, H. Qu, Q. Tian, "Target Detection and Recognition Based on Convolutional Neural Network for SAR Image," International Congress on Image and Signal Processing, pp. 1-5, 2018.
  10. S. Gu, L. Ding, "A Complex-valued VGG Network Based Deep Learning Algorithm for Image Recognition," Ninth International Conference of Intelligent Control and Information Processing, pp. 340-343, 2018.
  11. J. Ding, N. Xue, Y. Long, G.S Xia, Q. Lu, "Learning ROI Transformer for Oriented Object Detection in Aerial Images," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2849-2858, 2019.
  12. C. Trabelsi, O. Bilaniuk, Y. Zhang, "Deep Complex Networks," International Conference on Learning Representations, 2017.
  13. Z. Sun, X. Xu, Z. Pan, "SAR ATR Using Complex-valued CNN" Asia-pacific Conference of Image Processing, Electronics and Computers, pp. 125-128, 2020.
  14. H. Choi, J. Kim, J. Huh, A. Kim, J. Ha, K. Lee, "Phase-aware Speech Enhancement with Deep Complex U-net," International Conference on Learning Representations, 2019.
  15. X. Glorot, Y. Bengio, "Understanding the Difficulty of Training Deep Feedforward Neural Networks," In Aistats, pp. 249-256, 2019.