volume | PIER Journals

Abstract

Benefit from the high resolution, penetrating and all weather advantages of millimeter-wave (MMW) imaging, MMW imaging plays an important role in remote sensing, security inspection, navigation, etc. Among the MMW imaging systems, synthetic aperture imaging radiometer (SAIR) utilizes aperture synthetic technology to achieve higher imaging resolution, but the perception information is insufficient, resulting in poor image quality. In order to improve the image quality of passive SAIR MMW image effectively, we propose a novel multichannel depth convolutional neural network (MDCNN) in this paper. Aiming at the characteristics of original MMW images with more noise in low-frequency information and less features in high-frequency information, wavelet transform is incorporated into the MDCNN to obtain the high and low frequency components firstly. Then, dense residual block and skip connection technology are adopted to denoise and enhance target information in the four independent channels respectively. Finally, high quality MMW images are synthesized by inverse wavelet transform. The simulation results show that the reconstructed images of MDCNN have better image quality (such as image contour and texture details) than other deep learning-based methods.

1. Clark, S. E., J. A. Lovberg, C. A. Martin, and V. G. Kolinko, "Passive millimeter-wave imaging for airborne and security applications," Passive Millimeter-Wave Imaging Technology VI and Radar Sensor Technology VII, 16-21, International Society for Optics and Photonics, 2003. Google Scholar

2. Camps, A., J. Bará, I. C. Sanahuja, and F. Torres, "The processing of hexagonally sampled signals with standard rectangular techniques: Application to 2-d large aperture synthesis interferometric radiometers," IEEE Transactions on Geoscience and Remote Sensing, Vol. 35, No. 1, 183-190, 1997.
doi:10.1109/36.551946 Google Scholar

3. Duffo, N., I. Corbella, F. Torres, A. Camps, and M. Vall-llossera, "Advantages and drawbacks of near field characterization of large aperture synthesis radiometers," 8th Specialist Meeting on Microwave Radiometry and Remote Sensing Applications, 24-27, University La Sapienza, Rome, 2004. Google Scholar

4. Chen, J., Y. Li, J. Wang, Y. Li, and Y. Zhang, "An accurate imaging algorithm for millimeter wave synthetic aperture imaging radiometer in near-field,", Vol. 141, 517-535, 2013. Google Scholar

5. Van Ouwerkerk, J., "Image super-resolution survey," Image and Vision Computing, Vol. 24, No. 10, 1039-1052, 2006.
doi:10.1016/j.imavis.2006.02.026 Google Scholar

6. Zhou, F., W. Yang, and Q. Liao, "Interpolation-based image super-resolution using multisurface fitting," IEEE Transactions on Image Processing, Vol. 21, No. 7, 3312-3318, 2012.
doi:10.1109/TIP.2012.2189576 Google Scholar

7. Dong, C., C. C. Loy, K. He, and X. Tang, "Learning a deep convolutional network for image super-resolution," European Conference on Computer Vision, 184-199, Springer, 2014. Google Scholar

8. Dong, C., C. C. Loy, and X. Tang, "Accelerating the super-resolution convolutional neural network," European Conference on Computer Vision, 391-407, Springer, 2016. Google Scholar

9. Kim, J., J. K. Lee, and K. M. Lee, "Accurate image super-resolution using very deep convolutional networks," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1646-1654, 2016. Google Scholar

10. Lim, B., S. Son, H. Kim, S. Nah, and K. Mu Lee, "Enhanced deep residual networks for single image super-resolution," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 136-144, 2017. Google Scholar

11. Zhang, Y., Y. Tian, Y. Kong, B. Zhong, and Y. Fu, "Residual dense network for image super-resolution,", IEEE, 2018. Google Scholar

12. Long, Z., T. Wang, C. You, Z. Yang, K. Wang, and J. Liu, "Terahertz image super-resolution based on a deep convolutional neural network," Applied Optics, Vol. 58, No. 10, 2731-2735, 2019.
doi:10.1364/AO.58.002731 Google Scholar

13. Chen, J., S. Zhang, and X. Zhu, "Higher-order moving target detection for rotating scanning synthetic aperture interferometric radiometer," Progress In Electromagnetics Research Letters, Vol. 82, 41-49, 2019. Google Scholar

14. Woo, S., J. Park, J.-Y. Lee, and I. S. Kweon, "CBAM: Convolutional block attention module," Proceedings of the European Conference on Computer Vision (ECCV), 3-19, 2018. Google Scholar

15. Shin, D. K. and Y. S. Moon, "Super-resolution image reconstruction using wavelet based patch and discrete wavelet transform," Journal of Signal Processing Systems, Vol. 81, No. 1, 71-81, 2015.
doi:10.1007/s11265-014-0903-2 Google Scholar

16. Tanner, A., B. Lambrigsten, T. Gaier, and F. Torres, "Near field characterization of the geostar demonstrator," 2006 IEEE International Symposium on Geoscience and Remote Sensing, 2529-2532, IEEE, 2006.
doi:10.1109/IGARSS.2006.654 Google Scholar

17. Lannes, A., É. Anterrieu, and K. Bouyoucef, "Fourier interpolation and reconstruction via shannon-type techniques: I. Regularization principle," Journal of Modern Optics, Vol. 41, No. 8, 1537-1574, 1994.
doi:10.1080/09500349414552411 Google Scholar

18. Lannes, A., É. Anterrieu, and K. Bouyoucef, "Fourier interpolation and reconstruction via shannon-type techniques II. Technical developments and applications," Journal of Modern Optics, Vol. 43, No. 1, 105-138, 1996.
doi:10.1080/09500349608232728 Google Scholar

19. Lewis, B. and F. Sgallari, "Tikhonov regularization with nonnegativity constraint," Electronic Transactions on Numerical Analysis, Vol. 18, 153-173, 2004. Google Scholar

Dr. Ruyue Peng

Professor Jianfei Chen

Dr. Zhao Liu

Dr. Zhimin Guo