Skip to main content
Log in

Polarimetric synthetic aperture radar image segmentation by convolutional neural network using graphical processing units

  • Special Issue Paper
  • Published:
Journal of Real-Time Image Processing Aims and scope Submit manuscript

Abstract

Image segmentation is an important application of polarimetric synthetic aperture radar. This study aimed to create an 11-layer deep convolutional neural network for this task. The Pauli decomposition formed the RGB image and was used as the input. We created an 11-layer convolutional neural network (CNN). L-band data over the San Francisco bay area and C-band data over Flevoland area were employed as the dataset. For the San Francisco bay PSAR image, our method achieved an overall accuracy of 97.32%, which was at least 2% superior to four state-of-the-art approaches. We provided the confusion matrix over test area, and the kernel visualization. We compared the max pooling and average pooling. We validated by experiment that four convolution layers perform the best. Besides, our method gave better results than AlexNet. The GPU yields a 173× acceleration on the training samples, and a 181× acceleration on the test samples, compared to standard CPU. For the Flevoland PSAR image, our 11-layer CNN also gives better overall accuracy than five state-of-the-art approaches. The convolutional neural network is better than traditional classifiers and is effective in remote sensing image segmentation.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

References

  1. Hosseini, M., McNairn, H.: Using multi-polarization C- and L-band synthetic aperture radar to estimate biomass and soil moisture of wheat fields. Int. J. Appl. Earth Obs. Geoinf. 58, 50–64 (2017)

    Article  Google Scholar 

  2. Kim, S.B., van Zyl, J.J., Johnson, J.T., et al.: Surface soil moisture retrieval using the L-band synthetic aperture radar onboard the soil moisture active-passive satellite and evaluation at core validation sites. IEEE Trans. Geosci. Remote Sens. 55(4), 1897–1914 (2017)

    Article  Google Scholar 

  3. Boyarsky, M., Sleasman, T., Pulido-Mancera, L., et al.: Synthetic aperture radar with dynamic metasurface antennas: a conceptual development. J. Opt. Soc. Am. Opt. Image Sci. Vis. 34(5), A22–A36 (2017)

    Article  Google Scholar 

  4. Ravindra, V., Akbar, P.R., Zhang, M., et al.: A dual-polarization X-band traveling-wave antenna panel for small-satellite synthetic aperture radar. IEEE Trans. Antennas Propag. 65(5), 2144–2156 (2017)

    Article  Google Scholar 

  5. Maitra, S., Gartley, M.G., Kerekes, J.P.: A low-cost laboratory-based polarimetric synthetic aperture radar system for scattering analysis. IEEE Antennas Propag. Mag. 59(2), 130–141 (2017)

    Article  Google Scholar 

  6. Zhan, T.M., Chen, Y.: Multiple sclerosis detection based on biorthogonal wavelet transform, RBF kernel principal component analysis, and logistic regression. IEEE Access 4, 7567–7576 (2016)

    Article  MathSciNet  Google Scholar 

  7. Lu, S., Qiu, X.: A pathological brain detection system based on extreme learning machine optimized by bat algorithm. CNS Neurol Disord Drug Targets 16(1), 23–29 (2017)

    Article  Google Scholar 

  8. Yang, J.: Identification of green, Oolong and black teas in China via wavelet packet entropy and fuzzy support vector machine. Entropy 17(10), 6663–6682 (2015)

    Google Scholar 

  9. Chen, S., Yang, J.-F., Phillips, P.: Magnetic resonance brain image classification based on weighted-type fractional Fourier transform and nonparallel support vector machine. Int. J. Imaging Syst. Technol. 25(4), 317–327 (2015)

    Article  Google Scholar 

  10. Ding, M., Fan, G.L.: Articulated and generalized Gaussian kernel correlation for human pose estimation. IEEE Trans. Image Process. 25(2), 776–789 (2016)

    Article  MathSciNet  Google Scholar 

  11. Ding, M., Fan, G.L.: Multilayer joint gait-pose manifolds for human gait motion modeling. IEEE Trans. Cybern. 45(11), 2413–2424 (2015)

    Article  Google Scholar 

  12. Meng, D., Guoliang, F.: Multi-layer joint gait-pose manifold for human motion modeling. In: 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), pp. 1–8. IEEE, Shanghai (2013)

  13. Ding, M., Fan, G., Zhang, X., et al.: Structure-guided manifold learning for video-based motion estimation. In: 19th IEEE International Conference on Image Processing, pp. 1977–1980. IEEE, Orlando, FL (2012)

  14. Du, S.: Alzheimer’s disease detection by Pseudo Zernike moment and linear regression classification. CNS Neurol Disord Drug Targets 16(1), 11–15 (2017)

    Article  Google Scholar 

  15. Chen, Y.: A feature-free 30-disease pathological brain detection system by linear regression classifier. CNS Neurol Disord Drug Targets 16(1), 5–10 (2017)

    Article  Google Scholar 

  16. Lee, J.S., Grunes, M.R.: Classification of multi-look polarimetric SAR data based on complex Wishart distribution. In: NTC-92: National Telesystems Conference, pp. 721–724. IEEE, Washington, DC (1992)

  17. Khan, K.U., Yang, J.: Polarimetric synthetic aperture radar image classification by a hybrid method. Tsinghua Sci. Technol. 12(1), 97–104 (2007)

    Article  Google Scholar 

  18. Naggaz, N., Wei, G.: Remote-sensing image classification based on an improved probabilistic neural network. Sensors 9(9), 7516–7539 (2009)

    Article  Google Scholar 

  19. Salehi, M., Sahebi, M.R., Maghsoudi, Y.: Improving the accuracy of urban land cover classification using Radarsat-2 PolSAR data. IEEE J.Sel. Top. Appl. Earth Observ. Remote Sens. 7(4), 1394–1401 (2014)

    Article  Google Scholar 

  20. Yu, Z., Haipeng, W., Feng, X.: POLSAR terrain classification using deep convolutional networks. In: Progress in electromagnetic research symposium (PIERS), pp. 5121–5124. IEEE, Shanghai (2016)

  21. Wu, L.: Crop classification by forward neural network with adaptive chaotic particle swarm optimization. Sensors 11(5), 4721–4743 (2011)

    Article  Google Scholar 

  22. Wei, G.: A new classifier for polarimetric SAR images. Prog. Electromagn. Res. 94, 83–104 (2009)

    Article  Google Scholar 

  23. Satalino, G., Balenzano, A., Mattia, F., et al.: C-band SAR data for mapping crops dominated by surface or volume scattering. IEEE Geosci. Remote Sens. Lett. 11(2), 384–388 (2014)

    Article  Google Scholar 

  24. Wang, X.Y., Cao, Z.J., Ding, Y., et al.: Composite kernel method for PolSAR image classification based on polarimetric-spatial information. Appl. Sci. 7(6), 14 (2017)

    Google Scholar 

  25. Rosa, R.A.S., Fernandes, D., Barreto, T.L.M., et al.: Change detection under the forest in multitemporal full-polarimetric P-band SAR images using Pauli decomposition. In: International Geoscience and Remote Sensing Symposium (IGARSS), pp. 6213–6216. IEEE, Beijing (2016)

  26. Bai, X., Shi, B.G., Zhang, C.Q., et al.: Text/non-text image classification in the wild with convolutional neural networks. Pattern Recognit. 66, 437–446 (2017)

    Article  Google Scholar 

  27. Cintas, C., Quinto-Sanchez, M., Acuna, V., et al.: Automatic ear detection and feature extraction using geometric morphometrics and convolutional neural networks. IET Biom. 6(3), 211–223 (2017)

    Article  Google Scholar 

  28. Chen, Y.: Voxelwise detection of cerebral microbleed in CADASIL patients by leaky rectified linear unit and early stopping: a class-imbalanced susceptibility-weighted imaging data study. Multimed. Tools Appl. (2016). doi:10.1007/s11042-017-4383-9

    Article  Google Scholar 

  29. Ahmad, J., Mehmood, I., Baik, S.W.: Efficient object-based surveillance image search using spatial pooling of convolutional features. J. Vis. Commun. Image Represent. 45, 62–76 (2017)

    Article  Google Scholar 

  30. Qian, R.Q., Yue, Y., Coenen, F., et al.: Traffic sign recognition with convolutional neural network based on max pooling positions. In: 2th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD), pp. 578–582. IEEE, Changsha (2016)

  31. Zhu, S.G., Du, J.P.: Visual tracking using max-average pooling and weight-selection strategy. J. Appl. Math. (2014). doi:10.1155/2014/828907

    Article  Google Scholar 

  32. Oliva, D., Hinojosa, S., Cuevas, E., et al.: Cross entropy based thresholding for magnetic resonance brain images using Crow Search Algorithm. Expert Syst. Appl. 79, 164–180 (2017)

    Article  Google Scholar 

  33. Azizpour, H., Razavian, A.S., Sullivan, J., et al.: From generic to specific deep representations for visual recognition. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 36–45. IEEE, Beijing (2015)

  34. Yuan, Z.W., Zhang, J.: Feature extraction and image retrieval based on AlexNet. In: Proceedings of SPIE, p. 10033 (2016)

  35. Shelhamer, E., Long, J., Darrell, T.: Fully convolutional networks for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 640–651 (2017)

    Article  Google Scholar 

  36. Rahnemoonfar, M., Sheppard, C.: Deep count: fruit counting based on deep simulated learning. Sensors 17(4), 12 (2017)

    Google Scholar 

Download references

Acknowledgements

This study was supported by the National Natural Science Foundation of China (61602250), Natural Science Foundation of Jiangsu Province (BK20150983), and Project of Science and Technology of Henan Province (172102210272).

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Yu-Dong Zhang.

Ethics declarations

Conflict of interest

We have no conflicts of interest to disclose with regard to the subject matter of this paper.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, SH., Sun, J., Phillips, P. et al. Polarimetric synthetic aperture radar image segmentation by convolutional neural network using graphical processing units. J Real-Time Image Proc 15, 631–642 (2018). https://doi.org/10.1007/s11554-017-0717-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11554-017-0717-0

Keywords

Navigation