2020-10-16
A Robust Approach for Three-Dimensional Real-Time Target Localization Under Ambiguous Wall Parameters
By
Progress In Electromagnetics Research M, Vol. 97, 145-156, 2020
Abstract
To obtain three-dimensional (3-D) high-precision and real-time through-wall location under ambiguous wall parameters, an approach based on the extreme learning machine (ELM) which is a neural network is proposed. The wall's ambiguity and propagation effects are both included in the hidden layer feedforward network, and then the through-wall location problem is converted to a regression problem. The relationship between the scattered signals and the target properties are determined after the training process. Then the target properties are estimated using the ELM approach. Numerical results demonstrate good performance in terms of effectiveness, generalization, and robustness, especially for the kernel extreme learning machine (KELM) approach. Noiseless and noisy measurements are performed to further demonstrate that the approach can provide good performance in terms of stability and reliability. The location time, including the training time and the test time, is also discussed, and the results show that the KELM approach is very suitable for real-time location problems. Compared to the machine learning approach, the KELM approach is better not only in the aspect of accuracy but also in location time.
Citation
Hua-Mei Zhang, Sheng Zhou, Cheng Xu, and Jiao Jie Zhang, "A Robust Approach for Three-Dimensional Real-Time Target Localization Under Ambiguous Wall Parameters," Progress In Electromagnetics Research M, Vol. 97, 145-156, 2020.
doi:10.2528/PIERM20060701
References

1. Soldovieri, F. and R. Solimene, "Through-wall imaging via a linear inverse scattering algorithm," IEEE Geoscience and Remote Sensing Letters, Vol. 4, No. 4, 513-517, 2007.
doi:10.1109/LGRS.2007.900735        Google Scholar

2. Li, L. L., W. J. Zhang, and F. Li, "A novel autofocusing approach for real-time through-wall imaging under unknown wall characteristics," IEEE Transactions on Geoscience and Remote Sensing, Vol. 48, No. 1, 423-431, 2010.
doi:10.1109/TGRS.2009.2024686        Google Scholar

3. Li, H. Q., G. L. Cui, L. J. Kong, et al. "Robust human targets tracking for MIMO through-wall radar via multi-algorithm fusion," IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol. 12, No. 4, 1154-1164, 2019.
doi:10.1109/JSTARS.2019.2901262        Google Scholar

4. Chen, P. H. and R. M. Narayannan, "Shifted pixel method for through-wall radar imaging," IEEE Transactions on Antennas and Propagation, Vol. 60, No. 8, 3706-3716, 2012.
doi:10.1109/TAP.2012.2201105        Google Scholar

5. Ahmad, F., Y. M. Zhang, and M. G. Amin, "Three-dimensional wideband beamforming for imaging through a single wall," IEEE Geoscience and Remote Sensing Letters, Vol. 5, No. 2, 176-179, 2008.
doi:10.1109/LGRS.2008.915742        Google Scholar

6. Zhang, W. J., A. Hoorfar, C. Thajudeen, and F. Ahmad, "Full polarimetric beam-forming algorithm for through-the-wall radar imaging," Radio Science, Vol. 46, RS0E16-1-RS0E16-17, 2011.        Google Scholar

7. Zhang, W. J., A. Hoorfar, and Q. H. Liu, "Three dimensional imaging of targets behind multi-layered walls," IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting (APSURSI), 1-2, Chicago, 2012.        Google Scholar

8. Solimene, R., F. Soldovieri, G. Prisco, and R. Pierri, "Three-dimensional through-wall imaging under ambiguous wall parameters," IEEE Transactions on Geoscience and Remote Sensing, Vol. 47, No. 5, 1310-1317, 2009.
doi:10.1109/TGRS.2009.2012698        Google Scholar

9. Solimene, R., F. Soldovieri, G. Prisco, and R. Pierri, "3D microwave tomography by a 2D slice based reconstruction algorithm," IEEE Geoscience and Remote Sensing Letters, Vol. 4, No. 4, 556-560, 2007.
doi:10.1109/LGRS.2007.900741        Google Scholar

10. Wang, Y. Z. and A. E. Fathy, "Advanced system level simulation platform for three-dimensional UWB through-wall imaging SAR using time-domain approach," IEEE Transactions on Geoscience and Remote Sensing, Vol. 50, No. 5, 1986-2000, 2012.
doi:10.1109/TGRS.2011.2170694        Google Scholar

11. Wolf, E., "Three-dimensional structure determination of semi-transparent objects from holography data," Optics Communications, Vol. 1, No. 4, 153-156, 1969.
doi:10.1016/0030-4018(69)90052-2        Google Scholar

12. Zhang, W. J. and A. Hoorfar, "Three-dimensional real-time through-the-wall radar imaging with diffraction tomographic algorithm," IEEE Transactions on Geoscience and Remote Sensing, Vol. 51, No. 7, 4155-4163, 2013.
doi:10.1109/TGRS.2012.2227059        Google Scholar

13. Zhang, H. M., Z. B. Wang, Z. H. Wu, F. F. Wang, and Y. R. Zhang, "Real-time through-the-wall radar imaging under unknown wall characteristics using the least-squares support vector machines based method," Journal of Applied Remote Sensing, Vol. 10, No. 2, 020501-1-020501-8, 2016.        Google Scholar

14. Huang, G. B., Q. Y. Zhu, and C. K. Siew, "Extreme learning machine: a new learning scheme of feedforward neural networks," IEEE International Joint Conference on Neural Networks, 985-990, 2004.        Google Scholar

15. Huang, G. B., Y. Lan, and D. H. Wang, "Extreme learning machines: A survey," International Journal of Machine Learning and Cybernetics, Vol. 2, No. 2, 107-122, 2011.
doi:10.1007/s13042-011-0019-y        Google Scholar

16. Huang, G. B., "An insight into extreme learning machines: random neurons, random features and kernels," Cogn Comput, Vol. 6, 376-390, 2014.
doi:10.1007/s12559-014-9255-2        Google Scholar