TY - GEN
T1 - SAR Parameter Estimation Method for Rectangle Plane Based on Information Geometry
AU - Wen, Yuhan
AU - Chen, Xinliang
AU - Wei, Yangkai
AU - Fan, Yujie
AU - Zeng, Tao
AU - DIng, Zegang
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/12
Y1 - 2019/12
N2 - After establishing scattering models, the traditional synthetic aperture radar (SAR) parameter estimation methods usually utilize vanilla gradients to estimate target parameters from SAR echoes or images. However, the vanilla gradients will lead to lower iteration efficiency. Hence, in this paper, to take the rectangle plane as an example, we propose a SAR parameter estimation method based on the information geometry (SPEM-IG) to solve the above problem. The SPEM-IG adopts the natural gradient to estimate the parameters based on the information geometry optimization algorithm. The central objective of SPEM-IG is to project the least square function into probability distribution space and find the optimal solution in the new parameter space. In order to reduce the computational complexity caused by the multi-peak feature of least squares function, SPEM-IG utilizes the range of parameters rather than its exact value in calculating the value of least squares function, and takes the optimal solution in this range as the result of the current iteration process. By considering the geometric structure of manifolds, SPEM-IG calculates the optimal gradient direction called natural gradient to obtain faster convergence rate. The experimental results show that the SPEM-IG is effective for estimating target parameters. Besides, SPEM-IG has good performance even at low signal-to-noise ratios of SAR images.
AB - After establishing scattering models, the traditional synthetic aperture radar (SAR) parameter estimation methods usually utilize vanilla gradients to estimate target parameters from SAR echoes or images. However, the vanilla gradients will lead to lower iteration efficiency. Hence, in this paper, to take the rectangle plane as an example, we propose a SAR parameter estimation method based on the information geometry (SPEM-IG) to solve the above problem. The SPEM-IG adopts the natural gradient to estimate the parameters based on the information geometry optimization algorithm. The central objective of SPEM-IG is to project the least square function into probability distribution space and find the optimal solution in the new parameter space. In order to reduce the computational complexity caused by the multi-peak feature of least squares function, SPEM-IG utilizes the range of parameters rather than its exact value in calculating the value of least squares function, and takes the optimal solution in this range as the result of the current iteration process. By considering the geometric structure of manifolds, SPEM-IG calculates the optimal gradient direction called natural gradient to obtain faster convergence rate. The experimental results show that the SPEM-IG is effective for estimating target parameters. Besides, SPEM-IG has good performance even at low signal-to-noise ratios of SAR images.
KW - information geometry
KW - natural gradient
KW - parametric scattering model
UR - http://www.scopus.com/inward/record.url?scp=85091918148&partnerID=8YFLogxK
U2 - 10.1109/ICSIDP47821.2019.9173226
DO - 10.1109/ICSIDP47821.2019.9173226
M3 - Conference contribution
AN - SCOPUS:85091918148
T3 - ICSIDP 2019 - IEEE International Conference on Signal, Information and Data Processing 2019
BT - ICSIDP 2019 - IEEE International Conference on Signal, Information and Data Processing 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2019 IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2019
Y2 - 11 December 2019 through 13 December 2019
ER -