Demonstration of a fully neural network based synthetic aperture radar processing pipeline for image formation and analysis

2021 ◽  
Author(s):  
Andrew Rittenbach ◽  
John Paul Walters
Keyword(s):  
Neural Network ◽  
Synthetic Aperture Radar ◽  
Image Formation ◽  
Synthetic Aperture ◽  
Processing Pipeline ◽  
Aperture Radar

Compact acousto-optic system for real-time synthetic aperture radar image formation

1998 ◽  
Author(s):  
Michael W. Haney ◽  
Marc P. Christensen ◽  
Robert R. Michael, Jr. ◽  
Peter A. Wasilousky ◽  
Dennis R. Pape
Keyword(s):  
Synthetic Aperture Radar ◽  
Real Time ◽  
Image Formation ◽  
Synthetic Aperture Radar Image ◽  
Radar Image ◽  
Synthetic Aperture ◽  
Optic System ◽  
Aperture Radar

scholarly journals A Fourier-Based Image Formation Algorithm for Geo-Stationary GNSS-Based Bistatic Forward-Looking Synthetic Aperture Radar

Sensors ◽  
2019 ◽  
Vol 19 (9) ◽  
pp. 1965 ◽  
Author(s):  
Zhangfan Zeng ◽  
Zhiming Shi ◽  
Sainan Xing ◽  
Yongcai Pan
Keyword(s):  
Synthetic Aperture Radar ◽  
Spatial Resolution ◽  
Information Acquisition ◽  
Image Formation ◽  
Synthetic Aperture ◽  
Research Perspective ◽  
Information Gap ◽  
High Level ◽  
Aperture Radar ◽  
Forward Looking

A Geo-Stationary GNSS-based Bistatic Forward-Looking Synthetic Aperture Radar (GeoSta-GNSS-BFLSAR) system is a particular kind of passive bistatic SAR system. In this system, a geo-stationary GNSS is used as the transmitter, while the receiver is deployed on a moving aircraft, which travels towards a target in a straight line. It is expected that such a radar system has potential for self-landing, self-navigation and battlefield information acquisition applications, etc. Up to now, little information from a research perspective can be found about GeoSta-GNSS-BFLSAR systems. To address this information gap, this paper proposes a preliminary image formation algorithm for GeoSta-GNSS-BFLSAR. The full details of the mathematical derivation are given. It is highlighted that, to overcome the long dwell time and spatial variance of GeoSta-GNSS-BFLSAR, a modified migration correction factor must be designed. In addition, the system performances and technical limitations of GeoSta-GNSS-BFLSAR such as focusing depth and spatial resolution are analytically discussed. In the end, a set of simulations including the image formation algorithm, focusing depth and spatial resolution were conducted for verification. It is demonstrated that the focusing performances of the proposed algorithm have a high level of similarity with the theoretical counterparts. This article thus proves the feasibility of GeoSta-GNSS-BFLSAR systems from a simulation level and establishes a foundation for the real applications of such a radar scheme in the future.

scholarly journals Combined Use of GF-3 and Landsat-8 Satellite Data for Soil Moisture Retrieval over Agricultural Areas Using Artificial Neural Network

2018 ◽  
Vol 2018 ◽  
pp. 1-11 ◽  
Author(s):  
Qingyan Meng ◽  
Linlin Zhang ◽  
Qiuxia Xie ◽  
Shun Yao ◽  
Xu Chen ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Soil Moisture ◽  
Synthetic Aperture Radar ◽  
Synthetic Aperture ◽  
Landsat 8 ◽  
Combined Use ◽  
Artificial Neural ◽  
Agricultural Areas ◽  
Aperture Radar

Soil moisture is the basic condition required for crop growth and development. Gaofen-3 (GF-3) is the first C-band synthetic-aperture radar (SAR) satellite of China, offering broad land and ocean imaging applications, including soil moisture monitoring. This study developed an approach to estimate soil moisture in agricultural areas from GF-3 data. An inversion technique based on an artificial neural network (ANN) is introduced. The neural network was trained and tested on a training sample dataset generated from the Advanced Integral Equation Model. Incidence angle and HH or VV polarization data were used as input variables of the ANN, with soil moisture content (SMC) and surface roughness as the output variables. The backscattering contribution from the vegetation was eliminated using the water cloud model (WCM). The acquired soil backscattering coefficients of GF-3 and in situ measurement data were used to validate the SMC estimation algorithm, which achieved satisfactory results (R2 = 0.736; RMSE = 0.042). These results highlight the contribution of the combined use of the GF-3 synthetic-aperture radar and Landsat-8 images based on an ANN method for improving SMC estimates and supporting hydrological studies.

Sign in / Sign up

Export Citation Format

Share Document