SAR Ground Moving Target Refocusing by Combining mRe³ Network and TVβ-LSTM
- 9 December 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 60 (01962892) , 1-14
Abstract
This article proposes a novel framework by combining a modified real-time recurrent regression (mRe 3 ) network and a newly designed trajectory smoothing long short-term memory (LSTM) network for refocusing the ground moving target (GMT) in the synthetic aperture radar (SAR) image. The mRe 3 network that consists of a convolutional neural network (CNN) backbone and two LSTM modules is designed to track the GMT’s shadow in an SAR video. Furthermore, we find that the complex trajectory obtained by the tracking network cannot directly be used for refocusing the GMT because of the estimation error. To address the abovementioned problem, a $\beta $ -order total variation loss-based smoothing LSTM (TV ${}^{\beta }$ -LSTM) is proposed to recover the GMT’s trajectory to meet the requirement of refocusing. Besides, the effect of TV ${}^{\beta }$ on the performance of smoothing LSTM is analyzed. By the experiments on simulated and real SAR videos, we find that the mRe 3 has stronger robustness and a better trajectory reconstruction precision compared with the existing tracking methods, especially for the strong interference cases. In addition, the smoothing LSTM can recover the trajectory of the GMT with higher precision and better smoothness. When $\beta $ is set to 3, with the TV ${}^{\beta }$ -LSTM, the center distance error of a recovered complex trajectory can be reduced from 0.82 to 0.782, while its fluctuation can be suppressed from 6 to 1 mm. By using our framework, the focused GMT with bountiful geometrical features can be obtained even for the $K_{a}$ -band SAR.
Keywords
Funding Information
- National Natural Science Foundation of China (61671113)
- National Key Research and Development Program of China (2017YFB0502700)
- Natural Science Fund of China (61501098, 61571099)
This publication has 40 references indexed in Scilit:
- Struck: Structured Output Tracking with KernelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- High-Speed Tracking with Kernelized Correlation FiltersIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- High-Resolution SAR Imaging of Ground Moving Targets Based on the Equivalent Range EquationIEEE Geoscience and Remote Sensing Letters, 2014
- Detection and Imaging of Ground Moving Targets With Real SAR DataIEEE Transactions on Geoscience and Remote Sensing, 2014
- Is my new tracker really better than yours?2014
- ISAR based technique for refocusing non-cooperative targets in SAR imagesIET Radar, Sonar & Navigation, 2012
- Evaluating Multiple Object Tracking Performance: The CLEAR MOT MetricsEURASIP Journal on Image and Video Processing, 2008
- SAR imaging of moving targetsIEEE Transactions on Aerospace and Electronic Systems, 1999
- Long Short-Term MemoryNeural Computation, 1997
- Moving target imaging algorithm for SAR dataIEEE Transactions on Aerospace and Electronic Systems, 1990