Abstract
In this paper, a SAR target recognition method is proposed based on the improved joint sparse representation (IJSR) model. The IJSR model can effectively combine multiple-view SAR images from the same physical target to improve the recognition performance. The classification process contains two stages. Convex relaxation is used to obtain support sample candidates with the l1-norm minimization in the first stage. The low-rank matrix recovery strategy is introduced to explore the final support samples and its corresponding sparse representation coefficient matrix in the second stage. Finally, with the minimal reconstruction residual strategy, we can make the SAR target classification. The experimental results on the MSTAR database show the recognition performance outperforms state-of-the-art methods, such as the joint sparse representation classification (JSRC) method and the sparse representation classification (SRC) method.
Highlights
Synthetic aperture radar (SAR) is a high-resolution imaging radar
4.2 Experimental results and discussions To demonstrate the performance, our proposed improved JSR classification (IJSRC) algorithm is compared with the state-of-the-art methods, Table 2 The support sample indexes of five samples with greatly different azimuths
An improper low-rank matrix is generated by IJSRC, which leads to a bad recognition
Summary
Synthetic aperture radar (SAR) is a high-resolution imaging radar. It can work regardless of climatic circumstances and time constraint. It is widely applied in kinds of military and civilian areas such as disaster assessment, resource exploration, and battlefield reconnaissance. SAR target recognition plays an important role in the automatic analysis and interpretation of the SAR image data. Over the past several decades, lots of algorithms are exploited in SAR target recognition [1-3], it is a challenging issue due to the complexity of the measured information such as speckle noises, variation of azimuth, and poor visibility. There is still no commonly agreed-upon system that settles SAR target recognition so far
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
