PROJECT TITLE :

SAR Imaging With Structural Sparse Representation

ABSTRACT:

Sparse illustration (SR)-based SAR imaging approaches have shown their superior performance compared with conventional approaches. However, for a picture with rich spatial structures, a mounted global dictionary is sometimes ineffective to characterize the local structures. Piecewise autoregressive (PAR) model indicates that every pixel will be linearly represented by its local neighboring pixels. Galvanized by this, an adaptive sparse area, effectively characterizing the varying image local structures, is designed, in that the entries are derived from the PAR model. By incorporating the adaptive SR into the SAR imaging, a novel structural SR-primarily based SAR (SSR-SAR) imaging approach is proposed. Because of the actual fact that the adaptive sparse house is greatly passionate about the previous info of the SAR image, updating of the adaptive sparse area and SAR imaging could be a joint optimization downside. In our approach, we have a tendency to propose to introduce the alternative minimization theme to solve the problem. Besides, the Augmented Lagrangian Multiplier technique is adopted to accelerate the computation speed. Finally, experimental results are shown to demonstrate the validity of the proposed approach.