SAR Target Recognition Preprocessing Based on Reconfigurable Computing Architecture

Synthetic aperture radar (SAR) is widely used in various military and civilian fields due to its advantages such as high resolution, strong penetration and all-weather working ability. With the development of SAR imaging technology, the quantity of SAR image data continues to increase, which puts higher requirements on data processing capabilities. Moreover, the lightweight and miniaturized design of radar systems is the future development trend. Traditional computing models can no longer meet the above development needs, and new solutions are urgently needed. The SAR raw image contains a large amount of coherent speckle noise, which requires preprocessing to ensure the accuracy of subsequent target recognition. In order to solve the above problems, this paper implements the preprocessing of SAR target recognition based on coarse-grained reconfigurable array (CGRA). Experimental results show that compared with the implementation based on the most advanced FPGA, the proposed architecture has greatly improved energy efficiency.