Improving Efficiency of Microwave Wideband Imaging using Compressed Sensing Techniques

A compressed sensing technique was developed for wideband microwave synthetic aperture radar (SAR) imaging techniques, particularly suitable for nondestructive testing applications. This technique helps to significantly reduce the number of spatial measurement points, and consequently the acquisition time, by sampling below the Nyquist-Shannon rate. The reduced measurement data are processed to reconstruct SAR images via basis pursuit and orthogonal matching pursuit using discrete cosine transform sparse representation. Benefiting from a reduced number of samples, this paper proposes two scanning procedures, namely non-uniform raster and optimum path. Two sets of experiments were conducted to show the performance of the proposed technique. The first set of experiments was performed on a 120 x 180 mm(2) area with thin rubber and copper patches placed on foam posts in the 18 to 26.5 GHz frequency band (K-band) using conventional raster scanning and the proposed compressed sensing sampling techniques. Conventional raster scanning with a step size of 2 mm requires 2947 s to measure the 5551 points. In contrast, the proposed compressed sensing technique, measuring 20% of random spatial points uniformly selected from the full dataset, requires only 1020 s of scanning to achieve comparable quality. Another set of experiments was performed on a corrosion underpaint sample. The results of this experiment show that it is possible to detect the corrosion by measuring only 20% of the full dataset. This paper describes the compressed sensing algorithm as well as the measurement technique and the obtained results.