Supervised Automatic Detection of UWB Ground-Penetrating Radar Targets Using the Regression SSIM Measure

This letter introduces the concept of regression structural similarity index measure (regression SSIM) and builds a supervised graph framework of automatic detection of small-size ultrawideband (UWB) radar targets. The twofold contribution made in this letter includes the following: 1) The regression SSIM is proposed to measure the similarity of the local pattern between a test image and a reference image; and 2) the framework of a supervised graph, together with the regression SSIM, has been developed to address the automatic detection of UWB radar objects. As opposed to other detection techniques reported in the literature, our methodology does not rely on statistical modeling or imposing typical shape parameters. Selected results of processing simulated and real UWB ground-penetrating radar data are provided, which verifies the state-of-the-art performance of the proposed methodology and provides important potential for a wide class of target detection.