Using Phase Symmetry to Detect the Hyperbolic Region In GPR Images

Hyperbolic detection is an important task in the Ground-Penetrating Radar (GPR) images due to the buried targets display the form of hyperbolic and has been researched all the time. The detection of hyperbolic is beneficial to the buried threat detection, classification and environment change detection of GPR images. In this letter, a robust hyperbola detection method for GPR images is presented. A model based on image phase and symmetry information is developed as a detector. The detector solves the problem of hyperbola extraction from GPR images with low physical resolution. As far as we know, the phase symmetry (PS) model is used in this task for the first time and the experimental results show that the effectiveness of the proposed method is better than other methods used in recent researches.