Suboptimal threshold estimation for detection of point-like objects in radar images

Abstract

There are many methods for detection of point-like features in gray-leveled bitmap images. The problem of defining a threshold for acceptance or rejection of the results is usually neglected or left to experts. In this paper, a novel method of estimating suboptimal detection threshold values is proposed. It is based on overlapping the results of two or three different methods parametrized with respective thresholds. The quality functions (of two or three variables), whose global extrema (maximum) approximately correspond to the suboptimal levels of thresholds for the used methods, are defined. This method was applied to a series of the bitmaps generated by a radar sensor and by simulated bitmaps.