Specific Target Contour Extraction Method for Color Images Based on Priori Information-Assisted Dual-Threshold Binary Segmentation

To meet the need for attacking against specific targets, the patrol missile should have some target identification capability to facilitate comparison and targeting of the plotted target contour with the on-board data. For the problem of recognition and capture of specific targets, based on computer vision technology, this paper proposes a method for extracting target contours of color images based on priori information assisted dual-threshold binary segmentation with the ability to recognize and extract specific target contours. Through the experiments conducted on this contour extraction method in natural and artificial environments, it is proved that the method has high accuracy and applicability for the contour extraction of specific targets, and can provide an identification method for patrol missiles to attack specific targets.