An Infrared Small Target Detection Method Based on Gradient Correlation Measure

Abstract

To overcome the interference of complex background and improve the detection ability of infrared small target under low signal-to-clutter ratio (SCR) scenes, a novel detection method based on gradient correlation measure (GCM) is proposed in this letter. Initially, the infrared gradient vector field (IGVF) of the original image is constructed based on the facet model. Then, a gradient correlation template is designed to distinguish the difference of local gradient between small targets and background. Finally, an adaptive threshold is adopted to extract small targets from background clutter. The proposed GCM method can identify the unique gradient characteristics of small targets. Experimental evaluations prove that the proposed method can achieve higher SCR scores in complex backgrounds. Especially in the scene where the gray contrast of small targets is low, the proposed GCM method shows a more robust detection performance.