Infrared Small Target Detection Based on Facet Model and Structure Tensor

Small target in infrared image has small size, low signal-to-noise ratio (SNR), and lack of obvious structure or texture features, which bring great difficulties to target detection. In this paper, a single frame detection method is proposed, which combines the first-order directional derivative of facet model with structural tensor. First, four directional derivatives of the original infrared image are calculated based on facet model. Then, according to the directional derivative feature of the target, the structure tensor eigenvalue matrix is employed to enhance the target and suppress the background clutter. Four salient maps are gained. Finally, the final fusion map is obtained by multiplying the salient maps of all directions. The experimental results show that the performance of the proposed method is better than the other four methods in processing real infrared image.