An associative saliency segmentation method for infrared targets

Automatic infrared (IR) target segmentation plays an important role in IR image analysis. Recent works have shown that exploiting visual attention model can improve target segmentation performance in visible images. However, when directly applied to IR images, those methods cannot guarantee the effectiveness due to the low contrast between targets and background, high noise, etc. To address above problem, a novel associative saliency-based visual attention model for IR images is proposed in this paper. First, an IR image is decomposed into assemble of homogeneous regions. With those regions, saliency based on region and edge contrast is constructed, respectively. Then associative saliency, generated from those two kinds of saliency, is used to extract IR target from background. The superiority of the proposed method is examined and demonstrated through a large number of the experiments using IR images.