Infrared ship target segmentation based on region and shape features

We explore problem of ship target segmentation in infrared (IR) images, and propose an efficient method. The method consists of two procedures: first, based on the intensity properties of target and background region, we design a global background subtraction filter (GBSF) to suppress the background, and an adaptive row mean subtraction filter (ARMSF) to enhance the target. By iteratively applying the two filters, the target region could be separated from the background. Then, considering shape features of the ship targets, we propose a target selection method to get the final ship target. Experimental results show that, the presented method could effectively segment ship targets from IR images with different sea background. It performs better in both the visual and quantitative comparisons, especially for IR images with low contrast.