Segmentation of FLIR Images Based on Background Suppression

Image segmentation is the most important key in tracking processing of infrared imaging precise guidance. For the segmentation of forward-looking infrared (FLIR) images, a new method was proposed, which uses Wiener filter to suppress background and enhance target, then uses the C-V model to perform segmentation. The C-V model was improved on segmentation ability and precision. A new energy constructing method was proposed that using multi-characteristic information to divide homogeneity region in image. Experimental result shows that the presented method can more effectively and integrally extract the target than the method of traditional C-V model under low contrast condition, and reduce the influence of background greatly.