An efficient infrared image segmentation method

In order to solve the problem of efficiency of infrared image segmentation, a double threshold and MRF based infrared image segmentation method is proposed in this paper. Firstly, a double-threshold method is used initially, which aims to segment infrared image to get the energy parameters and infrared image´s seeds pixels. Then, MRF framework is used, aiming at building the Graph cuts model and getting the final segmentation. At last, it´s shown that better segmentation results can be got using the proposed method in the experiment, and real-time requirements are met.