According to the characteristic of infrared images, a new automatic fuzzy segmentation method was presented based on genetic algorithm for vehicle target image. Firstly, a region of interest was selected in order to reduce computation cost. Secondly, the region of interest was enhanced by fuzzy algorithm. Thirdly, 2D Maximum Between-cluster Variance algorithm was applied to segment the region of interest. At the same time, the genetic algorithm was combined with 2D MBV to make the calculation faster by its capacity of searching the best answer in a threshold bound. Then we detected fuzzy edge based on shortening width of fuzzy edge. At last, the final segmentation image could be obtained by OR and fill operations for the segmentation region by 2D MBV and the fuzzy edge. Experimental results show that only main body of the tank is segmented from the infrared image by one-dimensional and two-dimensional OTSU method. The new method can segment not only main body of the tank but also fuzzy gun from the infrared image.