We propose an improved segmentation algorithm to extract an object from a forward-looking infrared (FLIR) image. The observed FLIR images are considered to be made up of three stochastic models. The first model is in charge of the noise component and is assumed to be independent Gaussian. The labeling of two regions (i.e., the object and the background) in the second model should obey the Gibbs random field (GRF). Finally, we adopt a population parameter to represent the ratio of the size of the object to that of the background. The population parameter eases the tendency to produce similar-sized segmentations. Establishing the stochastic models, we incorporate maximum a posteriori (MAP) estimation to determine the region labels. The optimization of the MAP criterion is achieved by a deterministic relaxation method to converge quickly to a local maximum.