Infrared point target detection based on multi-label generative MRF model

Infrared point target detection based on markov random field (MRF) is mainly formulated as a binary classification problem, leading to a poor adaptability to complex background with high false alarm rate. This paper formulates the infrared point target detection as a multi-classification problem, and proposes a detection method based on multi-label generative MRF (MG-MRF) model. First, the MG-MRF model is proposed and the optimal label configuration of the infrared image is derived using iterated condition mode (ICM). Second, the pointwise adaptive filter is structured utilizing local labels to suppress the background clutter. Finally, an adaptive threshold is utilized to segment the target in the residual image. The experimental results on various backgrounds demonstrate that the detection method based on MG-MRF has a strong suppression of false alarm with superior performance in terms of accuracy and efficiency.