The invention discloses an infrared target detection method based on a Bayesian saliency map calculation model, in particular to an infrared target detection method based on a visual attention mechanism, belonging to the technical field of computer vision. The method comprises the follow steps: based on the Bayesian theorem, calculating the prior probability and the likelihood probability of the infrared image to establish a saliency map calculation model base on the Bayesian theorem; solving a prior probability based on the meanshift segmentation algorithm and side suppression; solving the likelihood probability based on pixel point statistics; based on the priori probability and likelihood probability, calculating the final saliency map and obtaining the infrared target detection results. The invention realizes infrared target detection based on a Bayesian saliency map calculation model, and has the advantages of strong background noise suppression ability and clear and complete salient area outline.