Abstract:In order to solve the problem that the infrared target image localization algorithm is susceptible to interference and the positioning accuracy is easy to be affected, and according to the gray target distribution of the infrared target in image, a high precision positioning method of infrared target image based on multi-centroid is proposed based on the requirement of measurement target location in the infrared target image. Through the clustering of each gray scale’s centroid, the influence of the measurement image noise and the non-equilibrium of the background gray scale is successfully avoided, which effectively improves the positioning accuracy of the centroid positioning algorithm. The experimental results show that the method has high positioning accuracy, strong anti - noise ability, high efficiency and easy implementation, and it has been applied in practical image measurement.