Infrared dim small target detection method based on background prediction and high-order statistics

In this paper, a new method based on background prediction and high-order statistics for infrared dim small target detection is proposed. Firstly, the wavelet filter is introduced to remove the target on image as noise, which could efficiently estimate the distribution of the background image. Secondly, the candidate target components are extracted from the foreground image. Finally, high-order statistics estimation method is used to get the target coordinates range and detect the target. Real images of photoelectric theodolite embedded with dim small targets are used to verify the efficiency of proposed method, and experimental results show effectiveness of our method.