In this paper, a detection method of infrared dim target under ground-sky background is proposed. In view of the situation that there are more edges under the ground-sky background, the top-hat and median filtering algorithm are used for preliminary processing, and a large number of boundaries are estimated by combining Laplacian operator and Canny operator, and then the difference is made to eliminate the influence of boundary on detection, leaving some suspected target points. Finally, a lightweight convolution neural network is used to determine the suspected target points, and the regression problem of the target position is simplified to a binary classification problem. The experimental results show that the proposed algorithm has higher detection probability and lower false alarm rate than the traditional infrared small target detection algorithm under the ground-sky background, and has good detection effect
|