An Infrared Small Target Fast Detection Algorithm in the Sky Based on Human Visual System

摘要

In order to solve the problem of poor real-time performance of traditional algorithms and high false alarms when there are complicated cloud disturbances in the scene, this paper proposed an infrared small target fast detection algorithm in the sky based on the human visual system. At first, a local contrast measurement method with single scale was proposed to quickly calculate candidate targets. Then, the Laplace Gaussian scale space theory is introduced to calculate the multi-scale filter response of the candidate targets. According to the difference of the statistical characteristics of the response value, the real target is obtained through adaptive threshold segmentation. Experimental results show that the proposed method has a detection rate of up to 97%, and a false alarm rate of lower than 3%, and our method can calculate the target position within 5ms for a 256×200 image.