An Efficient Method for Infrared Small Target Detection

The efficient detection of small target in the low SNR image is an important and challenging research task in wide civil and military applications. In this paper, we developed a novel and efficient infrared small target detection method based on gray-scale morphology transform and higher-order statistics. Firstly, most of the image background regions are removed using gray-scale morphology processing. Following by the background suppression, the method proposed in the paper firstly uses higher-order statistics method to locate coarsely the region containing the target. Then, the paper uses polynomial fitting to fit cumulative histogram of the region of interest after background suppression, and the optimal adaptive segmentation threshold is obtained through the dynamic analysis of the slope of polynomial fitting curve. The experimental results show that compared with the traditional detection methods, the proposed method is more effective and faster for infrared small target detection.