Space-time-based Detection of Infrared Small Moving Target

Abstract

ABSTRACT With the development of infrared monitoring and early warning system, more and more attention has been paid to the research of infrared small target detection. How to effectively detect the target in a complex background has always been a major challenge for researchers. This paper presents a space-time-based detection for small infrared target, which can improve the performance of infrared small target detection system. Firstly, the targets are enhanced and the background clutter is suppressed by the morphological filter. Then, the segmentation images method is proposed to erase the majority noises, which calculates an adaptive thresholds based on the constant false alarm rate (CFAR). Finally, a dynamic detection is proposed to erase all of the noises in the multi-frame, which adjust the size and position of the search window based on the kinematic rule of targets. Experimental results show that this technology can effectively detect the small infrared target with high performance.