Infrared moving point target detection using a spatial-temporal filter

Abstract

Infrared point target detection technology has widely applications, such as in tracking and surveillance system. In this paper, an moving point target detection method is proposed to detect targets from infrared sequence images. Firstly, a modified spatial-temporal total variation model is proposed for background prediction. Then the subtraction image is obtained by subtracting the predicted background from the corresponding sequence image. Finally, the target can be detected from the result that the product of the subtraction image and a temporal contrast filter. The effectiveness of the modified spatial-temporal filter on infrared moving point targets detection is verified by detecting targets from different infrared sequence images.