Target Detection by Eliminating Cluttered Backgrounds in Infrared Images

In this paper, we propose a method of target detection in IR(Infrared) images. In order to effectively detect target regions, the spatial information of the target is first considered by analyzing the pixel distributions of horizontal and vertical projections. Through analyzing the distributions, the target region is detected by eliminating various backgrounds such as noises and clutters. In order to effectively detect the target region, a novel thresholding method is proposed. As experimental results, the proposed method has achieved better performance than the existing methods.