Infrared Small Target Detection Based on the Weighted Double Local Contrast Measure Utilizing a Novel Window

Abstract

One of the integral parts of the infrared search and tracking (IRST) system is the infrared small target detection. To facilitate the detection of infrared small targets in complex backgrounds, infrared small target detection based on the weighted double local contrast measure (WDLCM) utilizing a novel window detection framework is proposed. First, a novel window is designed to measure the weighted double local contrast. Second, a double local contrast measure (DLCM) is proposed to enhance the region of infrared small targets in infrared images. It consists of the local contrast between the target region and surrounding background region and that within the target region. Then, a weighting function (W) is established to further enhance targets and suppress surrounding backgrounds by exploiting the variance of the target region, the standard deviation of the surrounding background region, and the difference variance between the target region and surrounding background region. Finally, after obtaining a WDLCM saliency map, adaptive threshold segmentation will be employed in order to capture real targets. The experimental results on different scene datasets show that the proposed method has a high detection rate, a low false alarm rate and good real-time performance compared with existing methods.