Small target detection in the clutter infrared image is a tough but significant work. In this paper, we will propose a novel
small target detection method. First, Graph Laplacian regularization is utilized to model similarity feature of graph
structure in the image. And Graph Laplacian regularization is incorporated in the background estimation model to
preserve edges of background in single frame infrared image. At last, the edge-preserving estimated background is
eliminated from original image to get foreground image which is used to detect the small target. Experimental results
show that our proposed method can achieve edge-preserving estimation of background, suppress clutter efficiently, and
get better detection results.
In this paper, a new procedure based on least trimmed square for clutter background estimation is proposed. Least trimmed square method identifies multiple outliers in the image, such as noise and target region. Then the clutter background is estimated without these outliers. The performance of this method is compared with the algorithms based on least mean square method, the results show that our method gets higher signal clutter ratio (SCR) gain in target region than other methods which use LMS filter.