Design of Multiple Demeaning Filters for Small Target Detection in Infrared Imageries

Abstract

In this paper, we propose multiple demeaning filters for small target detection in infrared (IR) images. The use of a demeaning filter is a promising method which detects a small object by removing the background components with a mean filter. The main factors in the design of a demeaning filter are two types of demeaning methods and the size of its window. We compare two demeaning methods, the sliding window method and the grid method, and we analyze the trade-off between the window size and the performance of the demeaning filters and present limitations related to their use. To overcome the drawbacks of a conventional demeaning filter, the use of multiple demeaning filters with filters of various sizes is considered. The proposed method not only has the advantage of being able to detect a small object in a densely cluttered environment, but it also can be used with low complexity with an integral image. Experimental results demonstrate the robustness and stability of the proposed multiple demeaning filters with low computational complexity compared with conventional methods.