Infrared Small Target Detection Using Two-Dimensional Least Mean Square Filter Based on Neighborhood Information

摘要

This chapter proposes an infrared small target detection algorithm using two-dimensional least mean square (TDLMS) filter based on neighborhood information. The structure of the TDLMS filter and prediction method is improved to make full use of neighborhood information of the predicted pixel, and the background is predicted using a nonlinear step adjustment method to improve the prediction accuracy. Experimental results show that the background can be effectively suppressed, and the detection rate of infrared small target is improved if the background is predicted by the TDLMS filter based on neighborhood information.