Filter design for small target detection on infrared imagery using normalized-cross-correlation layer

Abstract

In this paper, we introduce a machine learning approach to the problem of infrared small target detectionfilter design. For this purpose, similar to a convolutional layer of a neural network, the normalized-cross-correlational(NCC) layer, which we utilize for designing a target detection/recognition filter bank, is proposed. By employing theNCC layer in a neural network structure, we introduce a framework, in which supervised training is used to calculatethe optimal filter shape and the optimum number of filters required for a specific target detection/recognition task oninfrared images. We also propose the mean-absolute-deviation NCC (MAD-NCC) layer, an efficient implementation ofthe proposed NCC layer, designed especially for FPGA systems, in which square root operations are avoided for real-timecomputation. As a case study we work on dim-target detection on midwave infrared imagery and obtain the filters thatcan discriminate a dim target from various types of background clutter, specific to our operational concept.