Detection of sea surface small targets in infrared images based on multilevel filter and minimum risk Bayes test

This paper discusses the research in small target detection in infrared ima ges with heavy clutter background. For most infrared images, ship objects a re rather dim in the relative dark sea surface background. The existence of scan line disturbance and noise also increases the difficulty in proper de tection. Dim objects must be distinguished from a dark background. On the o ther hand, the small targets must also be distinguished from clutters. Thro ugh analysis of the targets and background, we build characteristic models of small ship objects, noise and sea backgrounds respectively, and indicate their differences in spatial and frequency domains among them. Based on th e principles of signal processing, pattern recognition and artificial intel ligence, we propose a combined algorithm for detecting sea surface small ta rgets. In this algorithm, components of background and noise are first supp ressed by a multilevel filter designed accordingly, meanwhile enhancing the target ones of interest. The pixels of the candidate targets are then disc riminated by minimum risk Bayes test. Finally, according to a priori knowle dge about the targets such as the ranges of their sizes, the targets of int erest can be detected. In particular, the related probability distributions used by statistic decision are obtained by offline learning of typical tra ining samples. Experiments show that the algorithm is excellent for such ki nds of target detection and is robust to noise.