NLEBS: Automatic target detection using a unique nonlinear-enhancement-based system in IR images

A new automatic target detection method for IR images that only requires in formation about the size of the targets is described. The. proposed nonline ar-enhancement-based system (NLEBS) algorithm is based on a nonlinear enhan cement paradigm that increases the contrast of the targets with minimal cha nge in the clutter's contrast. The NLEBS employs several stages of processi ng, each with a different operational purpose. First, the nonlinear enhance ment operation is performed by using an iterative procedure. After binariza tion, segmentation merging causes each local image region to grow by fillin g in holes. Then segmentation pruning is applied to remove spurious segment s. Finally, a heuristic-based metric is employed to validate the possible t argets. The performance of the NLEBS was tested with a targe set of IR imag es. The results of these experiments showed a probability of detection grea ter than 90% and a false-alarm rate of about 1 false alarm per image. (C) 2 000 Society of Photo-Optical Instrumentation Engineers.