An infrared maritime target detection algorithm applicable to heavy sea fog

Infrared maritime images taken in heavy sea fog (HSF) are usually nonuniform in brightness distribution and targets in different region have significant differences in local contrast, which will cause great difficulty for normal target detection algorithm to remove background clutters and extract targets. To this problem, this paper proposes a new target detection algorithm based on image region division and wavelet inter-subband correlation. This algorithm will firstly divide the original image into different regions by an adaptive thresholding method OTSU. Then, wavelet threshold denoising is adopted to suppress noise in subbands. Finally, the real target is extracted according to its inter-subband correlation and local singularity in original image. Experiment results show that this algorithm can overcome the brightness nonuniformity and background clutters to extract all targets accurately. Besides, target's area is well retained. So the proposed algorithm has high practical value in maritime target search based on infrared imaging system.