Infrared small target detection based on morphology and wavelet transform

Aiming at the features of moving small target in infrared sequence dynamic image, this paper presents a small target detection method based on morphology and wavelet transform. Firstly, the image is preprocessed using top-hat transformation to suppress most of the background clutter and enhance the target. Secondly, the image is decomposed by using single-scale wavelet transform and the high frequency components of horizontal and vertical are extracted, then segmented by self-adaptive threshold and fused segmentation image, above all are to get single frame detection results. Finally, the final detection result is obtained by expansion and “and” operation with several single-frame detection results. Simulation results show that the presented algorithm can detect the small target stable and accurately with high detection and low false alarm probability.