An Efficient Infrared Small Target Detection Method Based on Visual Contrast Mechanism

Robust and efficient detection of an infrared (IR) small target is very important in the IR search and track system. Based on the contrast mechanism of the human visual system, an IR small target detection method with high detection rate, low false alarm rate, and short processing time is proposed in this letter. This method consists of two stages. At the first stage, with the top-hat filter and an adaptive threshold operation based on the constant false alarm rate applied to the original image, the suspicious target regions are obtained. In this way, the computing time of the following steps would be reduced a lot; meanwhile, the desired and predictable detection probability with the constant false alarm probability is maintained. At the second stage, we first define a new efficient local contrast measure between the target and the background, and the local self-similarity of an image is introduced to calculate the local saliency map. With the combination of the local self-similarity and local contrast, an efficient saliency map is obtained, which cannot only increase the signal-to-clutter ratio but also suppress residual clutter simultaneously. Then, a simple threshold operation on the saliency map is used to get the true targets. Experimental results indicate that the proposed method is superior in detection rate, false alarm rate, and processing time compared with the contrast algorithms, and it is an efficient method for IR small target detection in a complex background.