Infrared small target detection based on local average contrast enhancement and corner response

Infrared (IR) small target detection plays an important role in the field of target detection. However, due to the small IR target texture feature is not obvious, low signal-to-noise ratio, strong clutter interference and other reasons, the IR small target detection and its challenges. Therefore, this paper designs a robust detection method which can accurately detect IR dim targets in strong background clutter environment. Firstly, the local mean contrast enhancement strategy is used to enhance the target and suppress the background of the IR image, and the influence of isolated noise is eliminated. Then Harris corner detection algorithm is used to calculate the corner response pixel by pixel for the image after contrast enhancement. Finally, a simple threshold segmentation is used to detect the IR dim small target. The experimental results show that our method has excellent detection effect in the case of very low SCR and strong background clutter. At the same time, compared with the existing methods, our method is more robust and has less false alarm rate.