Infrared Small-Target Detection Under a Complex Background Based on a Local Gradient Contrast Method

Small target detection under a complex background has always been a hot and difficult problem in the field of image processing. Due to the factors such as a complex background and a low signal-to-noise ratio, the existing methods cannot robustly detect targets submerged in strong clutter and noise. In this paper, a local gradient contrast method (LGCM) is proposed. Firstly, the optimal scale for each pixel is obtained by calculating a multiscale salient map. Then, a subblockbased local gradient measure is designed; it can suppress strong clutter interference and pixel-sized noise simultaneously. Thirdly, the subblock-based local gradient measure and the salient map are utilized to construct the LGCM. Finally, an adaptive threshold is employed to extract the final detection result. Experimental results on six datasets demonstrate that the proposed method can discard clutters and yield superior results compared with state-of-the-art methods.