Infrared Small-Target Detection Based on Multi-level Local Contrast Measure

Abstract

Infrared small target detection technology is one of the key technologies for reconnaissance, guidance, and early warning systems, and it has important theoretical and practical value to conduct in-depth research on it. However, there are several challenges in infrared small target detection. Firstly, infrared small targets have low signal-to-noise ratio, which makes them easily submerged in complex backgrounds. Secondly, since infrared small target detection is a long-distance imaging process, there is no shape or texture information available, which increases the difficulty of target detection. To address these challenges, this paper proposes a multi-level contrast enhancement method to suppress structural background, and develops a more effective detection algorithm. Based on the concept of local contrast measurement (LCM), a new contrast-based small target detection algorithm called Multi-Level Local Contrast Measurement (MLLCM) is constructed, and its effective implementation process is provided. Compared with LCM, MPCM (Multiscale Patch-based Contrast Measure), and other algorithms, this algorithm effectively enhances the target area and eliminates background clutter. The results on simulated images demonstrate the effectiveness of this algorithm.