Infrared small target detection based on salient region extraction and gradient vector processing

Abstract

Infrared small target detection plays a significant role in modern infrared search and track systems(IRST) and has also received much attention. Based on this background, a novel approach to detect infrared small target based on salient region extraction (SRE) and gradient vector processing (GVP) is proposed in this paper. This approach consists of three parts: pre-processing based on fast median filtering, SRE based on spectral residual algorithm (SRA) processing and similarity analysis algorithm (SAA) processing, and target detection in infrared gradient vector field (IGVF). Both theory and experimental have shown that the proposed algorithm can detect the target more robustly and accurately, and spend less time processing compared with the existing infrared small target detection algorithm. It is a small infrared target detection method with superior performance and good application prospect.