Infrared Small Target Detection Using Local Feature-Based Density Peaks Searching

• Published in: IEEE geoscience and remote sensing letters Vol. 19; pp. 1 - 5
• Main Authors: Zhu, Qiang, Zhu, Shuyuan, Liu, Guanghui, Peng, Zhenming
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Density; Density peaks; Detection; Entropy; feature; Feature extraction; Feature maps; fusion; Geoscience and remote sensing; Indexes; infrared small target; local tetra pattern (LTrP); Object detection; Position measurement; Robustness; Searching; Target detection
• ISSN: 1545-598X; 1558-0571
• DOI: 10.1109/LGRS.2022.3157051

In this letter, we propose a new local feature-based method for the detection of infrared small targets with the density feature map that can effectively suppress noise in the feature domain. First, we combine the local tetra pattern (LTrP) and the second-order LTrP to generate the density feature map. Second, we apply density peaks searching to the feature map to obtain candidate targets. Third, we generate two local features, i.e., the entropy and third-order moment, for each image patch whose center is a candidate target and then fuse them to employ the fused feature to find the real target. The experimental results demonstrate that our proposed method achieves better performance compared with the state-of-the-art approaches.