Small target detection based on difference accumulation and Gaussian curvature under complex conditions

• Published in: Infrared physics & technology Vol. 87; pp. 55 - 64
• Main Authors: Zhang, He, Niu, Yanxiong, Zhang, Hao
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.12.2017
• Subjects: Clustering; Different accumulation; Gaussian curvature; Small target detection; Small target detection; Different accumulation; Clustering; Gaussian curvature
• ISSN: 1350-4495; 1879-0275
• DOI: 10.1016/j.infrared.2017.08.016

•We propose a new method for small target detection under complex conditions.•Multi-scale neighborhood clustering is applied to remove heterogeneous region.•Small target can be separated from homogeneous region by Gaussian curvature. Small target detection is a significant subject in infrared search and track and other photoelectric imaging systems. The small target is imaged under complex conditions, which contains clouds, horizon and bright part. In this paper, a novel small target detection method is proposed based on difference accumulation, clustering and Gaussian curvature. Difference accumulation varies from regions. Therefore, after obtaining difference accumulations, clustering is applied to determine whether the pixel belongs to the heterogeneous region, and eliminate heterogeneous region. Then Gaussian curvature is used to separate target from the homogeneous region. Experiments are conducted for verification, along with comparisons to several other methods. The experimental results demonstrate that our method has an advantage of 1–2 orders of magnitude on SCRG and BSF than others. Given that the false alarm rate is 1, the detection probability can be approximately 0.9 by using proposed method.