Detection of infrared small target based on background subtraction local contrast measure and Gaussian structural similarity

• DOI: 10.1016/j.heliyon.2023.e16998
• Publication Date: 2023-06-05T05:52:32Z
• Authors: Deyan Zhu; Junwei Tang; Xiaoxuan Fu; Yuanchao Geng; Jingqin Su
• Keywords: Robustness; Similarity (geometry); Subtraction; Similarity measure; False alarm

Infrared (IR) small target detection, especially in a complex background, continues to present challenges the low false alarm rate and high robustness. In this paper, background subtraction local contrast measure (BSLCM) Gaussian structural similarity (GSS) integrated model is proposed detect IR target. model, BSLCM used suppress enhance GSS calculation conducted eliminate high-brightened residual noise further. To evaluate performance of method, real sequences seven state-of-the-art (SOTA) methods were adopted. The results demonstrated that can all types strong clutter true effectively.