Small and Dim Target Detection Under Strong Clutter Based on Similarly of Gaussian and Motion Outlier Significance Using Moving Infrared Camera

The detection of small and dim targets in cluttered environments remains a significant challenge. The similarity in spatial and temporal characteristics between strong clutter and small targets presents considerable difficulty for existing methods attempting to distinguish them. This article proposes a method for detecting small and dim targets in a strong clutter environment when an infrared (IR) camera is in motion, based on the similarity of Gaussian and motion outlier significance (SOG-MOS). Initially, the weighted average multidimensional derivative (WAMD) and SOG are employed to select suspected dots. Subsequently, adaptive observable filtering based on residual analysis facilitates the correlation of suspected dots having the Markov property. Then, the camera global motion (CGM) equation and the target local motion (TLM) equation are derived from the projection relationship and available trajectory data. Ultimately, the true target is segmented based on the motion outlier significance (MOS) of clutter and target. Experimental results demonstrate that the method outperforms existing state-of-the-art techniques in terms of detection robustness.