Single-Pixel Background Modeling Algorithm for Strong Sky Scenes Based on Local Region Spatial Bases

Area of Science:

• Computer Vision
• Signal Processing
• Image Analysis

Background:

• Background suppression is crucial for dim-small target detection.
• Existing methods struggle with low signal-to-noise ratios and complex backgrounds.

Purpose of the Study:

• To develop a novel background modeling algorithm for enhanced dim-small target detection.
• To improve target extraction stability and accuracy in challenging conditions.

Main Methods:

• Introduced Single Pixel Background modeling (SPB).
• Constructs pixel-specific background base functions using local background information.
• Optimally estimates the background of each pixel using these bases.

Main Results:

• SPB effectively separates targets from undulating sky backgrounds at SNR < 1.5 dB.
• Achieved stable and enhanced target detection amidst complex motion.
• Difference images show white noise residuals and significantly enhanced targets.

Conclusions:

• SPB demonstrates superior performance compared to five other algorithms for low SNR target detection.
• The algorithm provides a robust solution for dim-small target detection challenges.