A study on intuitionistic fuzzy generating function using T-Norm, T-Conorm operators to enhance night-time images for autonomous driving system

Abstract

Abstract Enhancing night-time images is crucial for improving the performance of autonomous driving systems, which rely on high-quality visual input for accurate decision-making. This study explores the application of intuitionistic fuzzy generator in combination with T-Norm and T-Conorm operators to enhance low-visibility night-time images. Unlike traditional image processing methods, intuitionistic fuzzy set (IFS) incorporates both the degree of belonging and non-belonging aspects of an image allowing for a more detailed representation of uncertainty in image enhancement. The proposed method analyzes various aggregation operators, out of which Einstein’s T-Norm, Hamacher’s T-Conorm, Weber’s T-Conorm and W-probabilistic T-Conorm operators refine contrast, suppress noise and enhance illumination while preserving critical visual details. Extensive experiments on night-time driving datasets in contrast with existing state-of-the-art methods demonstrate that the recommended approach significantly improves image clarity via standard image quality metrics like SSIM, PSNR and correlation coefficient. Additionally, a sensitivity analysis conducted to assess the robustness and stability of the IFS components and aggregation operators with respect to the parameter $$\Upsilon$$ in validating its effectiveness in diverse low-light conditions. The findings indicate that integrating IFS with some particular T-Norm and T-Conorm operations is an innovative strategy to improve the autonomous vehicle’s perception in low-light conditions.