Multi-scale fusion for image enhancement in shield tunneling: a combined MSRCR and CLAHE approach

Abstract Aiming at addressing the complex lighting conditions in shield construction environments and enhancing the contrast of low-light images while preserving image details, this paper presents an image enhancement technique based on multi-scale fusion. The proposed method first duplicates the input image into two copies. Subsequently, the first copy undergoes color and contrast adjustment via the adaptive weighted Retinex algorithm for color restoration (A-MSRCR) algorithm. Meanwhile, the second copy undergoes contrast enhancement and detail preservation by combining Gamma correction and Contrast Limited Adaptive Histogram Equalization (CLAHE). Finally, a normalized weight map is introduced to facilitate multi-scale fusion of the two enhanced images, ensuring an overall enhancement in both contrast and detail. The experimental results show that the proposed method provides better visual quality and objective data than the compared methods. Moreover, it offers valuable support for subsequent recognition and localization tasks.