Adaptive Road Crack Detection and Segmentation Using Einstein Operators and ANFIS for Real-Time Applications

A novel approach for road crack detection and segmentation was proposed, incorporating Einstein operators within an Adaptive Neuro-Fuzzy Inference System (ANFIS).This methodology leverages advanced fuzzy aggregation techniques and adaptive mechanisms, combined with dynamic Einstein sum and product operators, to enhance the identification of cracks.The model was designed to effectively manage varying crack intensities, geometries, and noise levels, thereby ensuring high sensitivity and accuracy in real-world road conditions.In the preprocessing stage, robust fuzzification was applied using Gaussian membership functions alongside Einstein operators, which significantly improved feature extraction.The segmentation framework based on ANFIS ensured precise detection and delineation of cracks.The performance of the proposed model was demonstrated through a comparative analysis, showing superior accuracy (95.2%), precision (94.1%), recall (96.4%), and F1-score (95.2%) when compared to state-of-the-art models.Statistical validation was conducted, with p-values < 0.01 for all performance metrics, confirming the reliability and statistical significance of the results.Advanced post-processing techniques, including fuzzy morphological refinement and adjacency matrix-based connectivity analysis, were employed to accurately identify even faint or disconnected cracks.The proposed method exhibits exceptional resilience to environmental variations, offering a reliable and adaptive solution for road maintenance and monitoring.This work highlights the potential of fuzzy logic, statistical validation, and adaptive mechanisms in addressing realworld challenges in road crack detection.