An Adaptive Multi-Stage Fuzzy Logic Framework for Accurate Detection and Structural Analysis of Road Cracks
Journal Title: Mechatronics and Intelligent Transportation Systems - Year 2024, Vol 3, Issue 3
Abstract
The degradation of road infrastructure presents significant challenges to public safety and maintenance budgets, with cracks serving as critical indicators of structural instability. Despite extensive advancements, existing detection methodologies frequently fail to address complex surface textures, variable illumination, and diverse crack geometries, resulting in inconsistent performance. An adaptive, multi-stage framework has been developed to mitigate these limitations, integrating advanced image processing techniques with fuzzy logic-based analysis. The proposed approach utilises dynamic contrast enhancement and multi-scale feature extraction to ensure accurate detection of both fine and extensive cracks across heterogeneous surfaces. A fuzzy graph-based methodology is employed to evaluate crack connectivity, while an adapted algorithm is applied to assess continuity and severity. The framework incorporates fuzzy wavelet transforms to enhance feature segmentation and employs morphological techniques for precise crack boundary delineation. Dijkstra’s algorithm is integrated to optimise connectivity analysis, facilitating the identification of critical structural deficiencies. The performance of the model has been rigorously validated through extensive experimental testing, achieving an accuracy rate of 94.2%, with high precision and recall metrics. Comparative analysis with conventional techniques reveals a significant reduction in false detection rates and an improved capacity for capturing intricate crack features. The results underscore the practical utility of the proposed model, demonstrating its scalability and reliability across diverse roadway conditions. By enabling early and accurate identification of structural anomalies, the framework enhances roadway safety, minimises maintenance costs, and supports proactive infrastructure management. The findings highlight its potential as a transformative solution for addressing modern challenges in road maintenance, with implications for improved public safety and resource optimisation.
Authors and Affiliations
Ibrar Hussain
Keywords
Related Articles
- EP ID EP752439
- DOI -
- Views 28
- Downloads 0
Machine Learning for Road Accident Severity Prediction
In the realm of road safety management, the development of predictive models to estimate the severity of road accidents is paramount. This study focuses on the multifaceted nature of factors influencing accident severity...
Automated Development of Railway Signalling Control Tables: A Case Study from Serbia
The automation of railway signalling control table preparation, a task historically marked by labor-intensity and susceptibility to error, is critically examined in this study. Traditional manual methods of generating th...
An Adaptive Multi-Stage Fuzzy Logic Framework for Accurate Detection and Structural Analysis of Road Cracks
The degradation of road infrastructure presents significant challenges to public safety and maintenance budgets, with cracks serving as critical indicators of structural instability. Despite extensive advancements, exist...
Regional Classification of Serbian Railway Transport System Through Efficient Synthetic Indicator
The railway transport system is one of the most important elements in the development of the economy and the social space of any area. The main objective of the study is to analyse the regional differentiation in railway...
Integrating Cultural Norms and Behavioral Risk Factors into Traffic Accident Mitigation: A Hybrid MCDM Approach for Libya
The mitigation of road traffic accidents remains a critical global challenge, particularly in regions where cultural norms and behavioral risk factors significantly influence driving practices. This study employs a hybri...