Automated real-time pavement distress detection using fuzzy logic and neural networks

Conventional visual and manual pavement distress analysis approaches are very costly, time-consuming, dangerous, labor-intensive, tedious, subjective, having high degree of variability, unable to provide meaningful quantitative information, and almost always leading to inconsistencies in distress detail over space and across evaluations. in this paper, a novel system for multipurpose automated real-time pavement distress analysis based on fuzzy logic and neural networks will be studied. The proposed system can: provide high data acquisition rates; effectively and accurately identify the type, severity and extent of surface distress; improve the safety and efficiency of data collection; offer an objective standard of analysis and classification of distress; help identify cost effective maintenance and repair plans; provide images and examplers through information highway to other user/researchers; provide image/sample bank for training or as the benchmark for testing new algorithms. The proposed system will reduce the cost for maintenance/repair greatly, and can contribute to other research in pavement maintenance, repair and rehabilitation.