TOMOGRAPHIC IMAGE BASED PAVEMENT CONDITION ASSESSMENT USING MACHINE LEARNING APPROACH

Abstract

The tomography is an emerging method of nondestructive concrete pavement diagnostics which can be used for improved quality assurance/quality control during concrete pavement construction and assist in rehabilitation decision making Pavement condition assessment provides information to make more cost-effective and consistent decisions regarding management of pavement network. Generally, pavement distress inspections are performed using sophisticated data collection vehicles and/or foot-on-ground surveys. In either approach, the process of distress detection is human-dependent, expensive, inefficient, and/or unsafe. Automated pavement distress detection via road images is still a challenging issue among pavement researchers and computer-vision community. In recent years, advancement in machine learning has enabled 

researchers to develop robust tools for analysing pavement tomographic images at unprecedented accuracies. Nevertheless, machine learning models necessitate big ground truth dataset, which is often not readily accessible for pavement field. In number google street-view images were extracted, images from Mumbai-Pune expressway, Dehu road were extracted manually annotated for classification. Afterward, YOLO (you look only once) machine learning framework was implemented to train the model using the labeled dataset of Indian road. In the current study, the model is use to classify the distresses and quantify their severity simultaneously. Various pavement condition indices are developed by implementing various machine learning algorithms using the YOLO machine learning framework for distress classification segmentation and distress densification. The output of the distress classification and segmentation models are used to develop a comprehensive pavement condition tool which rates each pavement Tomographic images according to the type and severity of distress extracted. As a result, we are able to avoid over-dependence on human judgement throughout the pavement condition evaluation process. The outcome of this study could be conveniently employed to evaluate the pavement conditions during its service life and help to make valid decisions for rehabilitation or reconstruction of the roads at the right time.