Assessment of crack severity of asphalt pavements using deep learning algorithms and geospatial system

Abstract

Applications of Artificial Intelligence (AI), Deep Learning (DL), and Machine Learning (ML) are becoming common in the field of civil and infrastructure engineering. This paper proposes an innovative asphalt pavement health monitoring framework based on state-of-the-art deep learning algorithms, a convenient data collection strategy, a novel crack width calculation algorithm, and a novel geolocation-based crack visualization method. Furthermore, this paper introduces a 2000-image (1440 × 1440) dataset for crack classification, an 8000 image dataset (360 × 360) dataset and another dataset with manually segmented images. Transfer learning based DL model achieved a validation accuracy of 99%. A novel crack width calculation algorithm is proposed based on the skeletonization and gradient calculation on binary images to quantify the severity of the crack. Locations of the cracked surface positions were identified using geotagged images, and a geospatial mapping method was proposed to visualize the crack locations for health monitoring and maintenance purposes.