Deep Learning Frameworks for Pavement Distress Classification: A Comparative Analysis
Preprint
Abstract
Automatic detection and classification of pavement distresses is critical in timely maintaining and rehabilitating pavement surfaces. With the evolution of deep learning and high performance computing, the feasibility of vision-based pavement defect assessments has significantly improved. In this study, the authors deploy state-of-the-art deep learning algorithms based on different network backbones to detect and characterize pavement distresses. The influence of different backbone models such as CSPDarknet53, Hourglass-104 and EfficientNet were studied to evaluate their classification performance. The models were trained using 21,041 images captured across urban and rural streets of Japan, Czech Republic and India. Finally, the models were assessed based on their ability to predict and classify distresses, and tested using F1 score obtained from the statistical precision and recall values. The best performing model achieved an F1 score of 0.58 and 0.57 on two test datasets released by the IEEE Global Road Damage Detection Challenge. The source code including the trained models are made available at [1].Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Generative adversarial network for road damage detectionComputer-Aided Civil and Infrastructure Engineering, 2020
- Deep machine learning approach to develop a new asphalt pavement condition indexConstruction and Building Materials, 2020
- Review of Pavement Defect Detection MethodsIEEE Access, 2020
- DeepCrack: Learning Hierarchical Convolutional Features for Crack DetectionIEEE Transactions on Image Processing, 2018
- Automatic classification of pavement crack using deep convolutional neural networkInternational Journal of Pavement Engineering, 2018
- Deep Convolutional Neural Networks with transfer learning for computer vision-based data-driven pavement distress detectionConstruction and Building Materials, 2017
- Network level pavement evaluation with 1 mm 3D survey systemJournal of Traffic and Transportation Engineering (English Edition), 2015
- CrackTree: Automatic crack detection from pavement imagesPattern Recognition Letters, 2012
- Adaptive Road Crack Detection System by Pavement ClassificationSensors, 2011
- A Novel LBP Based Methods for Pavement Crack DetectionJournal of Pattern Recognition Research, 2010