Deep Learning Frameworks for Pavement Distress Classification: A Comparative Analysis
| Autor: | Abdul Rashid Mussah, Yaw Adu-Gyamfi, Vishal Mandal |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Damage detection Network architecture Source code business.industry Computer science Computer Vision and Pattern Recognition (cs.CV) media_common.quotation_subject Deep learning Big data Computer Science - Computer Vision and Pattern Recognition 0211 other engineering and technologies 02 engineering and technology Supercomputer Machine learning computer.software_genre 021105 building & construction 0202 electrical engineering electronic engineering information engineering Statistical precision 020201 artificial intelligence & image processing Artificial intelligence F1 score business computer media_common |
| Zdroj: | IEEE BigData |
| DOI: | 10.1109/bigdata50022.2020.9378047 |
| Popis: | 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]. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|