A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Pavement Image Data Set for Deep Learning: A Synthetic Approach
Deep learning methods have shown a promising approach to reliable automated pavement condition survey in recent years. However, the training of models requires large quantities of annotated data, which is normally time consuming, expensive, and sometimes difficult to obtain. This research aims to explore the viability of using synthetic pavement image data to train convolutional neural networks (CNNs) for automated pavement crack detection. A procedural approach of generating synthetic pavement crack image data is proposed. Perlin noise is adopted to mimic the real-world cracks, and simple textures are used to control the generated crack type. Mask R-CNN is used to train on the synthetic data developed in this study. Both synthetic and real data sets are used to evaluate the performance of the trained model. The results indicate that training a crack detection model using only synthetic data can reach almost the same level of accuracy as using the real data.
Pavement Image Data Set for Deep Learning: A Synthetic Approach
Deep learning methods have shown a promising approach to reliable automated pavement condition survey in recent years. However, the training of models requires large quantities of annotated data, which is normally time consuming, expensive, and sometimes difficult to obtain. This research aims to explore the viability of using synthetic pavement image data to train convolutional neural networks (CNNs) for automated pavement crack detection. A procedural approach of generating synthetic pavement crack image data is proposed. Perlin noise is adopted to mimic the real-world cracks, and simple textures are used to control the generated crack type. Mask R-CNN is used to train on the synthetic data developed in this study. Both synthetic and real data sets are used to evaluate the performance of the trained model. The results indicate that training a crack detection model using only synthetic data can reach almost the same level of accuracy as using the real data.
Pavement Image Data Set for Deep Learning: A Synthetic Approach
Gong, Haitao (author) / Wang, Feng (author)
International Airfield and Highway Pavements Conference 2021 ; 2021 ; Virtual Conference
Airfield and Highway Pavements 2021 ; 253-263
2021-06-04
Conference paper
Electronic Resource
English
Pavement Image Data Set for Deep Learning: A Synthetic Approach
| TIBKAT | 2021
Three-dimensional tire-pavement contact stresses prediction by deep learning approach
| Taylor & Francis Verlag | 2022
Deep Machine Learning Approach to Develop a New Asphalt Pavement Condition Index
| ArXiv | 2020
Two-step deep learning approach for pavement crack damage detection and segmentation
| Taylor & Francis Verlag | 2023
| ArXiv | 2024