The road is a requisite asset to urban infrastructure for generating nations' economic growth and development. Therefore, road distress mapping is paramount for maintenance planning. Fusing deep learning methods with GIS techniques, provides insight to obtaining new opportunities using satellite imageries through spatial, temporal, and spectral resolutions with data integration. In this context, the research proposes implementing an end-to-end convolutional neural network architecture for extracting the road networks and its application towards road distress mapping using very high-resolution (VHR) remote sensing images. Understanding the limitations of existing methods, the proposed model is tweaked to extract finer features and, thus, increase the likelihood of accurate prediction.
Paper
Full text
Deep Learning Based Approach for Road Distress Mapping Using VHR Images
Semantic Scholar · Engineering · 2023
Abstract
The road is a requisite asset to urban infrastructure for generating nations' economic growth and development. Therefore, road distress mapping is paramount for maintenance planning. Fusing deep learning methods with GIS techniques, provides insight to obtaining new opportunities using satellite imageries through spatial, temporal, and spectral resolutions with data integration. In this context, the research proposes implementing an end-to-end convolutional neural network architecture for extracting the road networks and its application towards road distress mapping using very high-resolution (VHR) remote sensing images. Understanding the limitations of existing methods, the proposed model is tweaked to extract finer features and, thus, increase the likelihood of accurate prediction.