Exploring multiple crowdsourced data to learn deep convolutional neural networks for road extraction

Abstract

Road extraction from high-resolution remote sensing images (HRSIs) is essential for applications in various areas. Although deep convolutional neural networks (DCNNs) have exhibited remarkable success in road extraction, the performance relies on a large amount of training samples which are hard to obtain. To address this issue, multiple crowdsourced data are used in this study, including OpenStreetMap (OSM), Zmap and GPS. And a multi-map integration model (MMIM) is developed to improve the noise robustness of DCNNs for road extraction tasks. Specifically, rich geographical road information are obtained from multiple crowdsourced data, including main roads, new construction roads, midsize and small roads, which can generate complete road training samples and reduce the label noise. Meanwhile, by exploring the true road label information hidden in different crowdsourced data, the MMIM is used to generate high-quality refined labels for learning DCNNs. In this case, the DCNN-based road extraction methods have more opportunities to learn true road distribution and avoid the overfitting problems of label noise. Experiments based on real road extraction dataset indicate that the proposed method shows great performance, and road extraction results are smoother and more complete.