IEEE Geoscience and Remote Sensing Letters · 2019 · 26 citations · 18 references
ComputingComputer ScienceGeoinformaticsComputer VisionFeature EngineeringRemote SensingGeospatial Computer VisionImage Feature EngineeringRemote Sensing Image AnalysisRemote Sensing ImagerySemantic SegmentationTerrain Feature ExtractionConvolutional Neural NetworksFully Convolutional NetworksRemote Sensing Feature ExtractionRemote Sensing Image FeaturesRemote Sensing Image InterpretationRemote Sensing Terrain ExtractionRoad ExtractionRoad Network Extraction
Road extraction from the remote sensing image over mountainous areas is a difficult vision problem. In this letter, we propose a multiple feature fully convolutional network (MFFCN) on the basis of FCN for mountainous road extraction. The benefits of this model are twofold: first, MFFCN is a semantic segmentation model, which has deep convolutional networks. It avoids the problem of repeated storage and computational convolutions caused by the use of pixel blocks. Second, the MFFCN model could extract the spectral and terrain features. This method ensures the integrity and continuity of the road extraction results. The dataset is composed of GF-2 data and ASTER GDEM data in the Shigatse region of Tibet. We test our network on the dataset and compare it with four road extraction methods. The result shows that the proposed MFFCN is superior to all the comparing methods.
18
Gradient-based learning applied to document recognition
Yann LeCun, Léon Bottou, Yoshua Bengio et al. · Proceedings of the IEEE · 1998 · 58.2K citations · Full text
Going deeper with convolutions
Christian Szegedy, Wei Liu, Yangqing Jia et al. · 2015 · 46.8K citations
Fully convolutional networks for semantic segmentation
Jonathan Long, Evan Shelhamer, Trevor Darrell · 2015 · 36.9K citations