Road Extraction From Satellite Imagery by Road Context and Full-Stage Feature
Abstract：Road extraction from satellite imagery is vital in a broad range of applications. However, extracting complete roads is challenging due to the road occlusions caused by surroundings. This paper proposed an improved encoder-decoder network via extracting road context and integrating full-stage features from satellite imagery, dubbed as RCFSNet. A multi-scale context extraction (MSCE) module is designed to enhance the inference capabilities by introducing adequate road context. Multiple full-stage feature fusion (FSFF) modules in the skip connection are devised to provide accurate road structure information, and we devise a coordinate dual attention mechanism (CDAM) to strengthen the representation of road features. Extensive experiments are carried out on two public datasets, as a result, our RCFSNet outperforms other state-of-the-art methods. The results indicate that the road labels extracted by our method have preferable connectivity.
Our code is based on DLinkNet .
DeepGlobepython main_RCFSNet_road.py
Massachusettspython main_RCFSNet_Mas.py
DeepGlobepython test_RCFSNet_ROAD.pyMassachusettspython test_RCFSNet_Mas.py