Rse-net: Road-shape enhanced neural network for Road extraction in high resolution remote sensing image

Automatically extracting roads from remote sensing images is increasingly important for autonomous driving and geographic information systems. However, due to factors such as ground objects blocking road boundaries and some roads being narrow and long in high-resolution remote sensing images, it is difficult for the current mainstream pixel-level extraction model to guarantee the continuity of roads and the smoothness of boundaries. To solve this problem, this paper designs a neural network Rse-net based on semantic segmentation, using a two-stream semantic segmentation network algorithm to make the network pay more attention to the boundary information of roads and narrow roads. This structure uses shape stream to process road boundary information (roads' shape stream), and processes it in parallel with classic stream. Use the Gated Shape CNN to connect the two streams of roads' shape stream and classic stream, and use the classical stream to optimize the boundary information in the shape stream. At the same time, a multi-scale convolutional attention mechanism is used between the decoder and the encoder to expand the receptive field through large-core attention, and obtain more semantic information without causing too much calculation. Finally, the effectiveness of the proposed network is verified by comparative experiments.