Research on the integration of transformer network in high-resolution remote sensing imagery road extraction network

In order to overcome the strong local perception and weak global perception characteristics of traditional convolutional neural networks (CNNs), this paper proposes a multi-spectral guided CNN-Transformer hybrid road extraction model (M2SA-MSNet) which introduces a multi-scale multi-head attention mechanism so as to capture long-range dependencies in the encoding stage. Experimental results suggest that, compared to the current state-of-the-art road extraction methods, M2SA-MSNet achieves better recognition performance and exhibits good accuracy and completeness in road extraction.