基于自适应语义连接和感知注意力的沙漠分割方法OA

[Background]Desertification is recognized as a severe land degradation process threatening economic development and ecological security.Satellite remote sensing imagery is utilized for its wide coverage and high resolution,making deep neural networks and remote sensing tech-niques critical for desert boundary extraction in scientific research and sustainable develop-ment.[Methods]Inspired by this,a hybrid network model based on adaptive semantic connec-tivity is proposed,where global context and local texture features are fused to effectively re-duce semantic discrepancies between encoder and decoder,thereby enhancing desert boundary segmentation accuracy.To address high computational complexity and insufficient generalization capability,a dy-namic feature-scaled multi-head self-attention mechanism is designed,which is combined with a residual convo-lutional block attention module to strengthen multi-scale feature capture.Additionally,a differentiable boundary metric is introduced as a loss function to optimize boundary continuity.[Results]Experiments conducted on the Landsat-8 dataset demonstrate superior performance in both visual interpretation and quantitative evaluation met-rics,and a high-precision technical solution is provided for desertification monitoring.