Scholarlink

<p>Landslides are one of the most significant types of geological disasters worldwide. However, current landslide disaster recognition models generally face issues such as low training efficiency, reliance on large amounts of samples, and vague feature extraction. To address these problems, this paper proposes an enhanced intelligent recognition model based on an improved residual network. Taking remote sensing images from landslide-prone areas in Bijie City, Guizhou Province, China as the research subject, we implemented data augmentation techniques to expand the datasets, subsequently partitioning it into training and validation subsets at a 73:27 ratio. During model training, a transfer learning strategy was employed to improve training efficiency through the utilization of ImageNet pre-trained weights. The ResNet50 network architecture was enhanced through the integration of channel attention and spatial attention mechanisms, enabling more effective extraction of critical landslide features. Comparative analysis indicates that after introducing the attention mechanisms, the enhanced model achieved an increase of 1.49% in accuracy, 0.45% in precision, 1.52% in F1 score, and 0.0297 in Kappa coefficient on the validation set. Notably, recall improved by 2.59%, indicating that the improved model has enhanced landslide disaster recognition capability and overall performance. This study successfully coupled the transfer learning strategy with a dual-attention mechanism into the ResNet50 architecture, allowing the rapid construction of an efficient recognition model under limited sample conditions, significantly improving the comprehensive performance and generalisation ability of the landslide recognition model.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Landslide image recognition based on residual networks with transfer learning and spatial-channel dual attention mechanism

  • 期刊论文

  • 发表日期：

    2026年7月29日

查看全文
  • Cheng Zhao,
  • Jiacheng Yu,
  • Yongfei Xie,
  • Huiguan Chen,
  • Jinquan Xing,
  • Jialun Niu

摘要

Landslides are one of the most significant types of geological disasters worldwide. However, current landslide disaster recognition models generally face issues such as low training efficiency, reliance on large amounts of samples, and vague feature extraction. To address these problems, this paper proposes an enhanced intelligent recognition model based on an improved residual network. Taking remote sensing images from landslide-prone areas in Bijie City, Guizhou Province, China as the research subject, we implemented data augmentation techniques to expand the datasets, subsequently partitioning it into training and validation subsets at a 73:27 ratio. During model training, a transfer learning strategy was employed to improve training efficiency through the utilization of ImageNet pre-trained weights. The ResNet50 network architecture was enhanced through the integration of channel attention and spatial attention mechanisms, enabling more effective extraction of critical landslide features. Comparative analysis indicates that after introducing the attention mechanisms, the enhanced model achieved an increase of 1.49% in accuracy, 0.45% in precision, 1.52% in F1 score, and 0.0297 in Kappa coefficient on the validation set. Notably, recall improved by 2.59%, indicating that the improved model has enhanced landslide disaster recognition capability and overall performance. This study successfully coupled the transfer learning strategy with a dual-attention mechanism into the ResNet50 architecture, allowing the rapid construction of an efficient recognition model under limited sample conditions, significantly improving the comprehensive performance and generalisation ability of the landslide recognition model.