Scholarlink

<p>Satellite imagery classification plays a crucial role in land cover monitoring, urban planning, and environmental conservation. This paper presents a deep learning architecture designed to improve multi-scale feature learning for satellite image classification on the EuroSAT dataset. The model combines a ResNet50 backbone with atrous convolutions to capture multi-scale contextual information across multiple spectral bands, essential for accurately differentiating complex land-cover classes. The Convolutional Block Attention Module (CBAM) refines the spatial and channel features, focusing on details critical to classification. The Convolutional Long Short-Term Memory (ConvLSTM) module is incorporated as a recurrent spatial refinement stage operating over latent feature representations. Its gated update mechanism enables iterative feature modulation while preserving spatial structure, providing a alternative to purely feed-forward refinement strategies. The model achieves a mean Top-1 accuracy of approximately 97% across multiple random seeds, with a peak accuracy of 98%.</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

Atrous convolutions and ConvLSTM fusion for multi-scale feature learning in EuroSAT satellite imagery

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年8月3日

查看全文
  • Vageesh Jayaraman,
  • Indira Bharathi,
  • R. Kanniga Devi

摘要

Satellite imagery classification plays a crucial role in land cover monitoring, urban planning, and environmental conservation. This paper presents a deep learning architecture designed to improve multi-scale feature learning for satellite image classification on the EuroSAT dataset. The model combines a ResNet50 backbone with atrous convolutions to capture multi-scale contextual information across multiple spectral bands, essential for accurately differentiating complex land-cover classes. The Convolutional Block Attention Module (CBAM) refines the spatial and channel features, focusing on details critical to classification. The Convolutional Long Short-Term Memory (ConvLSTM) module is incorporated as a recurrent spatial refinement stage operating over latent feature representations. Its gated update mechanism enables iterative feature modulation while preserving spatial structure, providing a alternative to purely feed-forward refinement strategies. The model achieves a mean Top-1 accuracy of approximately 97% across multiple random seeds, with a peak accuracy of 98%.