您好，欢迎访问中国农业科学院 机构知识库！

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

Semantic Segmentation of Rice Fields in Sub-Meter Satellite Imagery Using an HRNet-CA-Enhanced DeepLabV3+Framework

文献类型： 外文期刊

作者： Shao, Yifan 1 ; Pan, Pan 1 ; Zhao, Hongxin 1 ; Li, Jiale 1 ; Yu, Guoping 1 ; Zhou, Guomin 3 ; Zhang, Jianhua 1 ;

作者机构： 1.Chinese Acad Agr Sci CAAS, Natl Nanfan Res Inst, Sanya 572024, Peoples R China

2.Chinese Acad Agr Sci, Agr Informat Inst, Beijing 100081, Peoples R China

3.Minist Agr & Rural Affairs, Nanjing Inst Agr Mechanizat, Nanjing 210014, Peoples R China

4.Natl Agr Sci Data Ctr, Beijing 100081, Peoples R China

5.Chinese Acad Agr Sci, Inst Western Agr, Changji 831100, Peoples R China

关键词： rice area; DeepLabV3+; High-Resolution Network; coordinate attention; semantic segmentation

期刊名称：REMOTE SENSING （ 影响因子：4.1； 五年影响因子：4.8 ）

ISSN：

年卷期： 2025 年 17 卷 14 期

页码：

收录情况： SCI

摘要： Accurate monitoring of rice-planting areas underpins food security and evidence-based farm management. Recent work has advanced along three complementary lines-multi-source data fusion (to mitigate cloud and spectral confusion), temporal feature extraction (to exploit phenology), and deep-network architecture optimization. However, even the best fusion- and time-series-based approaches still struggle to preserve fine spatial details in sub-meter scenes. Targeting this gap, we propose an HRNet-CA-enhanced DeepLabV3+ that retains the original model's strengths while resolving its two key weaknesses: (i) detail loss caused by repeated down-sampling and feature-pyramid compression and (ii) boundary blurring due to insufficient multi-scale information fusion. The Xception backbone is replaced with a High-Resolution Network (HRNet) to maintain full-resolution feature streams through multi-resolution parallel convolutions and cross-scale interactions. A coordinate attention (CA) block is embedded in the decoder to strengthen spatially explicit context and sharpen class boundaries. The rice dataset consisted of 23,295 images (11,295 rice + 12,000 non-rice) via preprocessing and manual labeling and benchmarked the proposed model against classical segmentation networks. Our approach boosts boundary segmentation accuracy to 92.28% MIOU and raises texture-level discrimination to 95.93% F1, without extra inference latency. Although this study focuses on architecture optimization, the HRNet-CA backbone is readily compatible with future multi-source fusion and time-series modules, offering a unified path toward operational paddy mapping in fragmented sub-meter landscapes.

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：中国农业科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台