您好，欢迎访问湖北省农业科学院 机构知识库！
湖北省农业科学院机构知识库

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

MT-SiamNet: A Multi-Scale Attention Network for Reducing Missed Detections in Farmland Change Detection

文献类型： 外文期刊

作者： Wang, Jiangqing 1 ; Tian, Juanjuan 1 ; Zheng, Lu 1 ; Xie, Jin 1 ; Xia, Meng 1 ; Li, Shuangyang 1 ; Chen, Pingting 4 ;

作者机构： 1.South Cent Minzu Univ, Coll Comp Sci, Wuhan 430074, Peoples R China

2.Hubei Prov Engn Res Ctr Intelligent Management Mfg, Wuhan 430074, Peoples R China

3.Hubei Prov Engn Res Ctr Agr Blockchain & Intellige, Wuhan 430074, Peoples R China

4.Hubei Acad Agr Sci, Inst Agr Econ & Technol, Wuhan 430064, Peoples R China

关键词： CNN; Transformer; farmland change detection; remote sensing

期刊名称：APPLIED SCIENCES-BASEL （ 影响因子：2.5； 五年影响因子：2.7 ）

ISSN：

年卷期： 2025 年 15 卷 6 期

页码：

收录情况： SCI

摘要： Farmland changes have a profound impact on agricultural ecosystems and global food security, making the timely and accurate detection of these changes crucial. Remote sensing image change detection provides an effective tool for monitoring farmland dynamics, but existing methods often struggle with high-resolution images due to complex scenes and insufficient multi-scale information capture, particularly in terms of missed detections. Missed detections can lead to underestimating land changes, which affects key areas such as resource allocation, agricultural decision-making, and environmental management. Traditional CNN-based models are limited in extracting global contextual information. To address this, we propose a CNN-Transformer-based Multi-Scale Attention Siamese Network (MT-SiamNet), with a focus on reducing missed detections. The model first extracts multi-scale local features using a CNN, then aggregates global contextual information through a Transformer module, and incorporates an attention mechanism to increase focus on key change areas, thereby effectively reducing missed detections. Experimental results demonstrate that MT-SiamNet achieves superior performance across multiple change detection datasets. Specifically, our method achieves an F1 score of 65.48% on the HRSCD dataset and 75.02% on the CLCD dataset, significantly reducing missed detections and improving the reliability of farmland change detection, thereby providing strong support for agricultural decision-making and environmental management.

  • 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：湖北省农业科学院

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