Views:170Downloads:69751CSCD:0

  • Export

  • Collection

  • Album

    • Lightweight urban surface anomaly event identification model for complex urban environments

    • “The research team proposed a high-precision lightweight urban surface anomaly recognition model DLAAD Net, which adopts a transfer learning strategy and uses a self supervised pre trained visual model DINOv3 as the feature extraction backbone. The low rank adapter (LoRA) is used to efficiently fine tune the parameters, achieving feature transfer from natural scenes to remote sensing scenes. With only 0.6M parameters, it achieves an F1 score of 97.29%, providing a solution for urban safety supervision and disaster emergency response.”
      • role：First author第一作者
      • Affiliation：

        Jiangsu Provincial Key Laboratory of Geographic Information Science and Technology, Key Laboratory for Land Satellite Remote Sensing Applications of Ministry of Natural Resources, School of Geography and Ocean Science, Nanjing University, Nanjing, Jiangsu, China 210023

      • Email：502025270077@smail.nju.edu.cn
      • Introduction：杜东阳，研究方向为遥感图像智能解译。E-mail： 502025270077@smail.nju.edu.cn

      DU Dongyang

      ,
      • Affiliation：

        Jiangsu Provincial Key Laboratory of Geographic Information Science and Technology, Key Laboratory for Land Satellite Remote Sensing Applications of Ministry of Natural Resources, School of Geography and Ocean Science, Nanjing University, Nanjing, Jiangsu, China 210023

      ZHOU Mengqing

      ,
      • Affiliation：

        Jiangsu Provincial Key Laboratory of Geographic Information Science and Technology, Key Laboratory for Land Satellite Remote Sensing Applications of Ministry of Natural Resources, School of Geography and Ocean Science, Nanjing University, Nanjing, Jiangsu, China 210023

      LI Kaiyuan

      ,
      • role：Corresponding author通信作者
      • Affiliation：

        Jiangsu Provincial Key Laboratory of Geographic Information Science and Technology, Key Laboratory for Land Satellite Remote Sensing Applications of Ministry of Natural Resources, School of Geography and Ocean Science, Nanjing University, Nanjing, Jiangsu, China 210023

      • Email：xiaopf@nju.edu.cn
      • Introduction：肖鹏峰，研究方向为遥感图像智能解译。E-mail： xiaopf@nju.edu.cn

      XIAO Pengfeng

      * ,
      • Affiliation：

        Jiangsu Provincial Key Laboratory of Geographic Information Science and Technology, Key Laboratory for Land Satellite Remote Sensing Applications of Ministry of Natural Resources, School of Geography and Ocean Science, Nanjing University, Nanjing, Jiangsu, China 210023

      ZHANG Xueliang

    • Pages: 1-16(2026)  

    • DOI：10.11834/jrs.20266180    

    Scan QR Code

    Scan QR Code

  • Quote

    Translate The Full Text

  •  
  •  

  • AI Introduction

  • Full Text(HTML)

  • Figs( 12 ) Tabs( 8 )

  • References

  • Publication Info

  • Metrics

Alert me when the article has been cited
Submit

Related Articles

Related Author

LI Zhi 中国科学院空天信息创新研究院 计算光学成像技术重点实验室;中国科学院大学 资源与环境学院
GAO Lianru 中国科学院空天信息创新研究院 计算光学成像技术重点实验室
ZHENG Ke 聊城大学 地理与环境学院
NI Li 中国科学院空天信息创新研究院 计算光学成像技术重点实验室
ZHOU Weixun 南京信息工程大学 遥感与测绘工程学院;北京师范大学 遥感科学国家重点实验室
LIU Jinglei 南京信息工程大学 遥感与测绘工程学院
PENG Daifeng 南京信息工程大学 遥感与测绘工程学院
GUAN Haiyan 南京信息工程大学 遥感与测绘工程学院

Related Institution

Key Laboratory of Computational Optical Imaging Technology, Aerospace Information Research Institute, Chinese Academy of Sciences
College of Resources and Environment, University of Chinese Academy of Sciences
School of Geography and Environment, Liaocheng University
School of Remote Sensing & Geomatics Engineering, Nanjing University of Information Science and Technology
State Key Laboratory of Remote Sensing Science, Beijing Normal University