深度学习PaddlePaddle框架支持下的遥感智能视觉平台研究与实现  

Research and implementation of remote sensing intelligent vision platform based on deep learning PaddlePaddle framework

作　　者：孙玉梅[1] 刘昱豪 边占新[1] 孙亮 陈敬周[1] SUN Yumei;LIU Yuhao;BIAN Zhanxin;SUN Liang;CHEN Jingzhou(Department of Surveying and Mapping Engineering,Shijiazhuang Institute of Railway Technology,Shijiazhuang 050018,China;North Latitude(Beijing)Technology Co.,Ltd.,Beijing 100043,China)

机构地区：[1]石家庄铁路职业技术学院,河北石家庄050018 [2]中科北纬(北京)科技有限公司,北京100043

出　　处：《测绘通报》2021年第11期65-69,75,共6页Bulletin of Surveying and Mapping

摘　　要：百度深度学习PaddlePaddle框架支持下的遥感智能视觉平台,能够运用深度学习技术实现遥感影像的智能建模、训练和解译。本文通过深入分析PaddlePaddle图像分割模型库PaddleSeg的图像处理深度学习算法模型DeepLabV3+、U^(2)-Net及RetinaNet,开发设计了遥感智能视觉平台,实现了遥感影像的地块分割、变化检测和斜框检测等专业功能。研究表明:遥感智能视觉平台提取的图斑总面积是目视解译的80%、有效图斑比例为76%、错误图斑比例为18%,实现了快速有效的遥感图像智能处理。The remote sensing intelligent vision platform supported by Baidu deep learning PaddlePaddle framework is researched and implemented.It can use deep learning technology to realize intelligent modeling,training and interpretation of remote sensing images.Through the deep analysis of the deep learning algorithm model DeepLabV3+,U^(2)-Net and RetionaNet of PaddleSeg image segmentation model library,the remote sensing intelligent vision platform is developed and designed,which realizes the professional functions of parcel segmentation,change detection and oblique frame detection of remote sensing image.The results show that:the total area of the spot extracted by the remote sensing intelligent vision platform is 80%of the visual interpretation,the proportion of effective spot is 76%,and the proportion of error spot is 18%,which realizes the fast and effective remote sensing image intelligent processing.

关 键 词：深度学习 PaddlePaddle 算法模型 遥感图像 智能处理 

分 类 号：P237[天文地球—摄影测量与遥感]