遥感大数据智能解译的地理学认知模型与方法  

Geo-cognitive models and methods for intelligent interpretation of remotely sensed big data

作　　者：张兵 杨晓梅 高连如[1,4] 孟瑜 孙显[1] 肖晨超 倪丽 ZHANG Bing;YANG Xiaomei;GAO Lianru;MENG Yu;SUN Xian;XIAO Chenchao;NI Li(Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China;University of Chinese Academy of Sciences,Beijing 100049,China;State Key Laboratory of Resources and Environment Information System,Institute of Geographic Sciences and Natural Resources Research,Chinese Academy of Sciences,Beijing 100101,China;Key Laboratory of Computational Optical Imaging Technology,Chinese Academy of Sciences,Beijing 100094,China;National Engineering Center for Geoinformatics,Beijing 100101,China;Land Satellite Remote Sensing Application Center,Beijing 100048,China)

机构地区：[1]中国科学院空天信息创新研究院,北京100094 [2]中国科学院大学,北京100049 [3]中国科学院地理科学与资源研究所资源与环境信息系统国家重点实验室,北京100101 [4]中国科学院计算光学成像技术重点实验室,北京100094 [5]国家遥感应用工程技术研究中心,北京100101 [6]自然资源部国土卫星遥感应用中心,北京100048

出　　处：《测绘学报》2022年第7期1398-1415,共18页Acta Geodaetica et Cartographica Sinica

基　　金：国家重点研发计划(2021YFB3900500)。

摘　　要：随着遥感数据和计算机算力的爆炸式增长、智能分析算法瓶颈的突破,亟须提升与之相匹配的遥感大数据处理与分析能力。针对复杂场景下遥感大数据智能处理与地理学认知耦合关联和交叉融合的关键问题,本文分析了遥感大数据与地理科学各自的特点与相互关系,提出了多模态知识融合关联的深度网络构建和面向地理制图的遥感智能解译思路,建立了遥感大数据智能处理与应用体系框架;面向技术发展和行业应用,本文提出了分别建设通用高分辨率遥感智能处理系统和智能精准应用平台的总体路线,以期推动遥感智能解译技术创新和工程化应用的全面发展。With the explosive growth of remotely sensed data and computing power,and the breakthrough of intelligent analysis algorithms,there is an urgent need to improve the capabilities to match in remotely sensed big data processing and analysis.Aiming at the crucial problems of coupling association and cross fusion of remotely sensed big data intelligent processing and geographical cognition in complex scenes,this paper analyzes the characteristics and relationships between remotely sensed big data and geographical science,puts forward the idea of building deep network of multimodal knowledge fusion and intelligent interpretation of remotely sensed data for geographical cartography,and establishes the framework of remotely sensed big data intelligent processing and application system.A general high-resolution remote sensing intelligent processing system for technology development and an intelligent application platform for industry applications are proposed,respectively,in order to boost the technological innovations and engineering applications of intelligent interpretation using remotely sensed big data.

关 键 词：遥感大数据 地理学 智能图像处理 国土资源调查 

分 类 号：P237[天文地球—摄影测量与遥感]