智能空间信息处理与时空大数据分析探索  

Intelligent Spatial Information Processing and Spatio-temporal Big Data Analysis Exploration

作　　者：秦昆[1] 许凯 吴涛 徐敏 黄静 陈一祥[6] 冯霞 赵鹏祥 王玉龙 张晔 徐源泉 毕奇 QIN Kun;XU Kai;WU Tao;XU Min;HUANG Jing;CHEN Yixiang;FENG Xia;ZHAO Pengxiang;WANG Yulong;ZHANG Ye;XU Yuanquan;BI Qi(School of Remote Sensing and Information Engineering,Wuhan University,Wuhan 430079,China;School of Geography and Information Engineering,China University of Geosciences(Wuhan),Wuhan 430078,China;School of Computer Science and Intelligent Education,Lingnan Normal University,Zhanjiang 524048,China;State Key Laboratory of Remote Sensing Science,Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100101,China;Beijing Institute of Applied Meteorology,Beijing 100029,China;School of Geographic and Biologic Information,Nanjing University,Nanjing 210023,China;School of Physics and Electronic Information Engineering,Hubei Engineering University,Xiaogan 432000,China;GIS Center,Department of Physical Geography and Ecosystem Science,Lund University,Lund,S-22362,Sweden;China Electronics Technology Group Corporation 27th Research Institute,Zhengzhou 450047,China;National Geomatics Center of China,Beijing 100830,China;School of Environment and Resources,Guangxi Normal University,Guilin 541006,China)

机构地区：[1]武汉大学遥感信息工程学院,湖北武汉430079 [2]中国地质大学(武汉)地理与信息工程学院,湖北武汉430078 [3]岭南师范学院计算机与智能教育学院,广东湛江524048 [4]中国科学院空天信息创新研究院遥感科学国家重点实验室,北京100101 [5]北京应用气象研究所,北京100029 [6]南京邮电大学地理与生物信息学院,江苏南京210023 [7]湖北工程学院物理与电子信息工程学院,湖北孝感432000 [8]瑞典隆德大学自然地理与生态系统科学系,隆德S-22362 [9]中国电子科技集团公司第二十七研究所,河南郑州450047 [10]国家基础地理信息中心,北京100830 [11]广西师范大学环境与资源学院,广西桂林541006

出　　处：《地理空间信息》2022年第12期1-11,共11页Geospatial Information

基　　金：国家自然科学基金资助项目(42171448);自然资源部地理国情监测重点实验室开放基金重点项目(2020NGCMZD03)。

摘　　要：提出一个智能空间信息处理与时空分析的研究框架,并对相关研究进行综述。首先分析讨论了其基础理论与关键技术,将关键技术总结为3个方面:智能空间信息处理、空间数据挖掘、时空大数据分析,分别介绍了智能空间信息处理的3个代表方法(云模型智能空间信息处理、数据场智能空间信息处理、空间统计智能信息处理),空间数据挖掘的3个代表方法(基于概念格的空间数据挖掘方法、基于商空间及粒计算的图像理解方法、基于深度学习的遥感场景识别方法),以及时空大数据分析的3个代表方法(轨迹聚类与分析、融合遥感与社会感知的城市功能区提取、地理多元流分析)。最后对智能空间信息处理与时空分析的理论、方法和应用进行了总结,并指明了进一步研究的方向。In this paper,we explored the research framework of intelligent spatio-temporal information processing and spatio-temporal analysis at first.And then,we discussed related basic theories and key technologies,including intelligent spatial information process(ISIP),spatial data mining(SDM),spatio-temporal big data analysis(ST-BDA).Specifically,the key technologies were analyzed which include①ISIP methods based on cloud model,data field,spatial statistics,②SDM methods including spatial data mining methods based on concept lattice,image understanding methods based on quotient space and granular computing,remote sensing scene recognition based on deep learning,③ST-BDA methods including trajectory clustering,urban functional district extraction combined remote sensing and social sensing,and geographical multiple flows analysis.Finally,we summarized the theories,methods and applications of intelligent spatio-temporal information processing and analysis,and discussed the future research directions.

关 键 词：智能空间信息处理 时空分析 空间数据挖掘 概念格 商空间 云模型 数据场 空间统计 轨迹分析 社会感知 地理多元流 

分 类 号：P208[天文地球—地图制图学与地理信息工程]