遥感大数据的智能处理:现状与挑战  

Intelligent Processing of Remote Sensing Big Data:Status and Challenges

作　　者：宋维静[1] 刘鹏[1] 王力哲[1] 吕科[2] 

机构地区：[1]中国科学院遥感与数字地球研究所,北京100094 [2]中国科学院大学工程管理与信息技术学院,北京100049

出　　处：《工程研究（跨学科视野中的工程）》2014年第3期259-265,共7页JOURNAL OF ENGINEERING STUDIES

摘　　要：随着遥感技术的发展,遥感数据空间分辨率、时间分辨率、光谱分辨率和辐射分辨率越来越高,数据类型越来越丰富,与此同时,数据量也越来越大。遥感大数据向传统的遥感数据智能处理提出了新的挑战。本文从信息处理的角度论述了遥感大数据的海量、异构、多源的外部特征与高维度、多尺度、非平稳的内部特征,阐述了遥感大数据智能处理在算法方面所涉及的关键技术,分析了遥感大数据稀疏表征字典训练与稀疏求解方面的研究现状与存在的问题,讨论了遥感大数据数据挖掘面临的挑战,阐述了遥感大数据知识发现数据降维方面现有的解决方法与难题,并对相应的问题进行了概括性讨论。最后,总结了遥感大数据智能处理目前的研究阶段与研究意义。With the development of remote sensing technology, the spatial resolution, the temporal resolu-tion, the spectral resolution and the radiometric resolution of remote sensing data becomes higher, meanwhile the amount of data is becoming lager. This paper focuses on the new challenges brought by remote sensing big data to the traditional large remote sensing data processing. Firstly, this article discusses the external features and the in-ternal features of remote sensing big data from the perspective of information processing. External features include massive, heterogeneous, multi-source and internal features are high-dimensional, multi-scale, and non-stationary. Secondly, we analyze the research status and problems of large data sparse representation, data mining and knowledge discovery. Finally, we discuss the remote sensing big data intelligent processing problems. As a typical representative of the science of big data, remote sensing big data is still in its infancy;therefore, there are many issues to be studied.

关 键 词：遥感大数据 智能处理 稀疏表征 数据挖掘 知识发现 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置]