摘要
地表覆盖数据是关于土地利用信息的重要来源,在地理国情监测、生态环境保护等方面发挥着重要的作用,目前遥感影像解译、实地测量是该数据生产的主要手段,但是仍然存在一定的局限性。随着Web2.0、互联网技术以及各种GPS设备的快速发展传播,普通大众也可以参与公众制图,志愿者用户的参与能够有效判定地表类型的空间分布和属性特征,提高地表覆盖制图的分类精度。本文以自发地理信息中最成功的项目OpenStreetMap为例,与中国新研制的全球最高30m分辨率地表覆盖数据产品GlobeLand 30进行对比分析,首先对数据进行相应的预处理和拓扑检查,然后建立两种数据的要素对应关系,最后生成误差矩阵并分析两种数据的一致性。实验结果表明:(1) OpenStreetMap数据缺失的部分主要是耕地类型,其草地和水体要素比GlobeLand 30更加丰富;(2) 2种数据的一致性较好为75%左右,其中林地和人造地表的精度较高,耕地和水体次之,草地较差;(3)重点对不一致区域的地表类型进行判断验证,能够发现GlobeLand 30数据中的错误分类,为进一步修改和优化提供依据。本文研究表明,自发地理信息中包含丰富的地表覆盖信息,能够给地表覆盖制图及评价验证带来巨大的发展潜力。
Land cover data, which plays a significant role in national geographical condition monitoring, ecological environmental protection and some other areas, is an important resource of the information on land use. At present, land cover data is produced mainly through the interpretation of remote sensing imagery and field measurement, and some limitations still exist to a certain extent. With the rapid development and wide spread of Web2.0, internet technology and various kinds of GPS equipment, the general public have the opportunity to participate in crowd sourced mapping. Volunteer users can identify the spatial distribution and attributive characters of the land cover effectively. Therefore, the classification accuracy of land cover map can be improved in the meantime. In this paper, OpenStreetMap, the most successful item of volunteered geographic information, was taken as an example on the comparison analysis with GlobeLand 30, the newly developed land cover data produced in China with 30m resolution. Firstly, the data was preprocessed and topologically checked, and then the feature relationship was established. Finally, a confusion matrix was built to analyze the consistency between the two kinds of data. The experimental results show that the missing part of the OpenStreetMap is mainly cultivated land, and the grassland and water elements are more abundant than those of GlobeLand 30. The consistency of OpenStreetMap and GlobeLand 30 is high with a value of 75%. Forest and artificial surface have the highest accuracy, and cultivated land and water body take the second place, while grassland possesses the worst consistency. The key point is to verify and determine the land cover type within the inconsistent areas, and try to find classification errors of GlobeLand 30 so as to provide basis for further modification and optimization. Volunteered geographic information contains abundant land cover information, so it can provide great potential for the development and evaluation of land cover maps. The research methods and conclusions of this paper can provide basis for exploring the application of OpenStreetMap data for land cover mapping, and provide support for assessment and improvement of the classification accuracy of GlobeLand 30.
作者
马京振
孙群
徐立
温伯威
李元復
MA Jingzhen;SUN Qun;XU Li;WEN Bowei;LI Yuanfu(Information Engineering University,Zhengzhou 450001,China)
出处
《地球信息科学学报》
CSCD
北大核心
2018年第9期1225-1234,共10页
Journal of Geo-information Science
基金
国家自然科学基金项目(41571399)~~