基于POI数据及四叉树思想的“三生空间”识别方法

城市区域内部建筑物较密集,外围建筑物逐渐稀疏,因此大多存在内部区域POI数据密度大,外围区域POI数据密度逐渐减小的现象,在使用均等网格作为识别单元进行城市“三生空间”的识别的过程中,就会出现网格尺度较大导致识别准确率较低或网格尺度较小导致无数据区较多两种情况。针对以上问题,本研究提出一种基于POI数据及四叉树思想的”三生空间”识别方法：综合利用互联网地图POI、行政区划、遥感影像等数据,引入四叉树思想对网格识别单元进行分级;将POI数据与城市建设用地分类和土地利用现状分类进行衔接,对POI进行重分类;综合各类POI的功能和面积,构建POI分类“三生功能”赋分体系,定量识别“三生空间”。以西安市中心城区为实验区进行实例验证,结果显示正确率在95%左右。通过与均等格网识别结果的对比,进一步证明引入四叉树思想对网格进行分级一方面能有效减少无数据区的存在,另一方面能使识别结果准确率大幅提高,为基于POI数据的城市三生空间的识别提供了一种新思路。

Recognition Method of "The Production,Living and Ecological Space" based on POI Data and Quad-tree Idea

In urban areas, the inner buildings are dense, and the buildings are gradually sparse in the periphery. Therefore, there is always a phenomenon that the POI data density in the inner area is high, and the POI data density in the periphery area gradually decreases. At present, the equal grid created by fishing net tool is often used as the identification unit to carry out the recognition of "The Production, Living, and Ecological space"(PLES) for urban areas. But in the process of recognition, there will be two situations: if the grid scale is large, the recognition accuracy may be low; if the grid scale is small, then it may cause more data-free areas. To solve the above problems, this paper proposes a method of identifying the PLES based on POI data and the idea of quad-tree. By comprehensively utilizing POI data of Internet map, administrative division, remote sensing images, and other data, we introduce the idea of quad-tree to classify grid identification units. We connect POI data with urban construction land classification and land use status classification to reclassify POI. Based on the function and area of various POI, a POI classification of "The Production, Living, and Ecological Function" score system is constructed to quantitatively identify PLES. Then taking Xi'an central urban area as the experimental area for method verification, the recognition results were sampled and compared with the visual interpretation results from remote sensing images and the current land use map. The experimental result shows that the correct rate was around 95%. By comparing with the results obtained by using the equal grid for recognition of PLES, the introduction of the quad-tree idea to classify the grid has the following advantages: in view of the low density of POI data in the periphery of the city, the introduction of quad-tree idea to merge grids can effectively reduce the existence of data-free areas and improve the utilization of less POI data in the periphery of the city; for areas with dense POI data within the city, using small-scale grids as the identification unit can give full play to its large data volume and improve the accuracy of the identification results of the PLES in the urban area. This method provides a new idea for the identification of the PLES for urban areas based on POI data.