Hilbert填充曲线与空间分布模式探测结合的点数据集空间划分方法

空间数据划分是空间索引、并行GIS数据分解以及分布式数据管理与调度等问题的核心环节之一。本文针对点数据集多目标空间划分问题，在Hilbert空间填充曲线的基础上建立随机、规则、聚集三类空间分布模式的判定模型，设计针对均匀和随机分布模式的等差划分以及针对聚集分布模式的迭代寻优划分。实验表明该方法能够在缺少覆盖范围信息的条件下准确判定空间分布类型，该方法能够兼顾空间聚集性、数据量均衡与空间重叠度三种约束条件。

Spatial partitioning approach to point geospatial data based on the combination of hilbert space-filling curve and spatial pattern detection

Optimal partitioning of spatial dataset is an import concern for many data management context such as spatial indexing, parallelizing GIS and distributed data access. We propose a new distribution pattern-based technique for partitioning randrom, regular and clustering spatial dataset. The method is based on Hilbert space filling defined over the given set of data, under constraints on the data distributions. We show that the proposed method can achieve optimal partitioning point dataset without point dataset boundary information. We also show that the proposed method can adapt to available information about data distributions, data sizes and clustering.