图斑数据的多密度属性连接聚类方法

A multi-density attribute clustering approach for polygons

图斑面的聚类处理是挖掘图斑空间知识的重要手段。针对当前图斑面大小不一、形态各异、分布不均等导致聚类结果不够准确的问题,同时为满足大规模图斑数据分析的需要,本文引入多密度属性计算指标,提出了一种图斑数据的聚类方法。首先,根据单个图斑内部点位置(包含边界)的不同赋予其多个密度属性;然后,根据图斑间密度低值向密度高值靠拢的趋势建立图斑归属连接,依次生成图斑要素的树状结构连接;最后,依据树状结构连接的结果对各连接进行剪枝或合并,生成多个独立树,完成图斑面的聚类。试验证明,本文方法可以有效识别各类不规则图斑的聚合集群,并在大规模图斑数据的聚合中具有良好的精度表现,满足高密度多边形区域的聚类识别需求。

Clustering of polygons is an important means of mining the intrinsic spatial knowledge of polygons.The current problems of varying size,morphology and distribution of polygons lead to less accurate clustering results.At the same time,in order to meet the needs of analysis of large batch of polygons data,this paper proposes a clustering method for polygons with multi-density attribute calculation index.Firstly,according to the different locations(including boundaries)of the internal points of a single polygon,multiple density attributes are assigned to a single polygon.Secondly,based on the tendency of the low density values among the polygons for converge to the high density values,a polygon aim vector is generated,and the tree structure connections of the elements are sequentially generated.Finally,the clustering of polygons is completed by the strategy of connection pruning and merging.It is proved that the method can effectively identify the aggregation clusters of various irregular polygons,and has good accuracy performance in the aggregation of massive polygons data,realizing the clustering needs of recognition of high density polygonal regions.