mqr-tree: A 2-dimensional Spatial Access Method

Abstract: In this paper, we propose the mqr-tree, a two-dimensional spatial access method that organizes spatial objects in a two-dimensional node and based on their spatial relationships. Previously proposed spatial access methods that attempt to maintain spatial relationships between objects in their structures are limited in their incorporation of existing one-dimensional spatial access methods, or have lower space utilization in its nodes, and higher tree height, overcoverage and overlap than is necessary. The mqr-tree utilizes a node organization, set of spatial relationship rules and insertion strategy in order to gain significant improvements in overlap and overcoverage. In addition, other desirable properties are identified as a result of the chosen node organization and insertion strategies. In particular, zero overlap is achieved when the mqr-tree is used to index point data. A comparison of the mqr-tree insertion strategy versus the R-tree shows significant improvements in overlap and overcoverage, with comparable space utilization. In addition, a comparison of region searching shows that the mqr-tree achieves a lower number of disk accesses in many cases