Name
Abstract | ||
|---|---|---|
textabstractGeospatial joins are a core building block of connectedmobility applications. An especially challenging problemare joins between streaming points and static polygons. Sincepoints are not known beforehand, they cannot be indexed.Nevertheless, points need to be mapped to polygons with lowlatencies to enable real-time feedback.We present an adaptive geospatial join that uses true hitfiltering to avoid expensive geometric computations in mostcases. Our technique uses a quadtree-based hierarchical gridto approximate polygons and stores these approximations in aspecialized radix tree. We emphasize on an approximate versionof our algorithm that guarantees a user-defined precision. Theexact version of our algorithm can adapt to the expected pointdistribution by refining the index. We optimized our implementationfor modern hardware architectures with wide SIMD vectorprocessing units, including Intel’s brand new Knights Landing.Overall, our approach can perform up to two orders of magnitudefaster than existing techniques. |
Year | Venue | Field |
|---|---|---|
2018 | arXiv: Databases | Geospatial analysis,Joins,Polygon,Computer science,SIMD,Radix tree,Computer hardware,Vector processor,Grid,Quadtree |
DocType | Volume | Citations |
Journal | abs/1802.09488 | 0 |
PageRank | References | Authors |
0.34 | 11 | 7 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Andreas Kipf | 1 | 32 | 11.03 |
| Harald Lang | 2 | 55 | 4.24 |
| Varun Pandey | 3 | 15 | 3.69 |
| Raul Alexandru Persa | 4 | 0 | 0.34 |
| Peter Boncz | 5 | 2517 | 244.81 |
| Thomas Neumann | 6 | 2523 | 156.50 |
| Alfons Kemper | 7 | 3519 | 769.50 |