A High-Dimensional Indexing Model for Multi-Source Remote Sensing Big Data

With continuous improvement of earth observation technology, source, and volume remote sensing data are gradually enriched. It is critical to realize unified organization form sharing service capabilities for massive effectively. We design a hierarchical multi-dimensional hybrid indexing model (HMDH), address the problems in underlying management, improve query efficiency. Firstly, we establish grid as smallest unit carrying processing spatio-temporal information. implement construction HMDH two steps, classification based on fuzzy clustering algorithm, optimization recursive neighborhood search algorithm. Then, construct “cube” structure, filled with space filling curves, complete coding HMDH. The reduces amount 6–17% improves accuracy more than eight times traditional model. Moreover, it can reduce time 25% some scenarios algorithms selected baseline this paper. proposed be used solve efficiency fast joint retrieval data. extends pattens has high application value.