摘要：Highly detailed surface models and their real-time applications are increasingly popular in architecture, construction and other design and engineering fields. However, new and related problems have emerged concerning the efficient management of the resulting large datasets and the seamless integration of heterogeneous data. Moreover, the increasingly common requirements of local high-fidelity modeling combined with large-scale landscapes lead to difficulty in the seamless multi-resolution representation of hybrid triangulated irregular networks (TINs) and Grids. This paper presents a hybrid data structure with high-efficiency and a related organizational method for the seamless integration of multi-resolution models. This approach is characterized by (1) a self-adaptive algorithm for feature-preserving surface partitioning, (2) an efficient hybrid index structure for combined Grid and TIN surfaces, and (3) a view-dependent scheduling strategy with access to Grids of necessary resolution, giving priority to the dynamic loading of TINs. Experiments using typical real design datasets of highway constructions are able to achieve accuracy-preserved and real-time availability of results that prove the validity and efficiency of this approach.
关键词：surface modeling; TIN; Grid; LoDs; high fidelity
