期刊论文

Liu, PC

英文

International Journal of Applied Earth Observation and Geoinformation

1569-8432

2024

129

103794

10.1016/j.jag.2024.103794

Fig. 5 (e) illustrates the first-order neighboring polygons (indicated by red lines) and second-order neighboring polygons (indicated by green lines) for building polygon A. As observed in Fig. 5 (d), within the Voronoi tessellation model, unlike regular images (of a single pixel are 8), the number of neighboring units for an individual building polygon may be greater or less than 8, and their directions are not restricted to fixed 8 directions (0°, 45°, 90°, 135°, 180°, 225°, 270°, 315°). Instead, they are distributed in the range θ ∈ [0°, 360°). Therefore, when constructing the texton co-occurrence matrix for a cluster of building polygons, it is necessary to partition the directions to determine the principal directions. This aspect will be elaborated upon in detail in Section 2.2.3.

本校为第一且通讯机构

The cluster patterns of features in map space represent a comprehensive reflection of individual feature geometric attributes and their spatial adjacency relationships. These patterns also embody spatial cognition results under the Gestalt principle. Describing non-linear spatial cluster patterns as effective regular structures is one of the fundamental tasks in deep learning for recognizing feature cluster patterns. In this study, based on the concept of texture co-occurrence matrices from regular gray-scale images, we utilized Voronoi diagrams to construct the tessellation structure of build...