An Automated Approach to Coastline Simplification for Maritime Structures with Collapse Operation

An Adaptive Simplification Method for Coastlines Using a Skeleton Line “Bridge” Double Direction Buffering Algorithm

“…According to visual constraints [17] (that is, there is no invisible part of the simplified coastline), then there must be 𝐶𝐷 = 𝑠𝑣𝑜 (where 𝑠𝑣𝑜 represents the minimum distance that can be recognized by human eyes). Letting CAE α ∠ = , we can derive…”

“…According to the basic idea described in Section 3.1, after performing the outer buffer zone transformation on the coastline, the next step is to extract the "bridging" skeleton line. The extraction of bridging skeleton lines is based on the extraction of coastline skeleton lines, and there are many methods for extracting line element skeleton lines [5][6][7][8][9][10][11][12][13][14][15][16][17][18][31][32][33][34][35]. In this paper, we first construct a constrained Delaunay triangulation network based on the data points on the coastline and extract the triangles located in the sea area.…”

“…In this paper, we first construct a constrained Delaunay triangulation network based on the data points on the coastline and extract the triangles located in the sea area. Then, we classify the triangles into three categories (I, II, and III) based on the number of According to visual constraints [17] (that is, there is no invisible part of the simplified coastline), then there must be CD = svo (where svo represents the minimum distance that can be recognized by human eyes). Letting ∠CAE = α, we can derive 2r cos α − 2( When α = 0, the extremum r = ν+svo 2 can be obtained (ν is the coastline stroke width and svo is the minimum distance perceivable by the human eye).…”

“…However, in the process of coastline simplification, directly selecting bends as a whole does not conform to their gradual change process with scale changes [16]. To address this issue, for complex estuary coastlines, one study [17] constructs a binary tree model of estuary skeleton lines supported by constrained Delaunay triangulation and then implements progressive coastline simplification through certain steps, such as small bend deletion, deletion of small parts of bends, and local enlargement, thus improving the quality of simplification. On this basis, for coastlines and island shorelines nearby, another study [18] proposes a hierarchical triangular mesh partitioning method for collaborative coastline simplification, effectively solving the problem of collaborative coastline simplification.…”

AlpineBends – A Benchmark for Deep Learning-Based Generalisation

“…However, the emergence of the image-based deep learning techniques has shown an ability to process images of geographic information. The question of their adaptation for map generalization is a trendy subject: road (Courtial et al 2020), building (Feng et al 2019) and coastline (Du et al 2021) generalization have been explored in recent years. Common methods for evaluating these techniques seems to be necessary for the comparison and development of this field.…”