Jing Zheng

The comprehensive expression of indoor maps directly affects the visualization effect of the map and the user’s map reading experience. Currently, only the points, lines, and polygons of outdoor maps are used as objects of cartographic generalization. Therefore, this study considers indoor map area features as generalization objects and deems the automatic clustering of the indoor area features of shopping malls as the research goal. The approach is used to construct an encoder-decoder clustering model, where the encoder consists of a graph convolutional network and its variant models. The results show that the proposed model framework effectively extracts the area features suitable for the indoor space clustering of shopping malls and improves clustering efficacy. Specifically, the model with the Relational Graph Convolutional Network as the encoder demonstrated the best performance, time complexity, and accuracy of clustering results, with accuracy up to 95%. This study extends the research object of cartographic generalization to indoor maps, enabling the automatic clustering of indoor area features, and proposes a clustering model for the important indoor scene of shopping malls. This is valuable for scholars interested in the cartographic generalization of indoor maps.

The selection of road networks is very important for cartographic generalization. Traditional artificial intelligence methods have improved selection efficiency but cannot fully extract the spatial features of road networks. However, current selection methods, which are based on the theory of graphs or strokes, have low automaticity and are highly subjective. Graph convolutional networks (GCNs) combine graph theory with neural networks; thus, they can not only extract spatial information but also realize automatic selection. Therefore, in this study, we adopted GCNs for automatic road network selection and transformed the process into one of node classification. In addition, to solve the problem of gradient vanishing in GCNs, we compared and analyzed the results of various GCNs (GraphSAGE and graph attention networks [GAT]) by selecting small-scale road networks under different deep architectures (JK-Nets, ResNet, and DenseNet). Our results indicate that GAT provides better selection of road networks than other models. Additionally, the three abovementioned deep architectures can effectively improve the selection effect of models; JK-Nets demonstrated more improvement with higher accuracy (88.12%) than other methods. Thus, our study shows that GCN is an appropriate tool for road network selection; its application in cartography must be further explored.