The building is a critical urban element for developing smart cities. Building extraction research has experienced rapid development due to abundant remote sensing image data availability. Building extraction methods have recently focused on enhancing regional accuracy without obtaining refined building boundaries, and do not fit the concave-convex shape of the building and have significant sawtooth noise. This paper proposes a building shape-preserving framework to solve the imperfect boundary problem. To delineate the concave and convex building boundaries from remote sensing images, we combine coarse and fine-grained information with the instance segmentation method, Mask region-based convolutional neural network (R-CNN), which can further refine the indeterminate boundary points, and perform inward fitting of the building boundary. A regular boundary network is designed to learn the features of the edges and footprints to calculate the boundary loss that can smoothen the boundary noise, considering the imperfect boundaries and sawtooth noise in the extracted building boundary. Furthermore, to enhance the ability to evaluate the extracted building shape, a building footprint information evaluation algorithm, the footprint distance metric, is proposed to calculate the footprint distance between each building boundary. Comparing the building extraction results indicate that the proposed method achieves excellent quantitative evaluation scores. Experiments performed using Spacenet and WHU datasets to verify the effectiveness of the proposed method are detailed. The experimental results indicate that the algorithm utilizes the powerful edge extraction capability of the method to exhibit excellent performance in terms of extracting building edges from complex remote sensing scenes. Code is available at https://github.com/AnnaCUG/Boundary-shape-preserving-model.

Road networks play an important role in navigation and city planning. However, current methods mainly adopt the supervised strategy that needs paired remote sensing images and segmentation images. These data requirements are difficult to achieve. The pair segmentation images are not easy to prepare. Thus, to alleviate the burden of acquiring large quantities of training images, this study designed an improved generative adversarial network to extract road networks through a weakly supervised process named WSGAN. The proposed method is divided into two steps: generating the mapping image and post-processing the binary image. During the generation of the mapping image, unlike other road extraction methods, this method overcomes the limitations of manually annotated segmentation images and uses mapping images that can be easily obtained from public data sets. The residual network block and Wasserstein generative adversarial network with gradient penalty loss were used in the mapping network to improve the retention of high-frequency information. In the binary image post-processing, this study used the dilation and erosion method to remove salt-and-pepper noise and obtain more accurate results. By comparing the generated road network results, the Intersection over Union scores reached 0.84, the detection accuracy of this method reached 97.83%, the precision reached 92.00%, and the recall rate reached 91.67%. The experiments used a public dataset from Google Earth screenshots. Benefiting from the powerful prediction ability of GAN, the experiments show that the proposed method performs well at extracting road networks from remote sensing images, even if the roads are covered by the shadows of buildings or trees.

Polyline simplification is a critical process in cartographic generalization, but the existing methods often fall short in considering the overall geographic morphology or local edge and vertex information of polylines. To enhance the graph convolutional structure for capturing crucial geographic element features and simultaneously learning vertex and edge features within map polylines, this study introduces a joint vertex–edge feature graph convolutional network (VE-GCN). The VE-GCN extends the graph convolutional operator from vertex features to edge features and integrates edge and vertex features through a feature transformation layer, enhancing the model’s capability to represent the shapes of polylines. To further improve this capability, the VE-GCN incorporates an architecture for retaining crucial geographic information. This architecture is composed of a structure for retaining local positional information and another for extracting multi-scale features. These components capture high–low dimensional and large–small scale features, contributing to polylines’ comprehensive local and global representation. The experimental results on road and coastline datasets verified the effectiveness of the proposed network in maintaining the overall shape characteristics of simplified polylines. After fusing the edge features, the differential distance between the roads before and after simplification decreased from 1.06 to 0.18. The network ensures invariant global spatial relationships, making the simplified data well suited for cartographic generalization applications, especially in simplifying vector map elements.