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.

The sound source localization in reverberant rooms is reformulated as a joint-sparsity support recovery problem in frequency domain under sparse Bayesian learning framework, where the reverberant effect is characterized using the image model. The joint sparsity in different frequencies is imposed by hierarchical probabilistic modeling with its hidden variables estimated by variational Bayesian inference. Numerical simulation results indicate that the proposed method achieves accurate sound source localization under low signal to noise ratio. The algorithm is evaluated by real data experiments using signals recorded in an anechoic chamber with one reflective plate and a rectangular room with strong reverberation. Both the numerical simulations and the real data experiments indicate that the proposed method can be applied in reverberant environments.

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.

In recent years, distantly-supervised relation extraction has achieved a certain success by using deep neural networks. Distant Supervision (DS) can automatically generate large-scale annotated data by aligning entity pairs from Knowledge Bases (KB) to sentences. However, these DS-generated datasets inevitably have wrong labels that result in incorrect evaluation scores during testing, which may mislead the researchers. To solve this problem, we build a new dataset NYTH, where we use the DS-generated data as training data and hire annotators to label test data. Compared with the previous datasets, NYT-H has a much larger test set and then we can perform more accurate and consistent evaluation. Finally, we present the experimental results of several widely used systems on NYT-H. The experimental results show that the ranking lists of the comparison systems on the DS-labelled test data and human-annotated test data are different. This indicates that our human-annotated data is necessary for evaluation of distantly-supervised relation extraction.