Urban vitality is a key indicator for measuring urban development. This topic has been trending in urban planning and sustainable development, and significant progress has been made in measuring single indicators of urban vitality based on parcel or block units. With the continuous development of smart sensing technology, multisource urban data are becoming increasingly abundant. The application of such data to measure the multidimensional urban vitality of street space, reflecting multiple functions of an urban space, can significantly improve the accuracy of urban vitality analyses and promote the construction of people-oriented healthy cities. In this study, streets were taken as the analysis unit, and multisource data such as the trajectories of taxies and shared bicycles, user reviews and cultural facility points of interest (POIs) in Chengdu, a city in southwestern China, were used to identify spatial patterns of urban vitality on streets across social, economic and cultural dimensions. The correlation between the built environment factors and the multidimensional urban vitality on the street was analyzed using a multiple regression model. The spatial distribution of the different dimensions of urban vitality of the street space in Chengdu varies to a certain extent. It is common for areas with high social vitality to have production and life centers nearby. High economic vitality centers are typically found along busy streets with a high concentration of businesses. Areas with high cultural vitality centers tend to be concentrated on the city’s central streets. Land use, transportation, external environment, population and employment are all closely linked to urban vitality on streets. The crowd counting and POI density have the greatest impact on multidimensional urban vitality. The crowd and the level of service facilities profoundly affect social interaction, trade activities and cultural communication. The goodness of fit (R²) of the regression models for social, economic and cultural vitality are 0.590, 0.423 and 0.409, respectively. Using multisource urban data, our findings can help stakeholders better understand the spatial patterns and influencing factors of multidimensional urban vitality on streets and provide sustainable urban planning and development strategies for the future.

Understanding the spatial patterns of retail stores in urban areas contributes to effective urban planning and business administration. A variety of methods have been proposed in the scientific literature to identify the spatial patterns of retail stores. These methods invariably employ arbitrary grid cells or administrative units (e.g., census tracts) as the fundamental analysis units. As most urban retail stores are distributed along street networks, using area-based analysis units is subject to statistical biases and may obfuscate the spatial pattern to some extent. Using the street segment as the analysis unit, this paper derives the spatial patterns of retail stores by crawling points of interest (POI) data in Zhengzhou, a city in central China. Then, the paper performs the network-based kernel density estimation (NKDE) and employs several network metrics, including the global, local, and weighted closeness centrality. Additionally, the paper discusses the correlation between the NKDE value and the closeness centrality across different store types. Further analysis indicates that stores with a high correlation tend to be distributed in city centers and subnetwork centers. The comparison between NKDE and cell-based KDE shows that our proposed method can address potential statistical issues induced by the area-based unit analysis. Our finding can help stakeholders better understand the spatial patterns and trends of small business expansion in urban areas and provide strategies for sustainable planning and development.

The classification and recognition of the shapes of buildings in map space play an important role in spatial cognition, cartographic generalization, and map updating. As buildings in map space are often represented as the vector data, research was conducted to learn the feature representations of the buildings and recognize their shapes based on graph neural networks. Due to the principles of graph neural networks, it is necessary to construct a graph to represent the adjacency relationships between the points (i.e., the vertices of the polygons shaping the buildings), and extract a list of geometric features for each point. This paper proposes a deep point convolutional network to recognize building shapes, which executes the convolution directly on the points of the buildings without constructing the graphs and extracting the geometric features of the points. A new convolution operator named TriangleConv was designed to learn the feature representations of each point by aggregating the features of the point and the local triangle constructed by the point and its two adjacency points. The proposed method was evaluated and compared with related methods based on a dataset consisting of 5010 vector buildings. In terms of accuracy, macro-precision, macro-recall, and macro-F1, the results show that the proposed method has comparable performance with typical graph neural networks of GCN, GAT, and GraphSAGE, and point cloud neural networks of PointNet, PointNet++, and DGCNN in the task of recognizing and classifying building shapes in map space.

Accurately identifying and delineating urban boundaries are the premise for and foundation of the control of disorderly urban sprawl, which is helpful for us to accurately grasp the scale and form of cities, optimize the internal spatial structure and pattern of cities, and guide the expansion of urban spaces in the future. At present, the concept and delineation of urban boundaries do not follow a unified method or standard. However, many scholars have made use of multi-source remote sensing images of various scales and social auxiliary data such as point of interest (POI) data to achieve large-scale, high-resolution, and high-precision land cover mapping and impermeable water surface mapping. The accuracy of small- and medium-scale urban boundary mapping has not been improved to an obvious extent. This study uses multi-temporal Sentinel-2 high-resolution images and POI data that can reflect detailed features of human activities to extract multi-dimensional features and use random forests and mathematical morphology to map the urban boundaries of the city of Zhengzhou. The research results show that: (1) the urban construction land extraction model established with multi-dimensional features has a great improvement in accuracy; (2) when the training sample accounts for 65% of the sample data set, the urban construction land extraction model has the highest accuracy, reaching 96.25%, and the Kappa coefficient is 0.93; (3) the optimized boundary of structural elements with a size of 13 × 13 is selected, which is in good agreement in terms of scope and location with the boundary of FROM-GLC10 (Zhengzhou) and visual interpretations. The results from the urban boundary delineation in this paper can be used as an important database for detailed basic land use mapping within cities. Moreover, the method in this paper has some reference value for other cities in terms of delineating urban boundaries.