With the launch of various remote-sensing satellites, more and more high-spatial resolution remote-sensing (HSR-RS) images are becoming available. Scene classification of such a huge volume of HSR-RS images is a big challenge for the efficiency of the feature learning and model training. The deep convolutional neural network (CNN), a typical deep learning model, is an efficient end-to-end deep hierarchical feature learning model that can capture the intrinsic features of input HSR-RS images. However, most published CNN architectures are borrowed from natural scene classification with thousands of training samples, and they are not designed for HSR-RS images. In this paper, we propose an agile CNN architecture, named as SatCNN, for HSR-RS image scene classification. Based on recent improvements to modern CNN architectures, we use more efficient convolutional layers with smaller kernels to build an effective CNN architecture. Experiments on SAT data sets confirmed that SatCNN can quickly and effectively learn robust features to handle the intra-class diversity even with small convolutional kernels, and the deeper convolutional layers allow spontaneous modelling of the relative spatial relationships. With the help of fast graphics processing unit acceleration, SatCNN can be trained within about 40 min, achieving overall accuracies of 99.65% and 99.54%, which is the state-of-the-art for SAT data sets.

Visual grounding for remote sensing images (RSVG) aims to localize the referred objects in the remote sensing (RS) images according to a language expression. Existing methods tend to align visual and text features followed by concatenation and then employ a fusion Transformer to learn a token representation for final target localization. However, simple fusion Transformer structure fails to sufficiently learn the location representation of referred object from the multi-modal features. Inspired by the detection Transformer, in this paper, we propose a novel language query based Transformer framework for RSVG termed LQVG. Specifically, we adopt the extracted sentence-level text features as the queries, called language queries, to retrieve and aggregate representation information of the referred object from the multi-scale visual features in the Transformer decoder. The language queries are then converted into object embeddings for final coordinate prediction of referred object. Besides, a multi-scale cross-modal alignment module is devised before the multimodal Transformer to enhance the semantic correlation between the visual and text features, thus facilitating the cross-modal decoding process to generate more precise object representation. Moreover, a new RSVG dataset named RSVG-HR is built to evaluate the performance of the RSVG approaches on very high-resolution remote sensing images with inconspicuous objects. Experimental results on two benchmark datasets demonstrate that our proposed method significantly surpasses the comparison methods and achieves state-of-the-art performance. The dataset and code are available at https://github.com/LANMNG/LQVG.

In the era of public participation in government, public emotions and expectations are important considerations influencing urban construction, planning, and management. A desirable urban environment can make people feel at ease and comfortable and contribute to promoting positive public emotions. However, in the process of rapid urban development, the high-density and overloaded urban built environment has triggered people’s mental tension and anxiety and has contributed to negative emotions. Thus, this study aimed to explore the spatial distribution of public emotions and urban built environments in cities and to thoroughly investigate the correlation between urban built environments and public emotions. Considering the lack of dynamic elements analysis and emotions spatial analysis in previous studies, this study takes Wuhan City as an example, uses social media big data as the basis for text emotion analysis, introduces dynamic traffic elements, and establishes a multidimensional urban built environment measurement index system from five aspects: land use, spatial form, road and traffic, green space and open space, and daily life service facilities. Subsequently, the spatial distribution characteristics of public sentiment and urban built environment elements in Wuhan were analyzed. Finally, a geographically weighted regression method was used to analyze the degree of influence of different urban built environment elements on public emotions. The results showed that public emotions in Wuhan are not homogeneously distributed in terms of score and space and that there are significant differences. The urban built environment has a significant influence on public emotions. Higher land use mix, higher road network density, higher number of public transportation facilities, higher number of public open spaces, lower traffic congestion, and impact of freight transportation play important roles in promoting positive emotions. Therefore, in the process of urban construction, planners and decision makers should purposefully improve the quality of the built environment. Measures can include improving the mix of land functions, alleviating traffic congestion, avoiding the negative effects of freight traffic, rationally constructing green and open spaces, and improving various living facilities. This can help contribute toward improving urban functions and urban environments, and promote the construction of a people-oriented healthy city.

As urban sprawl is proven to jeopardize the sustainability system of cities, the identification of urban sprawl is essential for urban studies. Compared with previous related studies which tend to utilize more and more complicated variables to recognize urban sprawl while still retaining an element of uncertainty, this paper instead proposes a simplified model to identify urban sprawl patterns. This is a working theory which is based on a diagram interpretation of the classic urban spatial structure patterns of the Chicago School. The method used in our study is K-means clustering with gridded population density and local spatial entropy. The results and comparison with open population data and mobile phone data verify the assumption and furthermore indicate that the accuracy of source population data will limit the precision of output identification. This article concludes that urban sprawl is mainly dominated by population and surrounding unevenness. Moreover, the Floating Catchment Area (FCA) local spatial entropy method presented in this research brings about an integration of Shannon entropy, Tobler’s first law of geography and the Moore neighborhood, improving the spatial homogeneity and locality of Batty’s Spatial Entropy model which can only be used in a general scope.

With the commercialization of housing and the deepening of urbanization in China, housing prices are having increasing influence on the land market, and thus indirectly affecting urban development. As various spatial features of an urban housing property directly affect its price, the study of this connection has significance for urban planning. The present study uses mainly open internet data of housing prices, supplemented by other data sources, to identify the spatial features of housing prices and the influence factors in a case study city, Wuhan. Methods employed in the study include the hedonic linear regression model, the geographically weighted regression (GWR) model and the artificial neural network (ANN) model, etc. Progress is made in the following two aspects: first, when calculating the influence factors, hierarchical values for accessibility variables of certain public facilities are used instead of simple Euclidean distance and the results shows a better model fit; second, the ANN model shows the best fit in the study, and while the three models all show respective strengths, the combined use of all models offers the possibility of a more comprehensive analysis of the influence factors of housing prices.

Urban functional regions are essential information in parsing urban spatial structure. The rapid and accurate identification of urban functional regions is important for improving urban planning and management. Thanks to its low cost and fast data update characteristics, the Point of Interest (POI) is one of the most common types of open access data. It mainly identifies urban functional regions by analyzing the potential correlation between POI data and the regions. Even though this is an important manifestation of the functional region, the spatial correlation between regions is rarely considered in previous studies. In order to extract the spatial semantic information among regions, a new model, called the Block2vec, is proposed by using the idea of the Skip-gram framework. The Block2vec model maps the spatial correlation between the POIs, as well as the regions, to a high-dimensional vector, in which classification of urban functional regions can be better performed. The results from cluster analysis showed that the high-dimensional vector extracted can well distinguish the regions with different functions. The random forests classification result (Overall accuracy = 0.7186, Kappa = 0.6429) illustrated the effectiveness of the proposed method. This study also verified the potential of the sentence embedding model in the semantic information extraction of POIs.