Landscape Patterns and Building Functions for Urban Land-Use Classification from Remote Sensing Images at the Block Level: A Case Study of Wuchang District, Wuhan, China

CAW: A Remote-Sensing Scene Classification Network Aided by Local Window Attention

Remote-sensing image scene data contain a large number of scene images with different scales. Traditional scene classification algorithms based on convolutional neural networks are difficult to extract complex spatial distribution and texture information in images, resulting in poor classification results. In response to the above problems, we introduce the vision transformer network structure with strong global modeling ability into the remote-sensing image scene classification task. In this paper, the parallel network structure of the local-window self-attention mechanism and the equivalent large convolution kernel is used to realize the spatial-channel modeling of the network so that the network has better local and global feature extraction performance. Experiments on the RSSCN7 dataset and the WHU-RS19 dataset show that the proposed network can improve the accuracy of scene classification. At the same time, the effectiveness of the network structure in remote-sensing image classification tasks is verified through ablation experiments, confusion matrix, and heat map results comparison.

A Combined Convolutional Neural Network for Urban Land-Use Classification with GIS Data

The classification of urban land-use information has become the underlying database for a variety of applications including urban planning and administration. The lack of datasets and changeable semantics of land-use make deep learning methods suffer from low precision, which prevent improvements in the effectiveness of using AI methods for applications. In this paper, we first used GIS data to produce a well-tagged and high-resolution urban land-use image dataset. Then, we proposed a combined convolutional neural network named DUA-Net for complex and diverse urban land-use classification. The DUA-Net combined U-Net and Densely connected Atrous Spatial Pyramid Pooling (DenseASPP) to extract Remote Sensing Imagers (RSIs) features in parallel. Then, channel attention was used to efficiently fuse the multi-source semantic information from the output of the double-layer network to learn the association between different land-use types. Finally, land-use classification of high-resolution urban RSIs was achieved. Experiments were performed on the dataset of this paper, the publicly available Vaihingen dataset and Potsdam dataset with overall accuracy levels reaching 75.90%, 89.71% and 89.91%, respectively. The results indicated that the complex land-use types with heterogeneous features were more difficult to extract than the single-feature land-cover types. The proposed DUA-Net method proved suitable for high-precision urban land-use classification, which will be of great value for urban planning and national land resource surveying.

Comparison of the Novel Probabilistic Self-Optimizing Vectorized Earth Observation Retrieval Classifier with Common Machine Learning Algorithms

The Vectorized Earth Observation Retrieval (VEOR) algorithm is a novel algorithm suited to the efficient supervised classification of large Earth Observation (EO) datasets. VEOR addresses shortcomings in well-established machine learning methods with an emphasis on numerical performance. Its characteristics include (1) derivation of classification probability; (2) objective selection of classification features that maximize Cohen’s kappa coefficient (κ) derived from iterative “leave-one-out” cross-validation; (3) reduced sensitivity of the classification results to imbalanced classes; (4) smoothing of the classification probability field to reduce noise/mislabeling; (5) numerically efficient retrieval based on a pre-computed look-up vector (LUV); and (6) separate parametrization of the algorithm for each discrete feature class (e.g., land cover). Within this study, the performance of the VEOR classifier was compared to other commonly used machine learning algorithms: K-nearest neighbors, support vector machines, Gaussian process, decision trees, random forest, artificial neural networks, AdaBoost, Naive Bayes and Quadratic Discriminant Analysis. Firstly, the comparison was performed using synthetic 2D (two-dimensional) datasets featuring different sample sizes, levels of noise (i.e., mislabeling) and class imbalance. Secondly, the same experiments were repeated for 7D datasets consisting of informative, redundant and insignificant features. Ultimately, the benchmarking of the classifiers involved cloud discrimination using MODIS satellite spectral measurements and a reference cloud mask derived from combined CALIOP lidar and CPR radar data. The results revealed that the proposed VEOR algorithm accurately discriminated cloud cover using MODIS data and accurately classified large synthetic datasets with low or moderate levels of noise and class imbalance. On the contrary, VEOR did not feature good classification skills for significantly distorted or for small datasets. Nevertheless, the comparisons performed proved that VEOR was within the 3–4 most accurate classifiers and that it can be applied to large Earth Observation datasets.

Local Semantic Enhanced ConvNet for Aerial Scene Recognition

Aerial scene recognition is challenging due to the complicated object distribution and spatial arrangement in a large-scale aerial image. Recent studies attempt to explore the local semantic representation capability of deep learning models, but how to exactly perceive the key local regions remains to be handled. In this paper, we present a local semantic enhanced ConvNet (LSE-Net) for aerial scene recognition, which mimics the human visual perception of key local regions in aerial scenes, in the hope of building a discriminative local semantic representation. Our LSE-Net consists of a context enhanced convolutional feature extractor, a local semantic perception module and a classification layer. Firstly, we design a multi-scale dilated convolution operators to fuse multi-level and multi-scale convolutional features in a trainable manner in order to fully receive the local feature responses in an aerial scene. Then, these features are fed into our two-branch local semantic perception module. In this module, we design a context-aware class peak response (CACPR) measurement to precisely depict the visual impulse of key local regions and the corresponding context information. Also, a spatial attention weight matrix is extracted to describe the importance of each key local region for the aerial scene. Finally, the refined class confidence maps are fed into the classification layer. Exhaustive experiments on three aerial scene classification benchmarks indicate that our LSE-Net achieves the state-of-the-art performance, which validates the effectiveness of our local semantic perception module and CACPR measurement.

Urban Food Takeaway Vitality: A New Technique to Assess Urban Vitality

As one of the most important criteria for measuring the quality of urban life and the environment, urban vitality has become the focus of urban-related research and related disciplines with an increasing number of advocates for the rapid and harmonious development of urban cities. Urban takeaway can represent urban vitality, but studies have not investigated this in a quantitative manner. Furthermore, current studies rarely focus on or even mention the urban food takeaway vitality generated by the spatial distribution of urban takeaway. This study first calculated the vitality of urban takeaways based on the urban takeaway distribution, building footprint, Open Street Map (OSM) data, and the Rapidly Exploring Random Tree (RRT). Then, the urban vitality was obtained using Tencent-Yichuxing data and night-time light data, followed by a spatial correlation analysis between the urban takeaway vitality and urban vitality. Finally, the results for Beijing, Shanghai, and Guangzhou were compared, and the following conclusions were drawn: (1) there is a significant spatial correlation between the urban takeaway vitality and urban vitality, but the correlation varies in different cities at different times; and (2) even in the same city, different road and building densities have an impact on the correlation. The urban takeaway vitality proposed in this study can be used as a new index to evaluate the urban vitality, which has important theoretical and practical significance for the sustainable development of future urban cities.

Using SPOT Data and FRAGSTAS to Analyze the Relationship between Plant Diversity and Green Space Landscape Patterns in the Tropical Coastal City of Zhanjiang, China

Urban green spaces provide a host of ecosystem services, the quantity and structure of which play an important role in human well-being. Rapid urbanization may modify urban green spaces, having various effects on plant diversity. Tropical coastal cities have urbanized rapidly in recent decades, but few studies have been conducted with a focus on their green spaces. We studied the responses of cultivated and spontaneous plants, both key components of urban flora, to the landscape structure of urban green spaces and possible social drivers. We analyzed existing relationships between plant diversity indices, urban green space landscape metrics (using Systeme Probatoire d’Observation de la Terre (SPOT) data,), and social factors, including the type, population density, construction age, and GPS coordinates of each Urban Functional Unit, or UFU. We found that UFUs with more green space patches had higher cultivated and spontaneous species richness than those with fewer green space patches. Spontaneous species richness decreased when green space patches became fragmented, and it increased when green space patches were more connected (e.g., via land bridges). Conversely, cultivated species richness increased with green space patch fragmentation. The phylogenetic diversity of both cultivated and spontaneous plants were weakly associated with green space structure, which was strongly driven by land use. Old UFUs and those with larger populations had more green space patches overall, although they tended to be small and fragmented. Green space patch density was found to increase as the UFU age increased. From the viewpoint of knowledge transfer, understanding the effects and drivers of landscape patterns of urban green spaces could inform the development of improved policies and management of urban green space areas.