For hyperspectral remote sensing image (HSI) classification, the learning process of deep neural networks has been progressively advanced in depth, but the fine features are often largely lost or even disappear in the process of depth transfer. With the increase in feature aggregation and connectivity, the complexity of the network and the training parameters increases greatly, requiring more training time. This paper proposed a multi-scale dense network (MSDN) for HSI classification that made full use of different scale information in the network structure and combined scale information throughout the network. It implemented feature extraction of HSIs in two dimensions, including the features at fine and coarse levels. In the horizontal direction, it considered the deep extraction of HSI features, and the 3-D dense connection structure was used for aggregating features at different levels. In the vertical direction, scale information was considered, and three-scale feature maps at low, middle, and high levels were generated based on the first layer of the network. The MSDN used stride convolution for downsampling and combined feature information at different scale levels. The MSDN extracted features along the diagonal line. The network implemented the reconstruction of deep feature extraction and multi-scale fusion for HSI classification. The MSDN model performed well on representative HSI datasets, namely, the Indian Pines, Pavia University, Salinas, Botswana, and Kennedy Space Center datasets. It improved the training speed and accuracy for HSI classification and especially improved the convergence speed, which effectively saved computing resources and had high stability.

Semantic segmentation of remote sensing images is an important but unsolved problem in the remote sensing society. Advanced image semantic segmentation models, such as DeepLabv3+, have achieved astonishing performance for semantically labeling very high resolution (VHR) remote sensing images. However, it is difficult for these models to capture the precise outlines of ground objects and explore the context information that revealing relationships among image objects for optimizing segmentation results. Consequently, this study proposes a semantic segmentation method for VHR images by incorporating deep learning semantic segmentation model (DeepLabv3+) and object-based image analysis (OBIA), wherein DSM is employed to provide geometric information to enhance the interpretation of VHR images. The proposed method first obtains two initial probabilistic labeling predictions using a DeepLabv3+ network on spectral image and a random forest (RF) classifier on hand-crafted features, respectively. These two predictions are then integrated by Dempster-Shafer (D-S) evidence theory to be fed into an object-constrained higher-order conditional random field (CRF) framework to estimate the final semantic labeling results with the consideration of the spatial contextual information. The proposed method is applied to the ISPRS 2D semantic labeling benchmark, and competitive overall accuracies of 90.6% and 85.0% are achieved for Vaihingen and Potsdam datasets, respectively.

Urban functional zones (UFZs) are important for urban sustainability and urban planning and management, but UFZ maps are rarely available and up-to-date in developing countries due to frequent economic and human activities and rapid changes in UFZs. Current methods have focused on mapping UFZs in a small area with either remote sensing images or open social data, but large-scale UFZ mapping integrating these two types of data is still not be applied. In this study, a novel approach to mapping large-scale UFZs by integrating remote sensing images (RSIs) and open social data is proposed. First, a context-enabled image segmentation method is improved to generate UFZ units by incorporating road vectors. Second, the segmented UFZs are classified by coupling Latent Dirichlet Allocation (LDA) and Support Vector Machine (SVM). In the classification framework, physical features from RSIs and social attributes from POI (Point of Interest) data are integrated. A case study of Beijing was performed to evaluate the proposed method, and an overall accuracy of 85.9% was achieved. The experimental results demonstrate that the presented method can provide fine-grained UFZs, and the fusion strategy of RSIs and POI data can distinguish urban functions accurately. The proposed method appears to be promising and practical for large-scale UFZ mapping.

The non-uniformity of the relationships between urban temperature and landscape has attracted board attention. The non-uniformity in urban areas is reflected in the spatial landscape’s heterogeneity and the difference of socio-economic functions. The former is shown as the spatial differentiation of land-cover, land-use, landscape composition, and configuration, while the latter leads to the difference of the intensity of human activities and population density, which are closely related with anthropogenic heat emission. Therefore, this study introduces urban functional zones (UFZs) to express urban spatial heterogeneity. This study also attempts to comprehend urban heat island (UHI) effects and discloses the variability of urban surface temperature (LST)–landscape relationships in different kinds of UFZs. There are two main technical difficulties—how to characterize the spatial heterogeneity of UFZs and how to quantify non-uniform LST effects. A three-level variable system is established from their attributes, inner structures, and interrelationships to characterize UFZs and their LST effects hierarchically. Considering the multi-collinearity among high-dimensional variables, the Elastic Net regression method is selected for quantitative analysis. The experimental results reveal the deficiency of uniform LST analysis for heterogeneous urban areas and verify the variable relationships of LST-landscaped with different kinds of UFZs.

Although much efforts have been made to develop automatic methods for building extraction from very high-resolution (VHR) imagery during the past 30 years; the methods with high performance are still unavailable due to the three issues: uncertainty of segmentation scales, selection of effective features, and sample selection. In this study, by introducing GIS data, a parameter mining approach is proposed to (1) mine parameter information for building extraction, and (2) detect changes of buildings between VHR imagery and GIS data. For the first target, the learning mechanism is proposed for identifying optimal segmentation scales, feature subsets, and samples. For the second target, the discovered information (i.e., optimal segmentation scales, feature subsets, and selected samples) is applied to classify the VHR imagery with a multilevel random forest (RF) classifier. The proposed approach is validated on two datasets: Dataset 1 and Dataset 2. The knowledge of building extraction is first learned from Dataset 1 and then used to classify both datasets, and change detection is conducted on Dataset 1. Results of change detection in Dataset 1 indicate that the false alarm ratio and omission error of increased buildings are 20.1% and 8.4%, while the false alarm ratio and omission error of destroyed buildings are 19.1% and 11.3%, respectively. Results of building extraction in Dataset 2 revealed scores of 81.50% and 81.09% at pixel- and object-based evaluation levels. Accordingly, our proposed method is successful in building extraction and change detection.

Urban functional zones, such as commercial, residential, and industrial zones, are basic units of urban planning, and play an important role in monitoring urbanization. However, historical functional-zone maps are rarely available for cities in developing countries, as traditional urban investigations focus on geographic objects rather than functional zones. Recent studies have sought to extract functional zones automatically from very-high-resolution (VHR) satellite images, and they mainly concentrate on classification techniques, but ignore zone segmentation which delineates functional-zone boundaries and is fundamental to functional-zone analysis. To resolve the issue, this study presents a novel segmentation method, geoscene segmentation, which can identify functional zones at multiple scales by aggregating diverse urban objects considering their features and spatial patterns. In experiments, we applied this method to three Chinese cities—Beijing, Putian, and Zhuhai—and generated detailed functional-zone maps with diverse functional categories. These experimental results indicate our method effectively delineates urban functional zones with VHR imagery; different categories of functional zones extracted by using different scale parameters; and spatial patterns that are more important than the features of individual objects in extracting functional zones. Accordingly, the presented multiscale geoscene segmentation method is important for urban-functional-zone analysis, and can provide valuable data for city planners.