Urban impervious surface (UIS) offers potentially valuable information for the development of sustainable urban management strategies and environmental change monitoring actions. In this article, we focus on UIS-detection-related issues, identify and analyze systematic challenges, construct a general processing scheme for UIS detection, provide four categories of major methods, and propose a deep compressive-based convolutional deep belief network (dc-CDBN) method and a novel classification strategy for multisource data fusion models.

This paper presents a novel framework to achieve 3D semantic labeling of objects (e.g., trees, buildings, and vehicles) from airborne laser-scanning point clouds. To this end, we propose a framework which consists of hierarchical clustering and higher-order conditional random fields (CRF) labeling. In the hierarchical clustering, the raw point clouds are over-segmented into a set of fine-grained clusters by integrating the point density clustering and the classic K-means clustering algorithm, followed by the proposed probability density clustering algorithm. Through this process, we not only obtain a more uniform size and more homogeneous clusters with semantic consistency, but the topological relationships of the cluster’s neighborhood are implicitly maintained by turning the problem of topology maintenance into a clustering problem based on the proposed probability density clustering algorithm. Subsequently, the fine-grained clusters and their topological context are fed into the CRF labeling step, from which the fine-grained cluster’s semantic labels are learned and determined by solving a multi-label energy minimization formulation, which simultaneously considers the unary, pairwise, and higher-order potentials. Our experiments of classifying urban and residential scenes demonstrate that the proposed approach reaches 88.5% and 86.1% of “m $F_1$ ” estimated by averaging all classes of the $F_1$ -scores. We prove that the proposed method outperforms five other state-of-the-art methods. In addition, we demonstrate the effectiveness of the proposed energy terms by using an “ablation study” strategy.

Vegetation measures are crucial for assessing changes in the ecological environment. Fractional vegetation cover (FVC) provides information on the growth status, distribution characteristics, and structural changes of vegetation. An in-depth understanding of the dynamic changes in urban FVC contributes to the sustainable development of ecological civilization in the urbanization process. However, dynamic change detection of urban FVC using multi-temporal remote sensing images is a complex process and challenge. This paper proposed an improved FVC estimation model by fusing the optimized dynamic range vegetation index (ODRVI) model. The ODRVI model improved sensitivity to the water content, roughness degree, and soil type by minimizing the influence of bare soil in areas of sparse vegetation cover. The ODRVI model enhanced the stability of FVC estimation in the near-infrared (NIR) band in areas of dense and sparse vegetation cover through introducing the vegetation canopy vertical porosity (VCVP) model. The verification results confirmed that the proposed model had better performance than typical vegetation index (VI) models for multi-temporal Landsat images. The coefficient of determination (R²) between the ODRVI model and the FVC was 0.9572, which was 7.4% higher than the average R² of other typical VI models. Moreover, the annual urban FVC dynamics were mapped using the proposed improved FVC estimation model in Hefei, China (1999–2018). The total area of all grades FVC decreased by 33.08% during the past 20 years in Hefei, China. The areas of the extremely low, low, and medium grades FVC exhibited apparent inter-annual fluctuations. The maximum standard deviation of the area change of the medium grade FVC was 13.35%. For other grades of FVC, the order of standard deviation of the change ratio was extremely low FVC > low FVC > medium-high FVC > high FVC. The dynamic mapping of FVC revealed the influence intensity and direction of the urban sprawl on vegetation coverage, which contributes to the strategic development of sustainable urban management plans.

Hyperspectral images (HSIs) provide unique capabilities for urban impervious surfaces (UIS) extraction. This paper proposes a multi-feature extraction model (MFEM) for UIS detection from HSIs. The model is based on a nonlinear dimensionality reduction technique, t-distributed stochastic neighbor embedding (t-SNE), and the deep learning method convolutional deep belief networks (CDBNs). We improved the two methods to create a novel MFEM consisting of improved t-SNE, deep compression CDBNs (d-CDBNs), and a logistic regression classifier. The improved t-SNE method provides dimensionality reduction and spectral feature extraction from the original HSIs and the d-CDBNs algorithm extracts spatial feature and edges using the reduced dimensional datasets. Finally, the extracted features are combined into multi-feature for the impervious surface detection using the logistic regression classifier. After comparing with the commonly used methods, the current experimental results demonstrate that the proposed MFEM model provides better performance for UIS extraction and detection from HSIs.

Accurate mapping urban impervious surfaces (UIS) from satellite images is crucial for understanding urban land cover change directions and addressing UIS change-induced environmental issues. The UIS index is an effective way to reduce the computational cost of processing remote sensing imageries although continuous UIS detection from multitemporal Landsat images, repeated fine-tuning, and reselection for a proper threshold should be considered. In this article, we proposed a novel UIS index and an improved particle swarm optimization (PSO)-based UIS automatic threshold selection model (UISAT) to overcome those shortages when detecting UIS derived from multitemporal Landsat images. The proposed UIS index transformed different temporal Landsat images into index images with distinguishable pixel values for each gray pixel. In this way, the pixel gray values representing UIS were enhanced, and non-UIS was weakened with lower gray scales in the transformed index images. Next, an automatic threshold selection strategy was developed to enhance the applicability of the PSO model in terms of threshold fine-tuning and reselection. Then, we performed comprehensive assessments for the UISAT model, including in comparison to an improved convolutional deep belief network for relative accuracy verification, random points matching with Google Earth images, and comparing to other typical indices. The results demonstrated that the UISAT model provided the best performance in UIS detection from multitemporal Landsat images. The producer’s accuracies (PAs) of UISAT results in Beijing, Hefei, and Guangzhou, China, were 91.73%, 93.87%, and 92.84%, while the user’s accuracies (UA) were at 91.51%, 93.35%, and 92.24%. The proposed model outperformed the existing commonly used UIS indices [e.g., the Biophysical Composition Index (BCI), the Combinational Build-up Index (CBI), the Genetic Algorithm-based Urban Cluster Automatic Threshold (GA-UCAT), and the Gaussian-based Automatic Threshold Modified Normalized Difference Impervious Surface Index (G-MNDISI)] by an average increase of 6.51% in overall accuracy.