High Spatial Resolution Remote Sensing Research Articles

PV Identifier: Extraction of small-scale distributed photovoltaics in complex environments from high spatial resolution remote sensing images

The precise location and size of distributed photovoltaics (PVs) is critical to infer the actual installed capacity and assess the remaining PV generation potential, and is therefore the cornerstone of strategic planning for distributed PV deployment. However, identifying small-scale distributed PVs in complex contexts from high spatial resolution remote sensing (HSRRS) images to obtain their information remains an issue. In this study, we propose an advanced deep learning model, called PV Identifier, to enhance the identification accuracy of small-scale PV systems from HSRRS images. PV Identifier uses a fine-grained feature layer (FFL) compatible with the size of PVs to improve the detection capability of the small-scale distributed PVs. At the same time, it effectively distinguishes between PVs and similar background using a novel semantic constraint module (SCM). We test PV Identifier on a distributed PV dataset in California. Experiments show that the inclusion of the FFL positively affects the model's sensitivity to small distributed PVs. Specifically, the PV Identifier with the FFL increases the Recall of identifying residential rooftop PVs by 1.9% compared to the model without the FFL. In addition, the integration of the SCM effectively improves the model's ability to locate residential rooftop PVs in complex environments, resulting in a 1.8% increase in the corresponding Precision. Compared to the four commonly used segmentation models, PV Identifier exhibits superior identification performance for residential rooftop PVs and commercial and industrial PVs, with an Intersection over Union (IoU) of 74.1% and 89.3%, respectively, which is at least 4.1% and 1.8% higher than other models. Overall, PV Identifier provides a viable solution to the problem of identifying small-scale distributed PV in complex backgrounds from HSRRS images.

New Fusion Approach of Spatial and Channel Attention for Semantic Segmentation of Very High Spatial Resolution Remote Sensing Images

New Fusion Approach of Spatial and Channel Attention for Semantic Segmentation of Very High Spatial Resolution Remote Sensing Images

AEDNet: An Attention-Based Encoder–Decoder Network for Urban Water Extraction From High Spatial Resolution Remote Sensing Images

AEDNet: An Attention-Based Encoder–Decoder Network for Urban Water Extraction From High Spatial Resolution Remote Sensing Images

R&D-Net: Integration of Registration-Net and Detection-Net for Identifying Building Changes in High Spatial-Resolution Remote Sensing Images

R&D-Net: Integration of Registration-Net and Detection-Net for Identifying Building Changes in High Spatial-Resolution Remote Sensing Images

Impact of Deep Convolutional Neural Network Structure on Photovoltaic Array Extraction from High Spatial Resolution Remote Sensing Images

Accurate information on the location, shape, and size of photovoltaic (PV) arrays is essential for optimal power system planning and energy system development. In this study, we explore the potential of deep convolutional neural networks (DCNNs) for extracting PV arrays from high spatial resolution remote sensing (HSRRS) images. While previous research has mainly focused on the application of DCNNs, little attention has been paid to investigating the influence of different DCNN structures on the accuracy of PV array extraction. To address this gap, we compare the performance of seven popular DCNNs—AlexNet, VGG16, ResNet50, ResNeXt50, Xception, DenseNet121, and EfficientNetB6—based on a PV array dataset containing 2072 images of 1024 × 1024 size. We evaluate their intersection over union (IoU) values and highlight four DCNNs (EfficientNetB6, Xception, ResNeXt50, and VGG16) that consistently achieve IoU values above 94%. Furthermore, through analyzing the difference in the structure and features of these four DCNNs, we identify structural factors that contribute to the extraction of low-level spatial features (LFs) and high-level semantic features (HFs) of PV arrays. We find that the first feature extraction block without downsampling enhances the LFs’ extraction capability of the DCNNs, resulting in an increase in IoU values of approximately 0.25%. In addition, the use of separable convolution and attention mechanisms plays a crucial role in improving the HFs’ extraction, resulting in a 0.7% and 0.4% increase in IoU values, respectively. Overall, our study provides valuable insights into the impact of DCNN structures on the extraction of PV arrays from HSRRS images. These findings have significant implications for the selection of appropriate DCNNs and the design of robust DCNNs tailored for the accurate and efficient extraction of PV arrays.

Emerging Signal of Englacial Debris on One Clean Surface Glacier Based on High Spatial Resolution Remote Sensing Data in Northeastern Tibetan Plateau

The Tibetan Plateau contains a large number of mountain glaciers with clean surfaces, where englacial debris is generally entrained by the ice flow and exposed at the glacier margins. The long-term observation on one of the typical clean surface glaciers (the Qiyi Glacier, northern Tibetan Plateau) suggests an early emergence of englacial debris on its transport pathway, with accelerated surface melting from the mid-2000s onwards. Given that the englacial debris layers of the tongue part of Qiyi Glacier are approximately parallel to the glacier surface, the continuing melting might be expected to result in the rapid expansion of exposed debris. Compared with the clean surface ice, debris cover at the same elevation reduced glacier mass loss by ~25.4% during a hydrological year (2020–2021), indicating that the early emergence of englacial debris can protect the glacier from climate warming with prolonged life expectance. As such, future glacial runoff will then reach its peak earlier and be followed by a gentler decreasing trend than model projections with constant clean surface ice. These findings imply that the emerging debris on clean surface glacier may mitigate the glacial-runoff risk, which has so far been neglected in projections of future water supplies.

A lightweight and stochastic depth residual attention network for remote sensing scene classification

AbstractDue to the rapid development of satellite technology, high‐spatial‐resolution remote sensing (HRRS) images have highly complex spatial distributions and multiscale features, making the classification of such images a challenging task. The key to scene classification is to accurately understand the main semantic information contained in images. Convolutional neural networks (CNNs) have outstanding advantages in this field. Deep CNNs (D‐CNNs) with better performance tend to have more parameters and higher complexity. However, shallow CNNs have difficulty extracting the key features of complex remote sensing images. In this paper, we propose a lightweight network with a random depth strategy for remote sensing scene classification (LRSCM). We construct a convolutional feature extraction module, DCAB, which incorporates depthwise separable convolutional and inverted residual structures, effectively reducing the numbers of required parameters and computations, and retains and utilizes low‐level features. In addition, coordinate attention (CA) is integrated into the module, thereby further improving the network's ability to extract key local information. To further reduce the complexity of model training, the residual module adopts a stochastic depth strategy, providing the network with a random depth. Comparative experiments on five public datasets show that the LRSCM network can achieve results comparable to those of other state‐of‐the‐art methods.

Semantic understanding of high spatial resolution remote sensing images using directional geospatial relationships

ABSTRACT Semantic understanding of high spatial resolution remote sensing (RS) images can be divided into object detection, object labelling, identification of geospatial relationships, and semantic description generation. Geographical relations represent the spatial distribution dependencies between geospatial entities such as points, lines, and polygons, and the topologies among them. Geospatial relations play a very important role in describing the relations between geographic objects. These relations can be broadly classified as topological, directional, and proximity relations. These relations describe the adjacency and association relations between geospatial objects. An approach to identify an appropriate directional geospatial relationship between geo-objects present in high spatial resolution RS images is proposed in this paper. Geospatial objects in the form of the closed boundary are taken as input and relationship triplets are generated. Two approaches have been used in the identification of directional relationships and the results of both approaches are compared. The first approach is based on the centroid of the objects and the second considers whole objects while calculating the direction. These relations are then further represented using a knowledge graph, where nodes represent objects and edges represent their relationship. Knowledge graph plays a very important role in overall scene understanding. It shows the association of all objects with each other. These relationships are then represented in the form of descriptions by using template-based sentence generation. Results show that these directional relationships are accurately identified between each pair of objects using both approaches, but relations generated by considering whole objects are closer to human cognition. Semantic understanding of remote sensing images is of great significance in different applications such as urban surveys, urban planning, and management, military intelligence, etc.

Data Augmentation Method for Extracting Partially Occluded Roads From High Spatial Resolution Remote Sensing Images

Data Augmentation Method for Extracting Partially Occluded Roads From High Spatial Resolution Remote Sensing Images

Building Extraction From High Spatial Resolution Remote Sensing Images of Complex Scenes by Combining Region-Line Feature Fusion and OCNN

Building extraction from remote sensing imagery has been a research hotspot for some time with the advancement of AI in remote sensing. However, the edges of buildings extracted using existing techniques are commonly broken and inaccurate for the complex scenes in suburban and rural areas. This study proposes a framework for extracting structures by combining region-line feature fusion with object-based convolutional neural networks to solve this problem. First, a building edge detection network known as the Multichannel Attention-based Dense Extreme Inception Network for Edge Detection (MA-DexiNed) is constructed, which is considered more accurate for building edge extraction in complicated image scenes. Second, the probability map of the building edges obtained by MA-DexiNed is refined. According to rule judgment, breakpoints are linked by an edge thinning connection algorithm to obtain single-pixel, contiguous building line features. Third, the geometric boundaries of buildings are obtained by combining region attributes derived by unsupervised image segmentation and line features obtained from deep learning supervised segmentation. Finally, the pretrained AlexNet is employed to identify the class characteristics of buildings. The suggested framework was used for two GF-2 images and one Google Earth image from various regions and with numerous types of complicated scenes. The experimental findings demonstrated that this approach could extract more precise and complete building edges for complex image scenes compared with several existing methods. This advancement results from constrained regional image segmentation using deep semantic edge features. This methodology can offer a benchmark for subsequent building extraction tasks from high resolution imagery.

Multi-Level Dynamic Analysis of Landscape Patterns of Chinese Megacities during the Period of 2016–2021 Based on a Spatiotemporal Land-Cover Classification Model Using High-Resolution Satellite Imagery: A Case Study of Beijing, China

In today’s accelerating urbanization process, timely and effective monitoring of land-cover dynamics, landscape pattern analysis, and evaluation of built-up urban areas (BUAs) have important research significance and practical value for the sustainable development, planning and management, and ecological protection of cities. High-spatial-resolution remote sensing (HRRS) images have the advantages of high-accuracy Earth observations, covering a large area, and having a short playback period, and they can objectively and accurately provide fine dynamic spatial information about the land cover in urban built-up areas. However, the complexity and comprehensiveness of the urban structure have led to a single-scale analysis method, which makes it difficult to accurately and comprehensively reflect the characteristics of the BUA landscape pattern. Therefore, in this study, a joint evaluation method for an urban land-cover spatiotemporal-mapping chain and multi-scale landscape pattern using high-resolution remote sensing imagery was developed. First, a pixel–object–knowledge model with temporal and spatial classifications was proposed for the spatiotemporal mapping of urban land cover. Based on this, a multi-scale district–BUA–city block–land cover type map of the city was established and a joint multi-scale evaluation index was constructed for the multi-scale dynamic analysis of the urban landscape pattern. The accuracies of the land cover in 2016 and 2021 were 91.9% and 90.4%, respectively, and the kappa coefficients were 0.90 and 0.88, respectively, indicating that the method can provide effective and reliable information for spatial mapping and landscape pattern analysis. In addition, the multi-scale analysis of the urban landscape pattern revealed that, during the period of 2016–2021, Beijing maintained the same high urbanization rate in the inner part of the city, while the outer part of the city kept expanding, which also reflects the validity and comprehensiveness of the analysis method developed in this study.

CA-BASNet: A Building Extraction Network in High Spatial Resolution Remote Sensing Images

Aiming at the problems of holes, misclassification, and rough edge segmentation in building extraction results from high spatial remote sensing images, a coordinate attention mechanism fusion network based on the BASNet network (CA-BASNet) is designed for building extraction in high spatial remote sensing images. Firstly, the deeply supervised encoder–decoder network was used to create a rough extract of buildings; secondly, to make the network pay more attention to learning building edge features, the mixed loss function composed of binary cross entropy, structural similarity and intersection-over-union was introduced into the network training process; finally, the residual optimization module of fusion coordinate attention mechanism was used for post-processing to realize the fine extraction of buildings from high spatial resolution remote sensing images. Experiments on the WHU building dataset show that the proposed network can achieve mIoU of 93.43%, mPA of 95.86%, recall of 98.79%, precision of 90.13% and F1 of 91.35%. Compared with the existing semantic segmentation networks, such as PSPNet, SegNet, DeepLapV3, SE-UNet, and UNet++, the accuracy of the proposed network and the integrity of object edge segmentation are significantly improved, which proves the effectiveness of the proposed network.

A Superpixel Spatial Intuitionistic Fuzzy C-Means Clustering Algorithm for Unsupervised Classification of High Spatial Resolution Remote Sensing Images

This paper proposes a superpixel spatial intuitionistic fuzzy C-means (SSIFCM) clustering algorithm to address the problems of misclassification, salt and pepper noise, and classification uncertainty arising in the pixel-level unsupervised classification of high spatial resolution remote sensing (HSRRS) images. To reduce information redundancy and ensure noise immunity and image detail preservation, we first use a superpixel segmentation to obtain the local spatial information of the HSRRS image. Secondly, based on the bias-corrected fuzzy C-means (BCFCM) clustering algorithm, the superpixel spatial intuitionistic fuzzy membership matrix is constructed by counting an intuitionistic fuzzy set and spatial function. Finally, to minimize the classification uncertainty, the local relation between adjacent superpixels is used to obtain the classification results according to the spectral features of superpixels. Four HSRRS images of different scenes in the aerial image dataset (AID) are selected to analyze the classification performance, and fifteen main existing unsupervised classification algorithms are used to make inter-comparisons with the proposed SSIFCM algorithm. The results show that the overall accuracy and Kappa coefficients obtained by the proposed SSIFCM algorithm are the best within the inter-comparison of fifteen algorithms, which indicates that the SSIFCM algorithm can effectively improve the classification accuracy of HSRRS image.

Feature Enhanced Anchor-Free Network for School Detection in High Spatial Resolution Remote Sensing Images

Object detection in remote sensing images (RSIs) is currently one of the most important topics, which can promote the understanding of the earth and better serve for the construction of digital earth. In addition to single objects, there are many composite objects in RSIs, especially primary and secondary schools (PSSs), which are composed of some parts and surrounded by complex background. Existing deep learning methods have difficulty detecting composite objects effectively. In this article, we propose a feature enhanced Network (FENet) based on an anchor-free method for PSSs detection. FENet can not only realize more accurate pixel-level detection based on enhanced features but also simplify the training process by avoiding hyper-parameters. First, an enhanced feature module (EFM) is designed to improve the representation ability of complex features. Second, a context-aware strategy is used for alleviating the interference of background information. In addition, complete intersection over union (CIoU) loss is employed for bounding box regression, which can obtain better convergence speed and accuracy. At the same time, we build a PSSs dataset for composite object detection. This dataset contains 1685 images of PSSs in Beijing–Tianjin–Hebei region. Experimental results demonstrate that FENet outperforms several object detectors and achieves 78.7% average precision. The study demonstrates the advantage of our proposed method on PSSs detection.

Quantitative Analysis on Coastline Changes of Yangtze River Delta Based on High Spatial Resolution Remote Sensing Images

The coastline situation reflects socioeconomic development and ecological environment in coastal zones. Analyzing coastline changes clarifies the current coastline situation and provides a scientific basis for making environmental protection policies, especially for coastlines with significant human interference. As human activities become more intense, coastline types and their dynamic changes become more complicated, which needs more detailed identification of coastlines. High spatial resolution images can help provide detailed large spatial coverage at high resolution information on coastal zones. This study aims to map the position and status of the Yangtze River Delta (YRD) coastline using an NDWI threshold method based on 2 m Gaofen-1/Ziyuan-3 imagery and analyze coastline change and coastline type distribution characteristics. The results showed that natural and artificial coastlines in the YRD region accounted for 42.73% and 57.27% in 2013 and 41.56% and 58.44% in 2018, respectively. The coastline generally advanced towards the sea, causing a land area increase of 475.62 km2. The changes in the YRD coastline mainly resulted from a combination of large-scale artificial construction and natural factors such as silt deposition. This study provides a reference source for large spatial coverage at high resolution remote sensing coastline monitoring and a better understanding of land use in coastal zone.

$\text{A}^{3}$Seg: An Annealing Augmented and Aligned Semantic Segmentation Network for High Spatial Resolution Remote Sensing Images

Semantic segmentation of high spatial resolution (HSR) remote sensing images (RSIs) plays an important role in many applications. However, HSR RSIs have significantly larger spatial sizes than typical natural images, which results in fewer valuable samples when training models. In addition, fusing multiscale features is the key step in obtaining features with strong semantic and high spatial information. However, current feature fusion methods are too straightforward to address misalignment issues. To handle these two problems, we propose an annealing augmented and aligned segmentation network, named <inline-formula><tex-math notation="LaTeX">$\text{A}^{3}$</tex-math></inline-formula>Seg. Specifically, we propose an annealing online hard example mining (AOHEM) strategy to automatically select more valuable samples during the training stage. Based on AOHEM, a contextual augmentation block is proposed to extract sufficient contextual information using three different attention mechanisms in consideration of three different feature properties. Finally, we propose a novel feature alignment block to fuse features at different levels by alignment with the guidance of a salient feature. Experimental results on three different HSR RSIs datasets demonstrate that the proposed method outperforms the state-of-the-art general semantic segmentation methods with a better tradeoff between accuracy and complexity.

High Spatial Resolution Remote Sensing Data Classification Method Based on Spectrum Sharing

Existing remote sensing data classification methods cannot achieve the sharing of remote sensing image spectrum, leading to poor fusion and classification of remote sensing data. Therefore, a high spatial resolution remote sensing data classification method based on spectrum sharing is proposed. A page frame recovery algorithm (PFRA) is introduced to allocate the wireless spectrum resources in low-frequency band, and a dynamic spectrum sharing mechanism is designed between the primary and secondary users of remote sensing images. Based on this, D-S evidence theory is used to fuse high spatial resolution remote sensing data and correct the pixel brightness of the fused multispectral image. The initial data are normalized, the feature of spectral image is extracted, the convolution neural network classification model is constructed, and the remote sensing image is segmented. Experimental results show that the proposed method takes shorter time and has higher accuracy for high spatial resolution image segmentation. High spatial resolution remote sensing data classification is more efficient, and the accuracy of data classification and remote sensing image fusion are more ideal.

Greenhouse extraction with high-resolution remote sensing imagery using fused fully convolutional network and object-oriented image analysis

The wide application of agricultural greenhouses globally has brought economic benefits; however, it has also led to many environmental problems. The timely and accurate acquisition of greenhouse areas and distribution is valuable for authorities seeking to optimize regional agricultural management and mitigate environmental pollution. Automatic extraction of the greenhouses from high spatial resolution remote sensing (RS) imagery based on deep learning can reduce labor costs and improve operational efficiency to have better application prospects. In this paper, we propose a multi-channel fused fully convolutional network (FCN) optimized by the optimal scale object-oriented segmentation results for agricultural greenhouse extraction from high spatial resolution RS imagery. First, to make full use of remote sensing feature images of target objects and to not increase the complexity of the deep learning network, we constructed a decision-level fusion FCN network that can simultaneously input multiple remote sensing images for preliminary extraction of greenhouse. Second, to address a defect in the classical FCN network causing the easy loss of ground object details, we optimized the preliminary extraction results from FCN by the results of object-oriented segmentation. Finally, the optimized greenhouse extraction results were processed by the mathematical morphology, and the final extraction results were obtained. The experimental results demonstrate that: (1) Multi-channel fused FCN model could use the unique spectral characteristics of different ground objects. (2) Optimized initial extraction results from FCN based on the optimal scale object-oriented segmentation results could fully maintain the edge details of the greenhouse. Experimental results show that the proposed method can extract the greenhouse effectively. The precision and F value of our proposed method are 92.68% and 0.94.

Cross-Domain Scene Classification Based on a Spatial Generalized Neural Architecture Search for High Spatial Resolution Remote Sensing Images

By labelling high spatial resolution (HSR) images with specific semantic classes according to geographical properties, scene classification has been proven to be an effective method for HSR remote sensing image semantic interpretation. Deep learning is widely applied in HSR remote sensing scene classification. Most of the scene classification methods based on deep learning assume that the training datasets and the test datasets come from the same datasets or obey similar feature distributions. However, in practical application scenarios, it is difficult to guarantee this assumption. For new datasets, it is time-consuming and labor-intensive to repeat data annotation and network design. The neural architecture search (NAS) can automate the process of redesigning the baseline network. However, traditional NAS lacks the generalization ability to different settings and tasks. In this paper, a novel neural network search architecture framework—the spatial generalization neural architecture search (SGNAS) framework—is proposed. This model applies the NAS of spatial generalization to cross-domain scene classification of HSR images to bridge the domain gap. The proposed SGNAS can automatically search the architecture suitable for HSR image scene classification and possesses network design principles similar to the manually designed networks. To obtain a simple and low-dimensional search space, the traditional NAS search space was optimized and the human-the-loop method was used. To extend the optimized search space to different tasks, the search space was generalized. The experimental results demonstrate that the network searched by the SGNAS framework with good generalization ability displays its effectiveness for cross-domain scene classification of HSR images, both in accuracy and time efficiency.

Damage Assessment of a Salt Dome in Jizan, Southwestern Saudi Arabia, Using High Spatial Resolution Remote Sensing Data

The salt dome in Jizan, southwestern Saudi Arabia, has caused several problems related to underground dissolution, particularly in the old part of the city. Examples of these problems include surface collapse, building failure, fracturing, tilting, and road cracking. Analysis of the salt dome using X-ray diffraction (XRD) revealed the dominance of gypsum, anhydrite, and halite. This study evaluates the damage assessment using multitemporal high spatial resolution data of the GeoEye-1, and QuickBird-2 sensors. Change detection technique, textural analysis, and visual interpretation were applied to these data. Analysis of the data recorded before and after a particular damage event revealed that three neighborhoods located above the Jizan salt dome—Al-Ashaima, Shamiya, and Aljabal—were affected to the greatest extent. The entire residential neighborhood of Al-Ashaima was evacuated, and the buildings located in it were demolished. Several buildings in the Shamiya and Aljabal neighborhoods were also demolished. Therefore, high spatial remote sensing data are effective in assessing building damage and for anticipating future damage, thus benefiting decision making for the affected cities.