Benchmark datasets play an important role in evaluating remote sensing image retrieval (RSIR) methods. At present, several small-scale benchmark datasets for RSIR are publicly available on the web and are mostly collected through the Google Map API or other desktop tools. Because the Google Map API requires the users to have programming skills and other collection tools are not publicly available, this may limit the possibility for a wide range of volunteers to participate in generating large-scale benchmark datasets. To address this challenge, we develop an open access web-based tool V-RSIR that allows volunteers to easily participate in generating new benchmark datasets for RSIR. This web-based tool not only facilitates the remote sensing image label and cropping, but also provides image editing, review, quantity statistics, spatial distribution, sharing, and so on. To validate this tool, we recruit 32 volunteers to label and crop remote sensing images by using the tool. Finally, a new benchmark dataset that contains 38 classes with at least 1500 images per class is created. Then, the new dataset is validated by five handcrafted low-level feature methods and four deep learning high-level feature methods. The experimental results show that the handcrafted low-level feature methods perform worse than the deep learning methods, in which the precision at top 5 can achieve 94%. The evaluation results are consistent with our theoretical understanding and experimental results on the PatternNet dataset. This indicates that our web-based tool can help users generating valid benchmark datasets with volunteers for the RSIR.INDEX TERMS Annotation tool, benchmark dataset, remote sensing image retrieval, volunteers, web-based tool.

Land cover change affects the carbon emissions of ecosystems in some way. The qualitative and quantitative understanding of carbon emissions from human activities (e.g., land cover change, industrial production, etc.) is highly significant for realizing the objective of carbon neutrality. Therefore, this paper used GlobeLand30 land cover maps, annual average normalised difference vegetation index (NDVI) data, annual average net ecosystem productivity (NEP) data and statistical yearbook data from 2000 to 2020 to explore the relationship between land cover change and carbon emissions. Specifically, it included land cover change, carbon storage changes influenced by land cover change, spatial and temporal analysis of carbon sources and sinks, land use intensity change and anthropogenic carbon emissions. The results of the study show that the main land cover changes in Shandong province during 2000–2020 was cultivated land conversion to artificial surfaces. Among them, the area of cultivated land converted to artificial surfaces from 2000 to 2010 was 4930.62 km2, and the proportion of cultivated land converted to artificial surfaces from 2010 to 2020 was as high as 78.35%. The total carbon stock of vegetation affected by land cover change decreased by 463.96 × 104 t and 193.50 × 104 t in 2000–2010 and 2010–2020 respectively. The spatial and temporal distribution of carbon sources and sinks differed more markedly from 2000 to 2020, and land use intensity changes in Shandong Province showed an upward trend. Of the total energy production, industry has the largest energy consumption, followed closely by total energy consumption in transportation, storage and postal services.

No abstract

Automatically extracting buildings from remote sensing images with deep learning is of great significance to urban planning, disaster prevention, change detection, and other applications. Various deep learning models have been proposed to extract building information, showing both strengths and weaknesses in capturing the complex spectral and spatial characteristics of buildings in remote sensing images. To integrate the strengths of individual models and obtain fine-scale spatial and spectral building information, this study proposed a stacking ensemble deep learning model. First, an optimization method for the prediction results of the basic model is proposed based on fully connected conditional random fields (CRFs). On this basis, a stacking ensemble model (SENet) based on a sparse autoencoder integrating U-NET, SegNet, and FCN-8s models is proposed to combine the features of the optimized basic model prediction results. Utilizing several cities in Hebei Province, China as a case study, a building dataset containing attribute labels is established to assess the performance of the proposed model. The proposed SENet is compared with three individual models (U-NET, SegNet and FCN-8s), and the results show that the accuracy of SENet is 0.954, approximately 6.7%, 6.1%, and 9.8% higher than U-NET, SegNet, and FCN-8s models, respectively. The identification of building features, including colors, sizes, shapes, and shadows, is also evaluated, showing that the accuracy, recall, F1 score, and intersection over union (IoU) of the SENet model are higher than those of the three individual models. This suggests that the proposed ensemble model can effectively depict the different features of buildings and provides an alternative approach to building extraction with higher accuracy.

No abstract