Building extraction is significant for the intelligent interpretation of high-resolution remote sensing images (HRSI). However, in some complex scenarios where the features of the building and its adjacent ground objects are similar, the current segmentation model cannot distinguish them effectively. Therefore, we propose a complex scenarios adaptive network (CSA-Net) for building extraction. CSA-Net is comprised of the hierarchical-context feature extraction (HFE) module, the global-local feature interaction (GFI) module, and the multiscale-adaptive feature fusion (MFF) structure. The HFE obtains high-level semantic information at different levels and fuses it with low-level detailed information by skipping connections to enhance the reasoning and perception ability of building structure in complex scenes. Then, the GFI acquires global-local features of buildings and their surrounding environment via dense multiscale dilated convolution. The information can be shared through efficient interaction among features, and irrelevant backgrounds can be suppressed. Then, in the up-sampling process, the MFF alleviates the feature loss and enhances the robustness of the network by using feature fusion after layer-by-layer adaptive weight allocation. Experiments show that CSA-Net outperforms other comparable methods, with intersection over union (IoU) values of 79.99%, 89.75%, and 73.59%, respectively, on the Google Arlinton (GA), WHU, and Massachusetts building datasets. The visual comparison results demonstrate that our method can enhance the accuracy of building extraction in complex scenes. Meanwhile, the efficiency results indicate our approach strikes a balance between calculation parameters and time and achieves high levels of efficiency. (Github: https://github.com/329719386/CSA-Net)

Individual tree extraction is an important process for forest resource surveying and monitoring. To obtain more accurate individual tree extraction results, this paper proposed an individual tree extraction method based on transfer learning and Gaussian mixture model separation. In this study, transfer learning is first adopted in classifying trunk points, which can be used as clustering centers for tree initial segmentation. Subsequently, principal component analysis (PCA) transformation and kernel density estimation are proposed to determine the number of mixed components in the initial segmentation. Based on the number of mixed components, the Gaussian mixture model separation is proposed to separate canopies for each individual tree. Finally, the trunk stems corresponding to each canopy are extracted based on the vertical continuity principle. Six tree plots with different forest environments were used to test the performance of the proposed method. Experimental results show that the proposed method can achieve 87.68% average correctness, which is much higher than that of other two classical methods. In terms of completeness and mean accuracy, the proposed method also outperforms the other two methods.

When using the traditional Douglas–Peucker (D–P) algorithm to simplify linear objects, it is easy to generate results containing self-intersecting errors, thus affecting the application of the D–P algorithm. To solve the problem of self-intersection, a new vector line simplification algorithm based on the D–P algorithm, monotonic chains and dichotomy, is proposed in this paper. First, the traditional D–P algorithm is used to simplify the original lines, and then the simplified lines are divided into several monotonic chains. Second, the dichotomy is used to search the intersection positions of monotonic chains effectively, and intersecting monotonic chains are processed, thus solving the self-intersection problems. Two groups of experimental data are selected based on large data sets. Results demonstrate that the proposed experimental method has advantages in algorithmic efficiency and accuracy when compared to the D–P algorithm and the Star-shaped algorithm.

The evaluation of urban economies has been one key concern identified by scholars. In the past, most research methods on urban development assessments have been based on statistical data, and the analysis results have been presented in the form of statistical tables. Moreover, the development of urban road networks reflects the status of urban development and spatial metrics, which are obtained from the urban road network which can be used to evaluate the growth of the urban economy. The OpenStreetMap (OSM) is collected through crowdsourcing, and the OSM road network has the characteristics of a simplified and efficient approach to collect data, update data, free available data, etc. Therefore, in this paper, the OSM road network density is used as a spatial metric which is taken as the main study subject, to evaluate the economic development of Chinese cities. In our experiment, results show that there is a significant regression correlation between the OSM road network density and municipal gross domestic product (GDP). For the 85 selected Chinese cities, a total of 71 cities with residuals between −0.1 and 0.1 account for 83.53%, and a total of 79 cities with residuals between −0.2 and 0.2 account for 92.94%. Therefore, it is apparent that the OSM road network density can be used as a spatial metric to evaluate the municipal GDP, and as a result, can be used by local governments and scholars to estimate, evaluate, and forecast the urban economic development of China.

The joint utilization of multi-source data is of great significance in geospatial observation applications, such as urban planning, disaster assessment, and military applications. However, this approach is confronted with challenges including inconsistent data structures, irrelevant physical properties, scarce training data, insufficient utilization of information and an imperfect feature fusion method. Therefore, this paper proposes a novel binary-tree Transformer network (BTRF-Net), which is used to fuse heterogeneous information and utilize complementarity among multi-source remote sensing data to enhance the joint classification performance of hyperspectral image (HSI) and light detection and ranging (LiDAR) data. Firstly, a hyperspectral network (HSI-Net) is employed to extract spectral and spatial features of hyperspectral images, while the elevation information of LiDAR data is extracted using the LiDAR network (LiDAR-Net). Secondly, a multi-source transformer complementor (MSTC) is designed that utilizes the complementarity and cooperation among multi-modal feature information in remote sensing images to better capture their correlation. The multi-head complementarity attention mechanism (MHCA) within this complementor can effectively capture global features and local texture information of images, hence achieving full feature fusion. Then, to fully obtain feature information of multi-source remote sensing images, this paper designs a complete binary tree structure, binary feature search tree (BFST), which fuses multi-modal features at different network levels to obtain multiple image features with stronger representation abilities, effectively enhancing the stability and robustness of the network. Finally, several groups of experiments are designed to compare and analyze the proposed BTRF-Net with traditional methods and several advanced deep learning networks using two datasets: Houston and Trento. The results show that the proposed network outperforms other state-of-the-art methods even with small training samples.

Cloud detection in high-resolution remote sensing images (HRSI) is widely applied to cross-spatiotemporal domains with various scenarios change. However, cloud detection semantic segmentation models based on limited samples cannot ensure the consistency of data distribution between the source domain (SD) and the target domain (TD), resulting in a decrease in cross-domain segmentation accuracy and robust ability. Therefore, this paper proposed a two-stage domain adaptation based on the image and feature levels (TDAIF) cloud detection framework. TDAIF designs a pseudo-target domain data generator (PTDDG) at the image level to fuse the SD foreground and TD background information effectively, assisting the model in mining invariant semantic knowledge of the TD. Then, a domain discriminator and self-ensembling joint (DDSEJ) framework is explored at the feature level to implicitly handle the alignment of global features and the optimization of decision boundaries-local features. TDAIF ultimately weakens the impact of image radiation diversity and scale divergence and improves the adaptive processing capabilities for cross-spatiotemporal data. Horizontal and internal comparative experiments on TDAIF were conducted on three domain transfer data. Experimental results show that TDAIF dramatically reduces the network accuracy loss in cross-domain. Compared with CycleGAN and AdaptSegNet, the IoU is improved by about 30%. TDAIF performs better than state-of-the-art computational visual domain adaptation methods, indicating that hierarchical data alignment from the image to the feature level is very effective.