Search

Abstract Point cloud registration is of great significance to the reconstruction of high‐precision 3D city models. There are some challenges when aligning aerial and close‐range photogrammetric point clouds, such as huge view differences caused by the different sights of the sensors, massive noisy points due to the error in dense matching, and scale uncertainty since there are no control points for absolute orientation. To achieve complementary advantages of aerial and close‐range point clouds, in this paper, a robust cross‐source point clouds registration method is proposed using image visual context features and scale consistency. First, a cross‐view image matching method based on image visual context features is proposed to obtain corresponding points. Second, to overcome the challenges of noisy points and scale differences, an outlier filtering method is designed based on scale consistency. Finally, the dual quaternions model considering the scale factor is introduced to solve the spatial transformation model. To analyze the feasibility of this method qualitatively and quantitatively, experiments are conducted using the public scene dataset of Dortmund, Germany, and the scene dataset of Zhengzhou City, China. Three kinds of cross‐source point clouds registration experiments are conducted in this paper, including aerial and close‐range point clouds registration in Dortmund, and aerial and ground point clouds registrations in both Dortmund and Zhengzhou. The chamfer distances of the three sets of experiments are 4.48 m, 5.97 m and 4.78 m, respectively. The ablation study shows that the outlier filtering method and the dual quaternions model improve the accuracy by at least 14% and 25%, respectively. The experiments demonstrate that the method accomplishes the cross‐source point clouds registration in large‐scale scenes accurately and efficiently, providing a solid foundation for subsequent fine 3D reconstruction.

Rapid urbanization currently poses a threat to cropland areas. Therefore, exploring the pattern of change in cropland areas and its driving mechanism is of great significance in safeguarding regional economic development and food security. In this study, data regarding cropland in the Changsha-Zhuzhou-Xiangtan city group (CZTCG) from 2000 to 2020 were collected, and dynamic changes in cropland in the past 20 years were analyzed. Based on this, the mechanisms that drive cropland change were explored in the context of multiple dimensions. Furthermore, an Inertial Development Scenario and a Cropland Priority Scenario were designed to simulate land use/land cover (LULC) changes in the CZTCG in 2025 and 2035, and, in particular, to analyze the characteristics of future spatiotemporal changes of cropland. The results demonstrated that the cropland area in the CZTCG in the past 20 years has shown a two-stage trend of increasing (2000–2015, increase of 8.25%) and decreasing (2015–2020, decrease of 2.91%), and the main reasons for cropland loss in the whole process of change were forest and building, with serious loss of cropland area in Changsha County and Wangcheng District. Between 2000 and 2020, socio-economic factors (GDP, total agricultural output), topography (elevation, slope), and climate change (average annual temperature, annual precipitation) were highly correlated with changes in cropland area, exhibiting significant temporal and regional variability. The simulation results indicate that until 2035, the Cropland Priority Scenario shows a significant increase in the area of cropland in the study area compared to the Inertial Development Scenario. Consequently, the implementation of a strategy that prioritizes cropland can effectively protect it, while helping to promote ecological development and regional socio-economic development.

Accurate building geometry information is crucial for urban planning in constrained spaces, fueling the growing demand for large-scale, high-precision 3D city modeling. Traditional methods like oblique photogrammetry and LiDAR prove time consuming and expensive for low-cost 3D reconstruction of expansive urban scenes. Addressing this challenge, our study proposes a novel approach to leveraging single-view remote sensing images. By integrating shadow information with deep learning networks, our method measures building height and employs a semantic segmentation technique for single-image high-rise building reconstruction. In addition, we have designed complex shadow measurement algorithms and building contour correction algorithms to improve the accuracy of building models in conjunction with our previous research. We evaluate the method’s precision, time efficiency, and applicability across various data sources, scenarios, and scales. The results demonstrate the rapid and accurate acquisition of 3D building data with maintained geometric accuracy (mean error below 5 m). This approach offers an economical and effective solution for large-scale urban modeling, bridging the gap in cost-efficient 3D reconstruction techniques.

Laser altimetry data from the Ice, Cloud, and land Elevation Satellite-2 (ICESat-2) contain a lot of noise, which necessitates the requirement for a signal photon extraction method. In this study, we propose a density clustering method, which combines slope and elevation information from optical stereo images and adaptively adjusts the neighborhood search direction in the along-track direction. The local classification density threshold was calculated adaptively according to the uneven spatial distribution of noise and signal density, and reliable surface signal points were extracted. The performance of the algorithm was validated for strong and weak beam laser altimetry data using optical stereo images with different resolutions and positioning accuracies. The results were compared qualitatively and quantitatively with those obtained using the ATL08 algorithm. The signal extraction quality was better than that of the ATL08 algorithm for steep slope and low signal-to-noise ratio (SNR) regions. The proposed method can better balance the relationship between recall and precision, and its F1-score was higher than that of the ATL08 algorithm. The method can accurately extract continuous and reliable surface signals for both strong and weak beams among different terrains and land cover types.

Sea ice extraction and segmentation of remote sensing images is the basis for sea ice monitoring. Traditional image segmentation methods rely on manual sampling and require complex feature extraction. Deep-learning-based semantic segmentation methods have the advantages of high efficiency, intelligence, and automation. Sea ice segmentation using deep learning methods faces the following problems: in terms of datasets, the high cost of sea ice image label production leads to fewer datasets for sea ice segmentation; in terms of image quality, remote sensing image noise and severe weather conditions affect image quality, which affects the accuracy of sea ice extraction. To address the quantity and quality of the dataset, this study used multiple data augmentation methods for data expansion. To improve the semantic segmentation accuracy, the SC-U2-Net network was constructed using multiscale inflation convolution and a multilayer convolutional block attention module (CBAM) attention mechanism for the U2-Net network. The experiments showed that (1) data augmentation solved the problem of an insufficient number of training samples to a certain extent and improved the accuracy of image segmentation; (2) this study designed a multilevel Gaussian noise data augmentation scheme to improve the network’s ability to resist noise interference and achieve a more accurate segmentation of images with different degrees of noise pollution; (3) the inclusion of a multiscale inflation perceptron and multilayer CBAM attention mechanism improved the ability of U2-Net network feature extraction and enhanced the model accuracy and generalization ability.

The complex backgrounds of satellite videos and serious interference from noise and pseudo-motion targets make it difficult to detect and track moving vehicles. Recently, researchers have proposed road-based constraints to remove background interference and achieve highly accurate detection and tracking. However, existing methods for constructing road constraints suffer from poor stability, low arithmetic performance, leakage, and error detection. In response, this study proposes a method for detecting and tracking moving vehicles in satellite videos based on the constraints from spatiotemporal characteristics (DTSTC), fusing road masks from the spatial domain with motion heat maps from the temporal domain. The detection precision is enhanced by increasing the contrast in the constrained area to accurately detect moving vehicles. Vehicle tracking is achieved by completing an inter-frame vehicle association using position and historical movement information. The method was tested at various stages, and the results show that the proposed method outperformed the traditional method in constructing constraints, correct detection rate, false detection rate, and missed detection rate. The tracking phase performed well in identity retention capability and tracking accuracy. Therefore, DTSTC is robust for detecting moving vehicles in satellite videos.

Image matching is the research basis of many computer vision problems, such as intelligent driving, object recognition and structure from motion. However, the traditional feature-based image-matching results are usually very sparse and unevenly distributed for wide baseline or weakly textured images. Implementing an efficient and robust image-matching technology is a challenging task. To solve these problems, we propose an efficient extractor and binary descriptor based on superpixels and a modified binary robust independent elementary features (BRIEF) descriptor called FSRB. FSRB can improve the computational efficiency, number of matches, feature distribution and robustness of feature-based image matching. In theory, FSRB is rotation-, scale-, affine-, distorted-, and intensity-invariant. A comprehensive performance evaluation of FSRB is performed. The experimental results show that our method can effectively obtain many matches for different types of images. Compared with state-of-the-art algorithms, our method performed very well in terms of the number of correct matches (which increased by 2-5 times), time consumption, matching accuracy, matching success rate and feature repetition rate. In addition, our method is applied to sparse 3D reconstruction of multiview images, and satisfactory results are obtained.

In the field of geoinformation science, multiview, image-based 3D city modeling has developed rapidly, and image depth estimation is an important step in it. To address the problems of the poor adaptability of training models of existing neural network methods and the long reconstruction time of traditional geometric methods, we propose a general depth estimation method for fast 3D city modeling that combines prior knowledge and information propagation. First, the original image is downsampled and input into the neural network to predict the initial depth value. Then, depth plane fitting and joint optimization are combined with the superpixel information and the superpixel optimized depth value is upsampled to the original resolution. Finally, the depth information propagation is checked pixel-by-pixel to obtain the final depth estimate. Experiments were conducted using multiple image datasets taken from actual indoor and outdoor scenes. Our method was compared and analyzed with a variety of existing widely used methods. The experimental results show that our method maintains high reconstruction accuracy and a fast reconstruction speed, and it achieves better performance. This paper offers a framework to integrate neural networks and traditional geometric methods, which provide a new approach for obtaining geographic information and fast 3D city modeling.

Image feature matching is an important step in close range photogrammetric applications, and implementing a fast, accurate and robust feature-based image matching technique is a challenging task. To solve the problems of traditional image feature matching algorithms, such as their low accuracy and long processing time, we present a parallax mapping-based matching (PMM) method that is able to improve the computation efficiency, accuracy and robustness of feature-based image matching for close range photogrammetric applications. First, the disparity of the initial corresponding points is calculated, and the mismatches are initially removed via local disparity clustering. Then, the local coordinates of the matching points are constrained by an image division grid. To ensure the correctness of the matching points, the fast polynomial transform is used for as a quadratic constraint. The method can extract high accuracy matching points from the original coarse matching points with low accuracy, and also preserve the true matching points to the greatest extent. Using a variety of experimental datasets and current mainstream feature extraction algorithms, we designed and compared commonly used feature-based image matching algorithms. The experimental results show that the proposed method is simple but effective, can meet the real-time calculation requirements, and outperforms the current state-of-the-art methods.

This article focuses on the first aspect of the album of deep learning: the deep convolutional method. The traditional matching point extraction algorithm typically uses manually designed feature descriptors and the shortest distance between them to match as the matching criterion. The matching result can easily fall into a local extreme value, which causes missing of the partial matching point. Targeting this problem, we introduce a two-channel deep convolutional neural network based on spatial scale convolution, which performs matching pattern learning between images to realize satellite image matching based on a deep convolutional neural network. The experimental results show that the method can extract the richer matching points in the case of heterogeneous, multi-temporal and multi-resolution satellite images, compared with the traditional matching method. In addition, the accuracy of the final matching results can be maintained at above 90%.

Excitability of hippocampal neurons in subarachnoid hemorrhage (SAH) rats has not been well studied. The rat SAH model was applied in this study to explore the role of nuclear factor E2-related factor (Nrf-2) in the early brain injury of SAH. The neural excitability of CA1 pyramidal cells (PCs) in SAH rats was evaluated by using electrophysiology experiments. Ferroptosis and neuroinflammation were measured by ELISA, transmission electron microscopy and western blotting. Our results indicated that SAH induced neurological deficits, brain edema, ferroptosis, neuroinflammation and neural excitability in rats. Ferrostatin-1 treatment significantly decreased the expression and distribution of IL-1β, IL-6, IL-10, TGF-β and TNF-α. Inhibiting ferroptosis by ferrostatin-1 can attenuate neural excitability, neurological deficits, brain edema and neuroinflammation in SAH rats. Inhibiting the expression of Nrf-2 significantly increased the neural excitability and the levels of IL-1β, IL-6, IL-10, TGF-β and TNF-α in Fer-1-treated SAH rats. Taken together, inhibiting the Nrf-2 induces early brain injury, brain edema and the inflammatory response with increasing of neural excitability in Fer-1-treated SAH rats. These results have indicated that inhibiting ferroptosis, neuroinflammation and neural excitability attenuates early brain injury after SAH by regulating the Nrf-2.

The current global image descriptors are mostly obtained by using the local image features aggregation, which fail to take full account of the details of the image, resulting in the loss of the semantic content information. It cannot be well used to make a good distinction between the high similarity images. In this paper, a new method of image representation, which can express the whole semantics and detail features of the image, is proposed by combining the edge features of the image. It is used to make a global description of the images and then clustering. The experimental results show that the proposed method is capable of clustering of the similarity images with high accuracy and low error rate. [ABSTRACT FROM AUTHOR]

Subarachnoid hemorrhage (SAH) is one kind of life-threatening stroke, which leads to severe brain damage. Pyroptosis plays a critical role in early brain injury (EBI) after SAH. Previous reports suggest that SAH-induced brain edema, cell apoptosis, and neuronal injury could be suppressed by dexmedetomidine (Dex). In this study, we used a rat model of SAH to investigate the effect of Dex on pyroptosis in EBI after SAH and to determine the mechanisms involved. Pyroptosis was found in microglia in EBI after SAH. Dex significantly alleviated microglia pyroptosis via reducing pyroptosis executioner GSDMD and inhibited the release of proinflammatory cytokines induced by SAH. Furthermore, the reduction of GSDMD by Dex was abolished by the PI3K inhibitor LY294002. In conclusion, our data demonstrated that Dex reduces microglia pyroptosis in EBI after SAH via the activation of the PI3K/AKT/GSK3β pathway.

Neuroinflammation plays a key role in the pathogenesis of early brain injury (EBI) after subarachnoid hemorrhage (SAH). Previous studies have shown that metformin exerts anti-inflammatory effects and promotes functional recovery in various central nervous system diseases. We designed this study to investigate the effects of metformin on EBI after SAH. Our results indicate that the use of metformin alleviates the brain edema, behavioral disorders, cell apoptosis, and neuronal injury caused by SAH. The SAH-induced NLRP3-associated inflammatory response and the activation of microglia are also suppressed by metformin. However, we found that the blockade of AMPK with compound C weakened the neuroprotective effects of metformin on EBI. Collectively, our findings indicate that metformin exerts its neuroprotective effects by inhibiting neuroinflammation in an AMPK-dependent manner, by modulating the production of NLRP3-associated proinflammatory factors and the activation of microglia.

Inflammation is typically related to dysfunction of the blood-brain barrier (BBB) that leads to early brain injury (EBI) after subarachnoid hemorrhage (SAH). Resolvin D1 (RVD1), a lipid mediator derived from docosahexaenoic acid, possesses anti-inflammatory and neuroprotective properties. This study investigated the effects and mechanisms of RVD1 in SAH. A Sprague-Dawley rat model of SAH was established through endovascular perforation. RVD1was injected through the femoral vein at 1 and 12 h after SAH induction. To further explore the potential neuroprotective mechanism, a formyl peptide receptor two antagonist (WRW4) was intracerebroventricularly administered 1 h after SAH induction. The expression of endogenous RVD1 was decreased whereas A20 and NLRP3 levels were increased after SAH. An exogenous RVD1 administration increased RVD1 concentration in brain tissue, and improved neurological function, neuroinflammation, BBB disruption, and brain edema. RVD1 treatment upregulated the expression of A20, occludin, claudin-5, and zona occludens-1, as well as downregulated nuclear factor-κBp65, NLRP3, matrix metallopeptidase 9, and intercellular cell adhesion molecule-1 expression. Furthermore, RVD1 inhibited microglial activation and neutrophil infiltration and promoted neutrophil apoptosis. However, the neuroprotective effects of RVD1 were abolished by WRW4. In summary, our findings reveal that RVD1 provides beneficial effects against inflammation-triggered BBB dysfunction after SAH by modulating A20 and NLRP3 inflammasome.

Background/Aims: To determine the cellular functions and clinical significance of micro-758-5p (miR-758-5p) in glioblastoma (GBM) by targeting zinc finger and BTB domain-containing protein 20 (ZBTB20). Methods: Fifty-five paired GBM tissues and adjacent normal tissues, GBM cell lines (U118, LN-299, H4, A172, U87-MG, and U251), and normal human astrocyte cell line (HEB) were used. miR-758-5p mimics, ZBTB20 siRNA, and pcDNA3.1-ZBTB20 were transiently transduced into cancer cells independently or together. qRT-PCR was conducted to analyze the expression of miR-758-5p and ZBTB20. Luciferase reporter assays were performed to determine the effect of miR-758-5p on ZBTB20. Western blot was applied to measure the expression of ZBTB20, PCNA, and cleaved caspase3. Cell Counting Kit-8 (CCK8), colony formation, FACS, and Transwell assays were carried out to detect cellular proliferation, apoptosis, migration, and invasion. Xenograft experiments were implemented to evaluate tumor growth and metastasis in vivo. Results: miR-758-5p was significantly downregulated in GBM tissues and cell lines compared with that in adjacent normal tissues and HEB cells. miR-758-5p overexpression inhibited the proliferation, migration, and invasion of GBM cells and induced apoptosis by regulating the ZBTB20 expression. Pearson correlation analysis also confirmed that miR-758-5p was inversely correlated with ZBTB20 in GBM tissues. miR-758-5p suppressed tumor growth and metastasis in vivo. The restored ZBTB20 expression partially rescued the miR-758-5p-induced inhibition of GBM cell proliferation, migration, and invasion. Kaplan–Meier curve analysis revealed that a high miR-758-5p expression indicated an enhanced prognosis of patients with GBM. Conclusion: miR-758-5p suppressed GBM progression by targeting ZBTB20. The miR-758-5p/ZBTB20 axis might be a promising therapeutic target for GBM treatment.