Search Results (422)

In long-corridor Unmanned Aerial Vehicle (UAV) photogrammetry, weak imaging geometry can compromise camera parameter estimation and lead to systematic reconstruction deformation, commonly referred to as the bowl effect, in conventional structure-from-motion (SfM) pipelines. To address this problem, this paper proposes a sub-scene-based GNSS (Global Navigation Satellite System) constrained SfM framework for robust long-corridor UAV photogrammetric reconstruction. First, camera parameter gradients derived from epipolar geometry are used to construct a gradient-consistency cost for identifying stable sub-scenes. Second, GNSS-constrained incremental structureless bundle adjustment (BA) is performed to recover reliable initial camera poses and absolute scale based on image triplets and GNSS/POS observations. Finally, GNSS-weighted BA and inequality-constrained GNSS fusion are introduced to refine camera parameters under a single ground control point (GCP). Experiments on four UAV corridor datasets demonstrate that the proposed method effectively suppresses the bowl effect and stabilizes camera parameter estimation. The proposed method achieves average planar, vertical, and three-dimensional accuracies of 0.040 m, 0.032 m, and 0.051 m, respectively, using only one control point. Compared with the standard Colmap pipeline, the runtime is reduced by approximately 52%. In addition, the proposed method achieves a lower average three-dimensional checkpoint RMSE (0.051 m) than MicMac (0.056 m), Pix4D (0.074 m), Agisoft Metashape (0.078 m) and ContextCapture (0.060 m). Full article

Grotto Buddhist Niches are important spatial carriers of Buddhist cave art, containing rich architectural, artistic, and historical information. However, image data of these Buddhist niches are fragmented across multiple scales, including visual features, cultural semantics, and spatial structures, which significantly hinders cross-scale correlative analysis. To address this issue, this paper proposes a multi-scale knowledge representation method based on image semantics and ontology. Specifically, we establish a five-tier semantic description model, comprising the visual feature layer, image data layer, entity layer, cultural semantics layer, and relational layer. Furthermore, using Protégé and the classical Seven-Step Method, we develop a domain ontology named Grotto Buddhist Niche Ontology (GBNOnto) to enable unified semantic modeling of multi-scale information. Based on this ontology, a knowledge graph focusing on cave imagery is constructed, with typical caves such as Cave 38 at the Yungang Grottoes selected as case studies. The resulting graph contains 892 entity nodes and 2621 semantic relations, effectively capturing the complex interconnections among architectural typology, artistic characteristics, and cultural semantics within the selected niche instances. The proposed method enables structured and associative integration of multi-scale information in grotto Buddhist niche images. It thus provides a foundational data infrastructure and modeling framework to support effective management, knowledge retrieval, and semantic reasoning. Full article

Super high-rise buildings are increasingly equipped with structural monitoring systems to track deformation responses during construction and operation, thereby supporting structural condition assessment and engineering management. To address key monitoring challenges, including GNSS multipath interference, insufficient vertical accuracy, accelerometer integration drift, and high-frequency noise, this study proposes a GNSS/accelerometer fusion monitoring method based on whale optimization algorithm–optimized variational mode decomposition (WOA-VMD) and adaptive robust Kalman filtering (ARKF). Continuous three-hour GNSS and accelerometer observations collected from a super high-rise building under construction are used for fusion validation. The results show that WOA-VMD effectively separates noise from deformation-related signals and outperforms conventional EMD and standard VMD in denoising performance. Compared with the raw observations, the fused east, north, and vertical displacement RMSEs are reduced by 68.84%, 75.97%, and 60.22%, respectively; the SNRs increase to 22.03 dB, 21.38 dB, and 16.74 dB, respectively; the STDs decrease by 72.58%, 75.62%, and 68.39%, respectively; and the PSDs increase to 9.47 dB, 9.02 dB, and 8.31 dB, respectively. The proposed framework exhibits sub-centimeter-level displacement monitoring performance in the horizontal directions and significantly enhances the monitoring capability of the vertical component. The field validation results demonstrate the feasibility and effectiveness of the proposed framework for short-term deformation monitoring of super high-rise buildings under practical monitoring conditions and indicate its potential for structural health monitoring applications. Full article

Accurate and automated extraction of solid waste sites from remote-sensing imagery constitutes a pivotal demand for contemporary environmental regulation and risk mitigation. However, in high-resolution remote-sensing imagery, solid waste sites are typically represented as a single semantic image object (SIO), which is composed of multiple physical image parcels (PIPs) exhibiting significant variations in scale, morphology, and spectral properties. This intrinsic heterogeneity substantially increases the complexity and uncertainty of multi-class site identification. To address this challenge, this paper proposes WasteMOE Net (WMN), which is developed based on the core concept of modeling the SIO–PIP relationship. WMN adopts a heterogeneous expert selection mechanism combined with a nested mixture-of-experts architecture. It thus enables adaptive perception of complex PIPs across diverse scenarios and their integrated discrimination at the SIO level. In addition, by incorporating the explicit nonlinear representation capability of the KAN network, WMN effectively improves multi-class recognition accuracy while maintaining computational efficiency. Furthermore, this study constructs a high-resolution solid waste site dataset in accordance with the SIO–PIP-aware annotation principle, encompassing five representative categories: tailings ponds (TP), construction spoil sites (CSS), landfill sites (LS), garbage dump sites (GDS), and excavation sites (ES). Experimental results show that WMN achieves mAP50 values of 74.2% (GDS), 63.5% (CSS), 80.9% (ES), 85.4% (TP), and 83.1% (LS) in detection tasks, and 75.4%, 64.1%, 83.0%, 86.7%, and 84.1% for the corresponding categories in segmentation tasks. It achieves competitive performance compared with state-of-the-art methods in both tasks. Further, in a real-world application over Loudi City, China, WMN completed the processing of a 490.67 km² area within 1.34 h. The recognition accuracies for GDS and ES reached 54.8% and 65.3%, respectively. Finally, the proposed method has been successfully integrated into a GIS-based solid waste pollution risk prevention system, which markedly boosts the overall efficiency of environmental monitoring and on-site inspections. Full article

In complex urban environments, GNSS satellite signals suffer from severe multipath errors caused by building occlusion and reflection, which significantly degrades the accuracy of precise point positioning (PPP). This paper proposes a deep-learning-based multipath hemispherical grid correction model (DL-MHM) that integrates combined filtering and satellite embedding mechanisms. The model adopts the multi-system interoperable MHM framework to achieve effective multipath error correction. First, pseudorange and carrier phase observation residuals are calculated using the ionosphere-free combination for PPP. Then, a joint median and Kalman filtering scheme is applied to suppress noise in multi-day continuous residual sequences. A transformer-based time-series learning model is constructed, which introduces satellite-specific embedding vectors to characterize the differences between individual satellites and deeply fuse temporal features. This enables the model to adaptively fit the residual variation patterns of different satellites and accurately extract multipath errors. Finally, the multipath components predicted by the deep learning model are incorporated into the multi-system interoperable MHM model to generate the final multipath corrections. Test results show that in heavily obstructed urban scenarios, the root mean square (RMS) values of the east (E), north (N), and up (U) coordinate residuals are improved by 49.27%, 1.80%, and 3.35%, respectively, after DL-MHM correction compared to the uncorrected data. In open-sky environments, the corresponding improvements are 7.70%, 5.48%, and 34.28%. In all experimental scenarios, the proposed method outperforms both the conventional multipath hemispherical map (MHM) model and the convolutional neural network-long short-term memory (CNN-LSTM)-based MHM model in terms of overall multipath correction performance. The experimental results demonstrate that the proposed DL-MHM model can effectively mitigate multipath errors in complex urban scenarios and significantly improve the accuracy of GNSS precise positioning. Full article

Aiming at the core pain point that in existing object detection models, it is difficult to balance detection accuracy and real-time inference efficiency on edge computing devices in UAV-based intelligent inspection of power transmission lines, this paper proposes a lightweight YOLO-PowerLiteV2 model for anomaly target detection in power transmission lines to address the shortcomings of YOLO-PowerLite. Based on YOLO11n as the baseline, the model achieves compression of model volume while guaranteeing detection performance through four core improvements: the C3k2-UIB lightweight backbone module, the MCA (Multi-scale Cross-Axis) attention mechanism, the MBConv lightweight detection head, and the MFM (Modulation Feature Fusion) module. Experiments were conducted on a dataset constructed from 5563 aerial images of transmission lines containing three types of targets: bird nests, defective insulators, and balloons. The results show that YOLO-PowerLiteV2 achieves a mAP@50 of 95.2%, with only 0.97 M parameters and 2.8 G floating point operations (FLOPs). Compared with the baseline model, the number of parameters is reduced by 62.5%, and FLOPs are decreased by 56.25%. On the NVIDIA Jetson Xavier NX edge platform, the model achieves 59.5 FPS with only 16.8 ms latency, outperforming the baseline by 31% in frame rate. Its comprehensive performance outperforms mainstream lightweight detection models. The model demonstrates excellent adaptability to UAV edge-terminal deployment requirements, thereby providing technical support for real-time intelligent inspection of power transmission lines. Full article

Aedes (Ae.) aegypti and Ae. albopictus are important vectors of arboviruses. Yet their blood-feeding pattern remains poorly characterised in Africa, including Cameroon. In this study, we characterised the blood-meal sources in both species collected from vegetation, household surroundings, and animal cages across four urban sites, one rural site, and a zoo-botanical garden where humans and animals in captivity are the main hosts. Overall, Aedes mosquitoes represented about half of 10,054 female mosquitoes collected, with Ae. albopictus strongly dominating Ae. aegypti among 5001 Aedes females, and only 5.95% of females visibly blood-fed. Sequencing a 748 base pairs (bp) fragment of the cytochrome oxidase I gene from 156 blood-fed abdomens yielded 126 high-confidence host assignments, of which 98.25% were humans, indicating a strong anthropophagic pattern in both species. Unpredictably, two Ae. albopictus individuals had fed on a baboon (Papio anubis) and a frugivorous bat (Pteropodidae), as confirmed by bio informatic analyses, highlighting the species’ opportunistic blood-feeding nature and providing preliminary molecular evidence consistent with a potential bridge-vector role in this setting. Despite the extreme anthropophagy of both species observed, results indicate that Ae. albopictus could also serve as a bridge vector enabling spillover of enzootic viruses to humans, including urbanised settings where wild animals are present. These findings emphasise the urgent need for enhanced arbovirus surveillance in Central Africa using a One Health approach. Full article

Land subsidence poses a significant threat to infrastructure stability and urban sustainability, particularly in rapidly developing coastal regions. In this study, land subsidence over Penang Island, Malaysia, was investigated by integrating Persistent Scatterer Interferometric Synthetic Aperture Radar (PS-InSAR) and Small Baseline Subset InSAR (SBAS-InSAR) techniques using both ascending and descending Sentinel-1 datasets. The combined PS-SBAS framework enables high-resolution and reliable deformation monitoring by exploiting the complementary advantages of the two approaches. To further improve deformation retrieval accuracy, an adaptive machine learning-based weighting strategy was incorporated into the InSAR time-series inversion process. Specifically, a data-driven model was employed to evaluate the reliability of interferometric observations using multiple quality indicators, enabling adaptive weighting of interferometric pairs and suppressing the influence of low-quality or noisy measurements. This strategy enhances the robustness and stability of deformation estimation without requiring additional external datasets. The results reveal spatially heterogeneous subsidence patterns across Penang Island, with pronounced deformation mainly concentrated in coastal and urbanized regions. Compared with conventional approaches, the proposed framework demonstrates improved temporal consistency and reduced sensitivity to noise, resulting in more reliable deformation time series. The findings provide valuable insights into regional subsidence dynamics and demonstrate the potential of the proposed framework for InSAR-based deformation monitoring in complex environments. Full article

Traditional visual SLAM pipelines are typically designed under the static-world assumption and often degrade severely in indoor environments with frequent human motion. To improve trajectory accuracy and front-end stability in such scenarios while maintaining real-time throughput, we present SY-SLAM, an RGB-D SLAM system for dynamic indoor environments with frequent human motion. (S stands for SuperPoint, which is used as a detector-only learned keypoint front-end, and Y stands for YOLO, which provides asynchronous person-aware keypoint suppression based on detected human bounding boxes.) We integrate a TensorRT-deployed detector-only SuperPoint module to improve keypoint repeatability and robustness while retaining ORB binary descriptors for efficient matching and place recognition within the ORB-SLAM3 framework. To avoid feature starvation while preserving keypoint quality, we further introduce an adaptive SuperPoint keypoint selection strategy that applies stricter filtering when keypoints are abundant and relaxes the selection constraints when they are scarce. In parallel, an asynchronous YOLOv8s TensorRT thread performs person detection with temporal bounding-box memory, and keypoints inside detected person regions are removed before ORB descriptor computation and matching to reduce dynamic-feature contamination in the front end. We evaluate SY-SLAM on five dynamic TUM RGB-D fr3 sequences using ATE and RPE metrics. Compared with ORB-SLAM3, SY-SLAM reduces ATE RMSE by 93.45% across four dynamic walking sequences. On the widely reported fr3/w/x sequence, SY-SLAM achieves competitive accuracy with recent dynamic SLAM methods while maintaining real-time performance. The system runs in real time at 46.8 Hz (21.36 ms per frame) on an Intel i9-13900H CPU with an NVIDIA RTX 4070 Laptop GPU. Full article

Building climate-resilient cities strengthens urban livability and sustainable development levels. This paper constructs a difference-in-differences model to examine the impact of the pilot policy for climate-resilient city construction (CRCC—CRCC is used uniformly in the following text to represent the policy) on green sustainable innovation, using panel data of 260 prefecture-level Chinese cities from 2009 to 2023. The results reveal that CRCC can significantly promote green sustainable innovation in Chinese cities. Additionally, CRCC promotes green sustainable innovation by increasing the level of informatization, improving green total-factor energy efficiency, boosting corporate ESG performance, and alleviating corporate financing constraints. Therefore, it is necessary to further strengthen the implementation and promotion of China’s climate pilot policy. Attention should be paid to optimizing the pathways through which the pilot policy affects green sustainable innovation. Differentiated regional policies should be implemented based on local conditions. A tripartite linkage mechanism involving the government, enterprises, and the public should be established to increase societal awareness and support for climate-resilient city construction. Full article

Traditional linear models in urban informatics struggle to capture the complex, non-linear spatial non-stationarity inherent in metropolitan housing markets. To overcome these constraints, this study introduces a data-driven computational framework integrating a Spatio-Temporal Graph Convolutional Network (STGCN) with gradient-based Explainable Artificial Intelligence (XAI) and Geographically Weighted Regression (GWR). This framework is empirically tested using 217,598 apartment transactions in Busan, the Republic of Korea, augmented with high-resolution micro-demographic grids and Digital Elevation Model (DEM) topographical data. Utilizing unsupervised K-Means clustering, the region is spatially stratified into a dense Urban Core and a dispersed Suburban Periphery. The STGCN demonstrates overwhelming predictive superiority ($R^2=0.802$) over the traditional Spatial Error Model ($R^2=0.437$). Crucially, gradient-based XAI and localized GWR coefficients successfully unspool the deep learning “black box,” visualizing hyper-localized economic realities that global linear models obscure. The analysis expose stark regional market segmentation driven by environmental topography, mathematically quantifying non-linear dynamics such as coastal high-floor premiums, severe mountainous altitude penalties, and latent urban reconstruction premiums. Ultimately, this research bridges the gap between predictive computational power and spatial economic interpretability, offering a robust informatics framework for equitable urban planning. Full article

Image-based PM2.5 estimation has emerged as a promising complementary approach to traditional physicochemical monitoring. However, achieving accurate predictions in severely polluted environments remains a critical challenge, as existing deep learning models tend to prioritize luminance variations induced by PM2.5 while neglecting the impact of complex atmospheric light interference, leading to substantial estimation errors. To address this issue, this paper proposes a novel luminance–spatial decoupling (LSD) module constructed based on L2–Lp Retinex theory and integrated into a VGG16 backbone. By establishing a prior knowledge module linking luminance to PM2.5, the proposed method achieves high-fidelity separation of atmospheric luminance (AL) and target luminance (TL) during feature extraction. TL represents the luminance variation induced by PM2.5 concentrations, whereas AL characterizes the luminance contribution arising from atmospheric light. Simulation experiments validate the reliability of the L2–Lp Retinex-based decomposition. Ablation studies reveal that the LSD module effectively mitigates haze interference in high-pollution conditions while minimizing influence on the backbone network in clear weather, thereby resolving the conflict between dehazing and feature extraction. Comparative experiments demonstrate that LSD-VGG16 significantly outperforms traditional methods and standard convolutional neural networks, achieving a minimum prediction error of 12.42 while exhibiting stronger stability against temporal variations. Furthermore, evaluation on the unseen RHID-AQI dataset without retraining confirms the model’s robust generalization capability under abrupt illumination fluctuations and diverse weather conditions. Full article

The 2024 World Heritage inscription of the Beijing Central Axis shifts the focus of historic district governance to quality-oriented urban regeneration. However, evaluating the precise alignment between infrastructural topology and cultural meaning remains a methodological challenge. To move beyond macro-level assumptions, this study constructs a novel “spatial–semantic coupling” diagnostic framework. Integrating multi-source street-view data, Space Syntax, and the zero-shot semantic extraction capabilities of the CLIP model, we performed high-resolution visual semantic identification across 550 fine-grained sampling points in the 6.6 km² South Central Axis Core Area. Rather than merely observing a general “decoupling,” our diagnostic tool successfully mapped the complex spectrum of spatial alignments. While it accurately diagnosed areas with “idle spatial potential”—where high Global Integration (Mean = 0.924) fails to translate into Visual Attraction (r = −0.03) or Historical Perception (r = 0.01)—it also precisely identified “Synergistic” heritage cores and “hidden gems” within capillary hutongs. Furthermore, the framework diagnosed a severe “green island” effect (Mean = 0.26) and a structural contradiction between Spaciousness and Historical Perception (r = −0.33). By utilizing Bivariate LISA to geographically pinpoint these varying coupling characteristics (e.g., severe “High–Low” spatial frictions at gateway transportation hubs), this study establishes a highly scalable, data-driven analytical paradigm for targeted micro-renewal, ensuring the precise alignment of physical centrality and cultural perception in complex historic districts globally. Full article

Outdoor jogging is a significant component of daily physical activities that benefit public health and urban living environments. However, it is still challenging to untangle the intricate associations between environmental variables and jogging paces, due to nonlinear interactions, spatial heterogeneity, and inadequacy in model interpretability. To this end, an interpretable spatial machine learning framework based on the integration of the Geographically Weighted Random Forest (GW-RF) model and SHapley Additive exPlanations (SHAP) is proposed. Drawing on multi-source urban datasets and Beijing’s large-scale jogging trajectory data, this model allows for global and local interpretation of environmental effects on the built, natural, and visual dimensions. The findings are as follows: (1) Built environment variables demonstrate the greatest explanatory power, with street network configuration (GAC, GAI) and population density identified as the dominant predictors of jogging intensity; (2) All environmental variables exhibit nonlinear threshold effects, with SHAP analysis revealing sign-switching points and optimal ranges—moderate NDVI and sky openness promote jogging while extreme values suppress it; (3) Natural and visual variables operate within distinct comfort thresholds, where moderate annual mean temperature, green view index, and sky openness are consistently associated with higher jogging intensity; and (4) The GW-RF model achieves superior predictive performance (R² = 0.7939, RMSE = 8.54, MAE = 5.72) over five benchmark models, confirming the necessity of spatial weighting in nonlinear ensemble learning. By revealing nonlinear response patterns and effective environmental ranges, the study presents quantitative evidence for the understanding urban physical activities and providing methodological guidance for fostering healthier and more activity-supportive urban environments. Full article

Net surface shortwave radiation (NSSR) is a key parameter in the Earth’s energy cycle, greatly affecting global water and heat balance. Currently, a comprehensive comparative analysis regarding the accuracy of different models remains severely lacking, and there is also a notable deficiency in the systematic exploration of seasonal radiative drivers. Therefore, we developed a machine learning-based seasonal NSSR estimation model. By integrating in-situ observational data with multi-source remote sensing datasets, we achieved precise quantification of radiative fluxes. This proposed model framework employed three cutting-edge algorithms, namely Random Forest (RF), eXtreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM), to capture the non-linear interactions among radiative drivers across the four seasons. Through mechanistic sensitivity analysis, we quantified the impacts of key variables on NSSR prediction. The results unequivocally demonstrated that the RF algorithm demonstrated the best performance. Its seasonal R² were 0.95 (spring), 0.89 (summer), 0.95 (autumn), and 0.96 (winter). The Solar Zenith Angle (SZA) dominated in spring and winter; its absence reduced R² by 0.23 and raised RMSE by 20.66–26.42 W/m². Meteorological factors mattered most in summer; excluding them cut R² by 0.17 and hiked RMSE by 23.82 W/m². This study provides actionable insights for terrestrial radiation budget research. Full article