Search Results (805)

This study presents a cross-cultural comparison of two fortified residences—Palazzo Farnese in Italy and Dong’s Fortified Compound in China—through a triadic analytical framework encompassing architectural form, symbolic ornamentation, and public perception. By combining field observation, iconographic interpretation, and digital ethnography, the research investigates how heritage meaning is constructed, encoded, and reinterpreted across distinct sociocultural contexts. Empirical materials include architectural documentation, decorative analysis, and a curated dataset of 4947 user-generated images and 1467 textual comments collected from Chinese and international platforms between 2020 and 2024. Methods such as CLIP-based visual clustering and BERTopic-enabled sentiment modelling were applied to extract patterns of perception and symbolic emphasis. The findings reveal contrasting representational logics: Palazzo Farnese encodes dynastic authority and Renaissance cosmology through geometric order and immersive frescoes, while Dong’s Compound conveys Confucian ethics and frontier identity via nested courtyards and traditional ornamentation. Digital responses diverge accordingly: international users highlight formal aesthetics and photogenic elements; Chinese users engage with symbolic motifs, family memory, and ritual significance. This study illustrates how historically fortified residences are reinterpreted through culturally specific digital practices, offering an interdisciplinary approach that bridges architectural history, symbolic analysis, and digital heritage studies. Full article

High-quality green gardens can markedly enhance the quality of life and mental well-being of their users. However, health and lifestyle constraints make it difficult for people to enjoy urban gardens, and traditional methods struggle to offer the high-fidelity experiences they need. This study introduces a 3D scene reconstruction and rendering strategy based on implicit neural representation through the efficient and removable neural radiation fields model (NeRF-RE). Leveraging neural radiance fields (NeRF), the model incorporates a multi-resolution hash grid and proposal network to improve training efficiency and modeling accuracy, while integrating a segment-anything model to safeguard public privacy. Take the crabapple tree, extensively utilized in urban garden design across temperate regions of the Northern Hemisphere. A dataset comprising 660 images of crabapple trees exhibiting three distinct geometric forms is collected to assess the NeRF-RE model’s performance. The results demonstrated that the ‘harvest gold’ crabapple scene had the highest reconstruction accuracy, with PSNR, LPIPS and SSIM of 24.80 dB, 0.34 and 0.74, respectively. Compared to the Mip-NeRF 360 model, the NeRF-RE model not only showed an up to 21-fold increase in training efficiency for three types of crabapple trees, but also exhibited a less pronounced impact of dataset size on reconstruction accuracy. This study reconstructs real scenes with high fidelity using virtual reality technology. It not only facilitates people’s personal enjoyment of the beauty of natural gardens at home, but also makes certain contributions to the publicity and promotion of urban landscapes. Full article

The Furuta pendulum is a well-known benchmark in the field of underactuated mechanical systems due to its reduced number of control inputs compared to its degrees of freedom, and richly nonlinear behavior. This work addresses the challenge of accurately modeling and controlling such a system without relying on traditional linearization techniques. In contrast to the common approach based on Lagrangian analytical modeling and state–space linearization, we propose a methodology that integrates a high-fidelity multibody model developed in Simscape Multibody (MATLAB), capturing the complete nonlinear dynamics of the system. The multibody model includes all geometric, inertial, and joint parameters of the physical hardware and interfaces directly with Simulink, enabling realistic simulation and control integration. To validate the physical fidelity of the multibody model, we perform a frequency-domain analysis of the pendulum’s natural free response. The dominant vibration frequency extracted from the simulation is compared with the theoretical prediction, demonstrating accurate capture of the system’s inertial and dynamic properties. This validation strategy strengthens the reliability of the model as a digital twin. The classical analytical formulation is provided to validate the simulation model and serve as a comparative framework. This dual modeling strategy allows for benchmarking control strategies against a trustworthy nonlinear digital twin of the Furuta pendulum. Preliminary experimental results using a physical prototype validate the feasibility of the proposed approach and set the foundation for future work in advanced nonlinear control design using the multibody representation as a digital validation tool. Full article

Accurate organ-level segmentation is essential for achieving high-throughput, non-destructive, and automated plant phenotyping. To address the challenge of intelligent acquisition of phenotypic parameters in tomato plants, we propose TSINet, an end-to-end dual-task segmentation network designed for effective and precise semantic labeling and instance recognition of tomato point clouds, based on the Pheno4D dataset. TSINet adopts an encoder–decoder architecture, where a shared encoder incorporates four Geometry-Aware Adaptive Feature Extraction Blocks (GAFEBs) to effectively capture local structures and geometric relationships in raw point clouds. Two parallel decoder branches are employed to independently decode shared high-level features for the respective segmentation tasks. Additionally, a Dual Attention-Based Feature Enhancement Module (DAFEM) is introduced to further enrich feature representations. The experimental results demonstrate that TSINet achieves superior performance in both semantic and instance segmentation, particularly excelling in challenging categories such as stems and large-scale instances. Specifically, TSINet achieves 97.00% mean precision, 96.17% recall, 96.57% F1-score, and 93.43% IoU in semantic segmentation and 81.54% mPrec, 81.69% mRec, 81.60% mCov, and 86.40% mWCov in instance segmentation. Compared with state-of-the-art methods, TSINet achieves balanced improvements across all metrics, significantly reducing false positives and false negatives while enhancing spatial completeness and segmentation accuracy. Furthermore, we conducted ablation studies and generalization tests to systematically validate the effectiveness of each TSINet component and the overall robustness of the model. This study provides an effective technological approach for high-throughput automated phenotyping of tomato plants, contributing to the advancement of intelligent agricultural management. Full article

In recent years, geographic knowledge graphs (GeoKGs) have shown great promise in representing spatio-temporal and event-driven knowledge. However, existing knowledge graph embedding approaches mainly focus on structural patterns and often overlook the dynamic evolution of entities in both time and space, which limits their effectiveness in downstream reasoning tasks. To address this, we propose a spatio-temporal evolutionary knowledge embedding approach (ST-EKA) that enhances entity representations by modeling their evolution through type-aware encoding, temporal and spatial decay mechanisms, and context aggregation. ST-EKA integrates four core components, including an entity encoder constrained by relational type consistency, a temporal encoder capable of handling both time points and intervals through unified sampling and feedforward encoding, a multi-scale spatial encoder that combines geometric coordinates with semantic attributes, and an evolutionary knowledge encoder that employs attention-based spatio-temporal weighting to capture contextual dynamics. We evaluate ST-EKA on three representative GeoKG datasets—GDELT, ICEWS, and HAD. The results demonstrate that ST-EKA achieves an average improvement of 6.5774% in AUC and 5.0992% in APR on representation learning tasks. In question answering tasks, it yields a maximum average increase of 1.7907% in AUC and 0.5843% in APR. Notably, it exhibits superior performance in chain queries and complex spatio-temporal reasoning, validating its strong robustness, good interpretability, and practical application value. Full article

The Building Information Modelling (BIM) methodology has been applied in distinct sectors of the construction industry with a growing demonstration of benefits, supporting the elaboration of integrated and collaborative projects. The main foundation of the methodology is the generation of a three-dimensional (3D) digital representation, the BIM model, concerning the different disciplines that make up a complete project. The BIM model includes a database referring to all the information regarding the geometric and physical aspects of the project. The procedure related to the generation of BIM models presents a significant difference depending on whether the project refers to new or old buildings. Current BIM systems contain libraries with various types of parametric objects that are effortlessly adaptable to new constructions. However, the generation of models of old buildings, supported by the definition of detailed new parametric objects, is required. The present study explores the distinct modelling procedures applied in the generation of specific parametric objects for new and old constructions, with the objective of evaluating the comparative complexity that the designer faces in modelling specific components. For a correct representation of new buildings in the design phase or for the reproduction of the accurate architectural configuration of heritage buildings, the modelling process presents significant differences identified in the study. Full article

With the widespread use of sensors in applications such as autonomous driving and intelligent security, stable and efficient target tracking from diverse sensor data has become increasingly important. Self-supervised visual tracking has attracted increasing attention due to its potential to eliminate reliance on costly manual annotations; however, existing methods often train on incomplete object representations, resulting in inaccurate localization during inference. In addition, current methods typically struggle when applied to deep networks. To address these limitations, we propose a novel self-supervised tracking framework based on image synthesis and domain adversarial learning. We first construct a large-scale database of real-world target objects, then synthesize training video pairs by randomly inserting these targets into background frames while applying geometric and appearance transformations to simulate realistic variations. To reduce domain shift introduced by synthetic content, we incorporate a domain classification branch after feature extraction and adopt domain adversarial training to encourage feature alignment between real and synthetic domains. Experimental results on five standard tracking benchmarks demonstrate that our method significantly enhances tracking accuracy compared to existing self-supervised approaches without introducing any additional labeling cost. The proposed framework not only ensures complete target coverage during training but also shows strong scalability to deeper network architectures, offering a practical and effective solution for real-world tracking applications. Full article

This paper introduces a hierarchical object-centric descriptor framework called TOSD (Triplet Object-Centric Semantic Descriptor). The goal of this method is to overcome the limitations of existing pixel-based and global feature embedding approaches. To this end, the framework adopts a hierarchical representation that is explicitly designed for multi-level reasoning. TOSD combines shape, color, and topological information without depending on predefined class labels. The shape descriptor captures the geometric configuration of each object. The color descriptor focuses on internal appearance by extracting normalized color features. The topology descriptor models the spatial and semantic relationships between objects in a scene. These components are integrated at both object and scene levels to produce compact and consistent embeddings. The resulting representation covers three levels of abstraction: low-level pixel details, mid-level object features, and high-level semantic structure. This hierarchical organization makes it possible to represent both local cues and global context in a unified form. We evaluate the proposed method on multiple vision tasks. The results show that TOSD performs competitively compared to baseline methods, while maintaining robustness in challenging cases such as occlusion and viewpoint changes. The framework is applicable to visual odometry, SLAM, object tracking, global localization, scene clustering, and image retrieval. In addition, this work extends our previous research on the Semantic Modeling Framework, which represents environments using layered structures of places, objects, and their ontological relations. Full article

Creating high-fidelity digital twins (DTs) for Industry 4.0 applications, it is fundamentally reliant on the accurate 3D modeling of physical assets, a task complicated by the inherent imperfections of real-world point cloud data. This paper addresses the challenge of reconstructing accurate, watertight, and topologically sound 3D meshes from sparse, noisy, and incomplete point clouds acquired in complex industrial environments. We introduce a robust two-stage completion-to-reconstruction framework, C2R3D-Net, that systematically tackles this problem. The methodology first employs a pretrained, self-supervised point cloud completion network to infer a dense and structurally coherent geometric representation from degraded inputs. Subsequently, a novel adaptive surface reconstruction network generates the final high-fidelity mesh. This network features a hybrid encoder (FKAConv-LSA-DC), which integrates fixed-kernel and deformable convolutions with local self-attention to robustly capture both coarse geometry and fine details, and a boundary-aware multi-head interpolation decoder, which explicitly models sharp edges and thin structures to preserve geometric fidelity. Comprehensive experiments on the large-scale synthetic ShapeNet benchmark demonstrate state-of-the-art performance across all standard metrics. Crucially, we validate the framework’s strong zero-shot generalization capability by deploying the model—trained exclusively on synthetic data—to reconstruct complex assets from a custom-collected industrial dataset without any additional fine-tuning. The results confirm the method’s suitability as a robust and scalable approach for 3D asset modeling, a critical enabling step for creating high-fidelity DTs in demanding, unseen industrial settings. Full article

3D object detection is a fundamental task in autonomous driving. In recent years, voxel-based methods have demonstrated significant advantages in reducing computational complexity and memory consumption when processing large-scale point cloud data. A representative method, Voxel-RCNN, introduces Region of Interest (RoI) pooling on voxel features, successfully bridging the gap between voxel and point cloud representations for enhanced 3D object detection. However, its robustness deteriorates when detecting distant objects or in the presence of noisy points (e.g., traffic signs and trees). To address this limitation, we propose an enhanced approach named Self-Attention Voxel-RCNN (SA-VoxelRCNN). Our method integrates two complementary attention mechanisms into the feature extraction phase. First, a full self-attention (FSA) module improves global context modeling across all voxel features. Second, a deformable self-attention (DSA) module enables adaptive sampling of representative feature subsets at strategically selected positions. After extracting contextual features through attention mechanisms, these features are fused with spatial features from the base algorithm to form enhanced feature representations, which are subsequently input into the region proposal network (RPN) to generate high-quality 3D bounding boxes. Experimental results on the KITTI test set demonstrate that SA-VoxelRCNN achieves consistent improvements in challenging scenarios, with gains of 2.49 and 1.87 percentage points at Moderate and Hard difficulty levels, respectively, while maintaining real-time performance at 22.3 FPS. This approach effectively balances local geometric details with global contextual information, providing a robust detection solution for autonomous driving applications. Full article

We propose a hybrid Convolutional Graph Neural Network (C-GNN) for direction-of-arrival (DOA) estimation in sparse sensor arrays under low-snapshot conditions. The C-GNN architecture combines 1D convolutional layers for local spatial feature extraction with graph convolutional layers for global structural learning, effectively capturing both fine-grained and long-range array dependencies. Leveraging the difference coarray technique, the sparse array is transformed into a virtual uniform linear array (VULA) to enrich the spatial sampling; real-valued covariance matrices derived from the array measurements are used as the network’s input features. A final multi-layer perceptron (MLP) regression module then maps the learned representations to continuous DOA angle estimates. This approach capitalizes on the increased degrees of freedom offered by the virtual array while inherently incorporating the array’s geometric relationships via graph-based learning. The proposed C-GNN demonstrates robust performance in noisy, low-data scenarios, reliably estimating source angles even with very limited snapshots. By focusing on methodological innovation rather than bespoke architectural tuning, the framework shows promise for data-efficient DOA estimation in challenging practical conditions. Full article

With the growing global demand for clean energy, the accuracy of wind-power forecasting plays a vital role in ensuring the stable operation of power systems. However, wind-power generation is significantly influenced by meteorological conditions and is characterized by high uncertainty and multiscale fluctuations. Traditional recurrent neural network (RNN) and long short-term memory (LSTM) models, although capable of handling sequential data, struggle with modeling long-term temporal dependencies due to the vanishing gradient problem; thus, they are now rarely used. Recently, Transformer models have made notable progress in sequence modeling compared to RNNs and LSTM models. Nevertheless, when dealing with long wind-power sequences, their quadratic computational complexity (O(L²)) leads to low efficiency, and their global attention mechanism often fails to capture local periodic features accurately, tending to overemphasize redundant information while overlooking key temporal patterns. To address these challenges, this paper proposes a wind-power forecasting method based on dimension-transformed collaborative multidimensional multiscale attention (DTCMMA). This method first employs fast Fourier transform (FFT) to automatically identify the main periodic components in wind-power data, reconstructing the one-dimensional time series as a two-dimensional spatiotemporal representation, thereby explicitly encoding periodic features. Based on this, a collaborative multidimensional multiscale attention (CMMA) mechanism is designed, which hierarchically integrates channel, spatial, and pixel attention to adaptively capture complex spatiotemporal dependencies. Considering the geometric characteristics of the reconstructed data, asymmetric convolution kernels are adopted to enhance feature extraction efficiency. Experiments on multiple wind-farm datasets and energy-related datasets demonstrate that DTCMMA outperforms mainstream methods such as Transformer, iTransformer, and TimeMixer in long-sequence forecasting tasks, achieving improvements in MSE performance by 34.22%, 2.57%, and 0.51%, respectively. The model’s training speed also surpasses that of the fastest baseline by 300%, significantly improving both prediction accuracy and computational efficiency. This provides an efficient and accurate solution for wind-power forecasting and contributes to the further development and application of wind energy in the global energy mix. Full article

Steel surface defect detection is a crucial step in ensuring industrial production quality. However, due to significant variations in scale and irregular geometric morphology of steel surface defects, existing detection algorithms show notable deficiencies in multi-scale feature representation and cross-layer multi-scale feature fusion efficiency. To address these challenges, this paper proposes an improved real-time steel surface defect detection model, NGD-YOLO, based on YOLOv5s, which achieves fast and high-precision defect detection under relatively low hardware conditions. Firstly, a lightweight and efficient Normalization-based Attention Module (NAM) is integrated into the C3 module to construct the C3NAM, enhancing multi-scale feature representation capabilities. Secondly, an efficient Gather–Distribute (GD) mechanism is introduced into the feature fusion component to build the GD-NAM network, thereby effectively reducing information loss during cross-layer multi-scale information fusion and adding a small target detection layer to enhance the detection performance of small defects. Finally, to mitigate the parameter increase caused by the GD-NAM network, a lightweight convolution module, DCConv, that integrates Efficient Channel Attention (ECA), is proposed and combined with the C3 module to construct the lightweight C3DC module. This approach improves detection speed and accuracy while reducing model parameters. Experimental results on the public NEU-DET dataset show that the proposed NGD-YOLO model achieves a detection accuracy of 79.2%, representing a 4.6% mAP improvement over the baseline YOLOv5s network with less than a quarter increase in parameters, and reaches 108.6 FPS, meeting the real-time monitoring requirements in industrial production environments. Full article

With the gradual development of digital twin technology from theory to practice, the importance of the efficient reuse of existing digital twin models has become increasingly prominent in order to reduce the waste of resources and additional costs caused by repeated modeling. To address the difficulty of reusing multi-dimensional model information (MMI) in existing digital twin models during the conversion process from geometric models to digital twin models, this paper proposes a method for reusing MMI in discrete workshops. First, MMI and its representations are defined and constructed. Subsequently, a model-matching approach is introduced to identify appropriate MMIs for geometric models. Following this, a reuse strategy for workshop MMIs is thoroughly explained. Finally, the effectiveness of the proposed method is validated through case studies in the arc-welding workshop. The accuracy of single-model matching remains consistently at 1 across all model tests, and the proposed method reduces the total number of operations by 126 (94.7%) compared to existing methods in multi-device model construction. The results show that this method can effectively organize the workshop digital twin model, compensate for the shortage of digital twin model reuse, and help engineers reuse the existing MMI to build a digital twin model. Full article

Identifying correspondences of road segments in different road networks, namely road-network matching, is an essential task for road network-centric data processing such as data integration of road networks and data quality assessment of crowd-sourced road networks. Traditional road-network matching usually relies on feature engineering and parameter selection of the geometry and topology of road networks for similarity measurement, resulting in poor performance when dealing with dense and irregular road network structures. Recent development of graph neural networks (GNNs) has demonstrated unsupervised modeling power on road network data, which learn the embedded vector representation of road networks through spatial feature induction and topology-based neighbor aggregation. However, weighting spatial information on the node feature alone fails to give full play to the expressive power of GNNs. To this end, this paper proposes a Spatial Pattern-aware Graph EMbedding learning method for road-network matching, named SP-GEM, which explores the idea of spatially-explicit modeling by identifying spatial patterns in neighbor aggregation. Firstly, a road graph is constructed from the road network data, and geometric, topological features are extracted as node features of the road graph. Then, four spatial patterns, including grid, high branching degree, irregular grid, and circuitous, are modelled in a sector-based road neighborhood for road embedding. Finally, the similarity of road embedding is used to find data correspondences between road networks. We conduct an algorithmic accuracy test to verify the effectiveness of SP-GEM on OSM and Tele Atlas data. The algorithmic accuracy experiments show that SP-GEM improves the matching accuracy and recall by at least 6.7% and 10.2% among the baselines, with high matching success rate (>70%), and improves the matching accuracy and recall by at least 17.7% and 17.0%, compared to the baseline GNNs, without spatially-explicit modeling. Further embedding analysis also verifies the effectiveness of the induction of spatial patterns. This study not only provides an effective and practical algorithm for road-network matching, but also serves as a test bed in exploring the role of spatially-explicit modeling in GNN-based road network modeling. The experimental performances of SP-GEM illuminate the path to develop GeoEmbedding services for geospatial applications. Full article