Search Results (46)

Campus streetscapes are a key part of universities’ everyday public realm, yet the same scene may be perceived positively in one dimension while negatively in another. To diagnose such multi-dimensional perceptual differences and translate them into actionable design evidence, this study develops an interpretable vision analytics framework for adaptive campus design. Using 72,733 Baidu Street View images collected from 41 campuses in mainland China, the study integrates ResNet-50-based perception prediction, spatial element extraction, XGBoost–SHAP-based mechanism interpretation, Kruskal–Wallis H testing, and GIS-based scene mapping. Supported by supplementary in situ validation, six types of multi-dimensional perceptual differences were identified. Sky, buildings, vegetation, hardscape, and terrain were found to be the five most important spatial elements overall, among which sky, buildings, and vegetation repeatedly emerged as the dominant core elements distinguishing different perceptual types. These elements do not act independently or linearly, but jointly shape different types of multi-dimensional perceptual differences through nonlinear threshold effects and interactions. These perceptual difference types were further found to cluster in recognizable campus scenes, including main roads, plazas, lawns, forest belts, and lakeside spaces. Based on these findings, scene-specific piecemeal optimization strategies were derived to support the coordinated enhancement of perceived safety, liveliness, and beauty. Overall, the study shows that campus perception is shaped by holistic spatial configurations rather than the simple accumulation of isolated elements, and provides a quantitative basis for iterative, feedback-oriented adaptive campus design. Full article

With the continuous expansion of maritime trade scale, ports have put forward increasingly higher requirements for transshipment efficiency. Container twist lock disassembly is a key link in the loading and unloading process, and its automation level has a significant impact on the ship’s berthing time at the port. Aiming at the demand of automated disassembly for high-precision 3D vision, this paper proposes a multi-view point cloud local registration method for twist lock recognition. First, Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) is used to extract the keyhole region with the highest overlap in multi-view point clouds, reducing the interference from non-overlapping structures. Then, a two-stage strategy of “coarse registration + fine registration” is adopted: initial alignment is achieved through Random Sample Consensus (RANSAC), and the Iterative Closest Point (ICP) algorithm is improved by combining adaptive distance threshold and normal consistency constraint to complete fine registration. Experimental results show that the proposed method outperforms the global registration scheme in both accuracy and efficiency: the Root Mean Square Error (RMSE) is reduced to 2.15 mm, the Relative Mean Distance (RMD) is reduced to 1.81 mm, and the registration time is approximately 2.41 s. Compared with global registration, the efficiency is improved by 44.2%, which can meet the real-time requirements of continuous operation at automated terminals for the perception link and the time constraints for subsequent manipulator control. The research results preliminarily verify the application potential of this method in the scenario of automated twist lock disassembly. Full article

Multi-view clustering (MVC) is crucial for exploiting complementary information from multi-view data. Anchor-based MVC methods are efficient for large-scale tasks but lack the ability to balance view-specific local complementarity and cross-view global consistency. To address this issue, we propose GL4-MVC, a dual-level anchor graph learning framework. It constructs anchor graphs with integrated adaptive learning of view-specific local anchors and concatenated a priori cross-view global anchor guidance, with an orthogonal mapping matrix enabling cross-level alignment to ensure effective guidance of global information for local learning. GL4-MVC is scalable and suitable for large-scale data. Extensive experimental results confirm the effectiveness and efficiency of GL4-MVC. Full article

Historic linear corridors in living-heritage settings concentrate identity, everyday mobility, and visitor experience. Balancing authenticity, adaptability, and publicness therefore benefits from evidence that jointly characterizes long-term physical change, network accessibility, and eye-level interface conditions. Existing assessments often focus on façades or single time slices, leaving limited evidence that relates decades of built-fabric reconfiguration (changes in building footprints, street edges, and open-space fragmentation) to multi-scale accessibility and pedestrian-facing qualities. We propose an integrated and interpretable workflow for the Beishan Street corridor in the West Lake World Heritage core (Hangzhou) over 1929–2024. Scale-sensitive morphological metrics, multi-radius network measures (integration and centrality), and street-view semantic segmentation are aligned at corridor-segment resolution and examined together with segment-level functional intensity derived from POIs using transparent linear models. The results indicate a long-term shift from a lakeshore-led to a road-led spatial logic, followed by post-2000 stabilization near saturation. Average integration increases, while the high-integration tail becomes thinner. In connector-removal scenarios, the eastern segment shows a relative accessibility decline, and a central hinge node emerges as a vulnerability hotspot (bottleneck) where through-movement concentrates. Eye-level profiles differ by segment: the west exhibits maximal canopy and lower sky visibility, the center shows stronger continuous walls around compounds with intermittent forecourt openings, and the east is characterized by compact residential heritage frontage with low vegetation. Segment-level associations suggest that address and wayfinding density tends to co-occur with clearer frontages, wider sky cones, and stronger tree cover. Transportation-related and access/passage facilities tend to co-occur with higher ground-plane legibility, measured as wider and more continuous road and sidewalk surfaces. Medical and government clusters tend to co-occur with lower sky openness. Recommended actions include the following: (1) mesh-aware protection of key connectors and the hinge, (2) segment-specific targets for façade share and ground cues with planned punctuations, (3) tailored interface standards for institutional clusters, (4) scalable address and wayfinding systems, and (5) event staging that preserves effective roadway and sidewalk capacity. Full article

Tracking worker identities across cameras is increasingly important for advanced construction site monitoring, such as safety and productivity monitoring. However, current computer vision-based tracking faces challenges in reliably associating worker identities due to frequent occlusions and extreme viewpoint shifts between aerial and ground cameras, resulting in fragmented trajectories and ID switches. This study proposes a Dual-Stage Graph-based Association framework that integrates worker detections across multiple views using complementary Re-identification models and camera-aware adaptive thresholding. The framework synergistically combines TransReID for viewpoint-invariant global features and BPBReID for occlusion-robust part-based features, producing more discriminative representations. Data association leverages a graph-based clustering approach to combine representation features, camera topology, and temporal cues for robust identity maintenance. The first stage enables cross-view clustering while preventing false matches, and the second stage ensures long-term identity stability through EMA-based gallery management. Experiments on two construction sites demonstrate that the proposed framework achieves an HOTA of 39.85% and an IDF1 of 63.58%, outperforming existing baselines while reducing ID switches by 35.0%. Results on the AG-ReID.v2 benchmark demonstrate strong generalization with 90.82% Rank-1 accuracy in aerial-to-CCTV matching. The approach highlights initial feasibility for cross-view multi-camera tracking in construction with potential for extension to more complex industrial environments. Full article

Background/Objectives: Accurate segmentation of gliomas in 3D volumetric MRI is critical for diagnosis, treatment planning, and surgical navigation. However, the scarcity of expert annotations limits the applicability of supervised learning approaches, motivating the development of unsupervised methods. This study presents US-ATHC (Unsupervised Segmentation using Adaptive Thresholding and Hierarchical Clustering), a fully unsupervised two-step pipeline for both global tumor detection and multi-class subregion segmentation. Methods: In the first step, a global tumor mask is extracted by combining adaptive thresholding (Sauvola) with morphological processing on individual MRI slices. The resulting candidates are fused across axial, coronal, and sagittal views using a strict 3D consistency criterion. In the second step, the global mask is refined into a three-class segmentation (active tumor, edema, and necrosis) using optimized affinity propagation clustering. Results: The method was evaluated on the BraTS 2021 dataset, demonstrating accurate tumor and subregion segmentation that outperformed both classical clustering techniques and state-of-the-art deep learning models. External validation on the Gliobiopsy dataset from the University Hospital of Poitiers confirmed robustness and practical applicability in real-world clinical settings. Conclusions: US-ATHC establishes an unsupervised paradigm for glioma segmentation that balances accuracy with computational efficiency. Its annotation-independent nature makes it suitable for scenarios with scarce labeled data, supporting integration into clinical workflows and large-scale neuroimaging studies. Full article

Multi-view clustering, which improves clustering performance by using the complementary and consistent information from multiple diverse feature sets, has been attracting increasing research attention owing to its broad applicability in real world scenarios. Conventional approaches typically leverage this complementarity by projecting different views into a common embedding space using view-specific or shared non-linear neural networks. This unified embedding is then fed into standard single-view clustering algorithms to obtain the final clustering results. However, a single common embedding may be insufficient to capture the distinct or even contradictory characteristics of multi-view data, due to the divergent representational capacities of different views. To address this issue, we propose a mixture of experts (MoE) based embedding learning method that adaptively models inter-view relationships. This architecture employs a typical MoE module as a projection layer across all views, which uses shared expert and several groups of experts for consistency and complementarity mining. Furthermore, a Kullback-Leibler divergence based objective with over clustering is designed for clustering-oriented embedding learning. Extensive experiments on six benchmark datasets confirm that our method achieves superior performance compared to a number of state-of-the-art approaches. Full article

Using Machine Learning (ML) in educational management transforms higher education strategy. This study examines students’ views on machine learning (ML) technologies and how they might be used to plan, monitor, and predict student performance. The Faculty of Industrial Engineering and Robotics surveyed 118 third-year undergraduates. It featured closed- and open-ended questions to collect quantitative and qualitative data. Descriptive statistics showed broad patterns, inferential tests (Chi-square, t-test, ANOVA) showed group differences, regression models predicted school outcomes, and exploratory factor analysis (EFA) and clustering found hidden attitudes and student profiles. A multi-method quantitative approach combining descriptive statistics, inferential tests, regression modeling, and exploratory techniques (EFA and clustering) was employed. The findings show that most students realize that ML may help them be more productive, adapt their study pathways, and learn about the future. Concerns remain regarding its accuracy, overreliance, and morality. The findings indicate that ML can both support and challenge educational management, depending on how responsibly it is implemented. Results show that institutions may utilize ML as a strategic tool to boost academic progress and make better judgments, provided they incorporate it responsibly and follow ethical rules and training. Full article

Accurate interpretation of multimodal wearable data remains challenging in occupational environments due to heterogeneous sensing modalities, motion artifacts, and dynamic work conditions. This study proposes and validates an adaptive multimodal clustering framework for occupational health monitoring. The framework jointly models physiological, activity, and location data from 24 highway-maintenance workers, incorporating a silhouette-guided feature-weighting mechanism, multi-scale temporal change-point detection, and KDE-based spatial analysis. Specifically, the analysis identified three distinct and interpretable behavioral–physiological states that exhibit significant physiological differences (p < 0.001). Notably, it reveals a predominant yet heterogeneous baseline state alongside acute high-intensity and episodic surge states, offering a nuanced view of occupational risk beyond single-modality thresholds. The integrated framework provides a principled analytical workflow for spatiotemporal health risk assessment in field settings, particularly for vibration-intensive work scenarios, while highlighting the complementary role of physiological indicators in low- or static-motion tasks. This framework is particularly effective for vibration-intensive tasks involving powered tools. However, to mitigate potential biases in detecting static heavy-load activities with limited wrist motion (e.g., lifting or carrying), future extensions should incorporate complementary weighting of physiological indicators such as heart rate variability. Full article

Multi-view learning has recently gained considerable attention in graph representation learning as it enables the fusion of complementary information from multiple views to enhance representation quality. However, most existing studies neglect that irrelevant views may introduce noise and negatively affect representation quality. To address the issue, we propose a novel multi-view representation learning framework called a View Filter-driven graph representation fusion network, named ViFi. Following the “less for better” principle, the framework focuses on filtering informative views while discarding irrelevant ones. Specifically, an entropy-based adaptive view filter was designed to dynamically filter the most informative views by evaluating their feature–topology entropy characteristics, aiming to not only reduce irrelevance among views but also enhance their complementarity. In addition, to promote more effective fusion of informative views, we propose an optimized fusion mechanism that leverages the filtered views to identify the optimal integration strategy using a novel information gain function. Through extensive experiments on classification and clustering tasks, ViFi demonstrates clear performance advantages over existing state-of-the-art approaches. Full article

In practical application, the gathered multi-view data typically misses samples, known as incomplete multi-view data. Most existing incomplete multi-view clustering methods obtain consensus information in multi-view data by completing incomplete data using zero, mean values, etc. These approaches often ignore the higher-order relationship and structural information between different views. To alleviate the above problems, we propose enhanced tensor incomplete multi-view clustering with dual adaptive weight (ETIMC), which can acquire the higher-order relationship, and structural information between multiple perspectives, adaptively recover the missing samples and distinguish the contribution degree of different views. Specifically, the embedded representations obtained from incomplete multi-view data are stacked into a third-order tensor to capture the higher-order relationship. Then, a consensus matrix can be drawn from these potential representations via a self-weighting mechanism. Additionally, we adaptively reconstruct the missing samples while capturing structural information by the hypergraph Laplacian item. Moreover, we integrate the embedded representation of each view, tensor constraints, hypergraph Laplacian regularization, and dual adaptive weighted mechanisms into a unified framework. Experimental results on natural and synthetic incomplete datasets show the superiority of ETIMC. Full article

Counting small, densely clustered objects from low-altitude aerial views is challenging due to large scale variations, complex backgrounds, and severe occlusion, which often degrade the performance of fully supervised or density-regression methods. To address these issues, we propose a weakly supervised crowd counting framework that leverages point-level supervision and a feature-adaptive fusion strategy to enhance perception under low-altitude aerial views. The network comprises a front-end feature extractor and a back-end fusion module. The front-end adopts the first 13 convolutional layers of VGG16-BN to capture multi-scale semantic features while preserving crucial spatial details. The back-end integrates a Feature-Adaptive Fusion module and a Multi-Scale Feature Aggregation module: the former dynamically adjusts fusion weights across scales to improve robustness to scale variation, and the latter aggregates multi-scale representations to better capture targets in dense, complex scenes. Point-level annotations serve as weak supervision to substantially reduce labeling cost while enabling accurate localization of small individual instances. Experiments on several public datasets, including ShanghaiTech Part A, ShanghaiTech Part B, and UCF_CC_50, demonstrate that our method surpasses existing mainstream approaches, effectively mitigating scale variation, background clutter, and occlusion, and providing an efficient and scalable weakly supervised solution for small-object counting. Full article

Using Shanghai as a case study, this paper develops a multi-source fusion and interpretable machine learning framework. Sentiment indices were extracted from Weibo check-ins with ERNIE 3.0, street-view elements were identified using Mask2Former, and urban indicators like the Normalized Difference Vegetation Index, floor area ratio, and road network density were integrated. The coupling between residents’ sentiments and streetscape features during heatwaves was analyzed with Extreme Gradient Boosting, SHapley Additive exPlanations, and GeoSHAPLEY. Results show that (1) the average sentiment index is 0.583, indicating a generally positive tendency, with sentiments clustered spatially, and negative patches in central areas, while positive sentiments are concentrated in waterfronts and green zones. (2) SHapley Additive exPlanations analysis identifies NDVI (0.024), visual entropy (0.022), FAR (0.021), road network density (0.020), and aquatic rate (0.020) as key factors. Partial dependence results show that NDVI enhances sentiment at low-to-medium ranges but declines at higher levels; aquatic rate improves sentiment at 0.08–0.10; openness above 0.32 improves sentiment; and both visual entropy and color complexity show a U-shaped relationship. (3) GeoSHAPLEY shows pronounced spatial heterogeneity: waterfronts and the southwestern corridor have positive effects from water–green resources; high FAR and paved surfaces in the urban area exert negative influences; and orderly interfaces in the vitality corridor generate positive impacts. Overall, moderate greenery, visible water, openness, medium-density road networks, and orderly visual patterns mitigate negative sentiments during heatwaves, while excessive density and hard surfaces intensify stress. Based on these findings, this study proposes strategies: reducing density and impervious surfaces in the urban area, enhancing greenery and quality in waterfront and peripheral areas, and optimizing urban–rural interfaces. These insights support heat-adaptive and sustainable street design and spatial governance. Full article

The goal of multi-view graph clustering (MVGC) for remote sensing data is to obtain a consistent partitioning by capturing complementary and consensus information across multiple views. However, numerous ambiguous background samples in multi-view remote sensing data increase structural heterogeneity while simultaneously hindering effective information extraction and fusion. Existing MVGC methods cannot selectively integrate and fully refine both graph structure and node attribute information for consensus representation learning. Furthermore, current methods tend to overlook distant nodes, thus failing to capture the global graph structure. To solve these issues, we propose a novel method called Improved Multi-View Graph Clustering with Global Graph Refinement (IMGCGGR). Specifically, we first design a view-specific fusion network (VSFN) to extract and integrate node attribute and structural information into view-specific representation for each view. VSFN not only utilizes a global self-attention mechanism to enhance the global properties of structural information but also constructs a clustering loss through a self-supervised strategy to guide the view-specific clustering distribution assignment. Moreover, to enhance the capability of view-specific representation, a learnable attention-driven aggregation strategy is introduced to flexibly fuse the attribute and structural feature. Then, we adopt a cross-view fusion module to adaptively merge multiple view-specific representations for generating the final consensus representation. Comprehensive experiments show that IMGCGGR achieves significant clustering performance improvements over baseline methods across various benchmark datasets. Full article

Historic districts face persistent challenges balancing heritage preservation and urban vitality due to fragmented governance and static conservation. This study develops a multi-source data-driven evaluation system coupling spatial quality and urban vitality, focusing on China’s Republican-era historic districts with Nanjing’s Yihe Road as a case study. Integrating field surveys and big data (street view imagery, POI data, heatmaps), we quantitatively assess environmental quality and vitality. Key findings reveal a distinct spatial pattern: “high-quality concentration internally” and “high-vitality concentration externally,” where core areas exhibit functional homogenization and low vitality, while peripheries show high pedestrian activity but lack spatial coherence. Clustering analysis categorizes streets into four types based on quality and vitality levels, highlighting contradictions between static conservation and adaptive reuse. The study deepens understanding of spatial differentiation mechanisms and reveals universal patterns for sustainable development strategies. A multi-tiered governance strategy is proposed: urban-level flexible governance harmonizes cross-departmental policies via adaptive planning, district-level differentiated governance activates spatial value through functional reorganization, and street-level fine-grained management prioritizes incremental micro-renewal. The research underscores the critical need to balance heritage preservation with contemporary functional demands during urban renewal, offering a practical framework to resolve spatial conflicts and reconcile conservation with regeneration. Full article