Search Results (43,459)

Despite offering rich complementary information, multimodal remote sensing images collected by diverse sensors increase the computational burden in clustering. To alleviate this issue, we devise an efficient multimodal clustering approach (MCSM) on superpixel manifolds formed by superpixel segmentation. The MCSM jointly learns cluster representation of all modalities and a consensus cluster membership graph that fuses the multimodal representation to yield clusters. To capture the local geometric structure of the superpixel manifolds, the optimization is constrained by manifold regularization of the consensus graph. In contrast to vanilla multiview subspace clustering techniques, the proposed approach does not rely on spectral clustering, and only involves element-wise product and multiplication on small-scale matrices. In addition, we prove that the MSCM is a special case of classic low-rank subspace clustering models, providing a perspective for understanding the learned cluster graphs. Extensive experiments are conducted on three popular multimodal remote sensing datasets, showing that the proposed method achieves competitive clustering performance compared to state-of-the-art methods, and significantly outperforms the latter in computational efficiency. Full article

Sustainable building research increasingly incorporates AI technologies to enhance efficiency and decision-making, yet little is known about how algorithmic mediation shapes the cultural identity processes essential for heritage sustainability. This study proposes and validates a Content-Driven Dual-Track (CDDT) Model examining the relationships among AI content quality (AIQ), technology acceptance, and Architectural Cultural Identity (ACI). Based on a survey of 631 architecture and design students, structural equation modeling identified three patterns. First, AIQ strongly predicts perceived usefulness, perceived ease of use (PEOU), and perceived enjoyment, supporting a content-driven formation of system evaluations. Second, an “ease-of-use paradox” is observed: PEOU negatively relates to ACI (β = −0.18, p = 0.005), suggesting that frictionless browsing may hinder the cognitive effort required for deeper heritage value internalization. Third, ACI independently predicts continuous engagement intention (β = 0.110, p < 0.05) and correlates strongly with perceived content quality (r = 0.719, p < 0.001). Together, these findings suggest that while operational convenience serves as an essential entry point, sustainable digital heritage engagement requires moving beyond interface usability to prioritize the cultural depth of content assets, a principle applicable to BIM-driven cultural heritage systems and AI-based educational platforms. Full article

Accurate flood detection is critical for disaster response, yet the scarcity of diverse annotated datasets hinders robust model development. Existing resources typically suffer from limited geographic scope and insufficient annotation granularity, restricting the generalization capabilities of computer vision methods. To bridge this gap, we introduce AIFloodSense, a comprehensive evaluation benchmark designed to advance domain-generalized Artificial Intelligence for climate resilience. The dataset comprises 470 high-resolution aerial images capturing 230 distinct flood events across 64 countries and six continents. Unlike prior benchmarks, AIFloodSense ensures exceptional global diversity and temporal relevance (2022–2024), supporting three complementary tasks: (i) Image Classification, featuring novel sub-tasks for environment type, camera angle, and continent recognition; (ii) Semantic Segmentation, providing precise pixel-level masks for flood, sky, buildings, and background; and (iii) Visual Question Answering (VQA), enabling natural language reasoning for disaster assessment. We provide baseline benchmarks for all tasks using state-of-the-art architectures, demonstrating the dataset’s complexity and its utility in fostering robust AI tools for environmental monitoring. Crucially, we show that despite its compact size, AIFloodSense enables better generalization on external test sets than much larger alternatives, validating the premise that rigorous diversity is more effective than scale for training robust flood detection models, and is made publicly available to accelerate further research in the field. Full article

Multi-Object Tracking (MOT) is a fundamental research topic in the field of computer vision, with broad application potential in unmanned aerial vehicle (UAV) videos. However, existing methods still face significant challenges in detection discriminability and identity association stability due to the small scale and weak appearance of objects under aerial viewpoints, as well as complex background interference. To address these issues, we propose an Edge-Graph Enhanced Network (EGEN) for UAV aerial MOT, aiming to improve the performance of small object detection (SOD) and tracking in complex scenes. The framework follows a one-step tracking paradigm and consists of three main components: object detection, embedding feature extraction, and data association. In the detection stage, we design an Edge-Guided Gaussian Enhancement Module (EGGEM), which models edge relationships between objects and backgrounds from a global perspective and selectively enhances Gaussian features guided by edge information, thereby strengthening key structural features of small objects while suppressing background interference. In the embedding feature extraction stage, we develop a Graph-Guided Embedding Enhancement Module (GGEEM), which explicitly represents re-identification (ReID) embeddings as a graph structure and jointly models nodes and their neighborhood relationships to fully capture inter-object associations and enhance embedding discriminability. In the data association stage, we introduce a hierarchical two-stage association strategy to match objects with different confidence levels separately, improving tracking stability and robustness. Extensive experiments on the VisDrone, UAVDT, and self-constructed WildDrone datasets demonstrate that the proposed method significantly outperforms state-of-the-art approaches in both SOD and MOT, demonstrating strong generalization and practical applicability. Full article

Maintaining high quality of water resources is essential to the physical health of mankind and sustainable development of society. Accordingly, it is necessary to detect anomalies in water quality variations, which may be caused by pollution. However, prompt anomaly detection is a challenging task, either demanding a lot of human effort or yielding low accuracy, due to the nonlinear and non-stationary characteristics of water quality data. In this paper, we present an efficient real-time anomaly detection scheme which boosts detection accuracy while mitigating human effort. The scheme takes a prediction–detection–verification approach in which a deep learning prediction model is built from historical data and is used to predict future values. The predicted values are compared with the actual measurements, and the residuals are inspected by a detection model. An alarm is sent to field engineers for verification for each anomaly detected by the detection model, and the verification result is analyzed by the scheme to maintain high prediction and detection accuracy. Experiments on multiple water quality datasets show that the proposed scheme achieves significantly higher recall rates and lower false alarm rates in almost all test scenarios, compared with schemes that do not utilize verification. Full article

Autonomous exploration in unknown environments remains a challenging problem for UAVs. This paper proposes a hierarchical exploration planning framework that explicitly leverages real-time acquired prior knowledge to improve exploration efficiency. To efficiently represent the structural information embedded in the prior knowledge, two map structures, namely the quasi-prior map and the hybrid-topo map, are designed, enabling more reasonable space partition and facilitating exploration planning. Subsequently, based on the hybrid-topo map, the hierarchical exploration planner computes a global exploration guidance that provides an efficient traversal order over all unexplored regions. The local coverage problem in unknown regions is formulated as a coverage traveling salesman problem (CTSP), where visibility information derived from the hybrid-topo map is exploited to optimize local viewpoint sequences with high coverage efficiency. Finally, a long-horizon trajectory planning strategy is proposed to maintain high flight speed while ensuring safety and dynamic feasibility. Simulations demonstrate that the proposed framework significantly outperforms state-of-the-art exploration methods in terms of exploration efficiency, while ablation studies further validate the effectiveness of each module. Real-world experiments are conducted to confirm the practical capability of the proposed approach. Full article

Existing general image inpainting works require the user to customize a mask to indicate the region to be inpainted. However, the mask is often hard to calibrate accurately in real-world applications, e.g., graffiti removal. Blind image inpainting aims to automatically restore the degraded image into the visually reasonable one without a priori mask to indicate the area to be repaired. So far, most proposed blind inpainting methods convert the task into general inpainting by predicting the mask before inpainting. However, these methods are highly dependent on mask prediction results, which may produce inferior inpainting results if the prediction is inaccurate. To address this issue, we propose a two-stage blind inpainting framework with two novel designs: (1) cross-space contrastive learning, to remove the noise in the degraded images and realize the automatic inpainting in the latent space by reducing the distance of the degraded images and the corresponding complete images in the latent space; and (2) mask-aware adversarial training, to minimize the mutual information between the inpainted feature and the noise. Extensive experiments prove that our blind inpainting framework performs better on multiple datasets than the state-of-the-art methods. Full article

Traditional mechanized chestnut harvesting is too costly for small producers, non-selective, and prone to damaging nuts. Accurate, reliable detection of chestnuts on the orchard floor is crucial for developing low-cost, vision-guided automated harvesting technology. However, developing a reliable chestnut detection system faces challenges in complex environments with shading, varying natural light conditions, and interference from weeds, fallen leaves, stones, and other foreign on-ground objects, which have remained unaddressed. This study collected 319 images of chestnuts on the orchard floor, containing 6524 annotated chestnuts. A comprehensive set of 29 state-of-the-art real-time object detectors, including 14 in the YOLO (v11–v13) and 15 in the RT-DETR (v1–v4) families at various model scales, was systematically evaluated through replicated modeling experiments for chestnut detection. Experimental results show that the YOLOv12m model achieved the best mAP@0.5 of 95.1% among all the evaluated models, while RT-DETRv2-R101 was the most accurate variant among the RT-DETR models, with mAP@0.5 of 91.1%. In terms of mAP@[0.5:0.95], the YOLOv11x model achieved the best accuracy of 80.1%. All models demonstrated significant potential for real-time chestnut detection, and YOLO models outperformed RT-DETR models in terms of both detection accuracy and inference, making them better suited for on-board deployment. This work lays a foundation for developing AI-based, vision-guided intelligent chestnut harvest systems. Full article

Mushroom farms in the United States continue to face persistent labor shortages, especially during the harvesting of white button mushrooms (Agaricus bisporus) which requires selective picking by skilled workers. This study addresses this challenge by developing a depth-guided computer vision framework for automated mushroom detection, segmentation, and tracking to support timely harvest decisions, providing the foundation needed to support selective and timely robotic harvesting. The specific objectives of the study were to (1) develop a novel image-processing algorithm (RD-GuideNet) that integrates RGB and depth images for accurate detection and segmentation of mushrooms; (2) implement a custom depth-guided tracking algorithm to preserve mushroom identities across sequential frames; (3) compare the performance of RD-GuideNet against state-of-the-art deep learning models, YOLOv8 and YOLOv11, focusing on segmentation and tracking accuracies. The proposed RD-GuideNet achieved an F1-score of 0.93 for segmentation, outperforming YOLOv8 (0.88) and YOLOv11 (0.86), and produced sharper, more geometrically consistent boundaries that closely followed true mushroom cap contours. Its tracking consistency reached 92.7%, compared to YOLOv8 (95.3%) and YOLOv11 (94.6%). Although slightly lower, RD-GuideNet maintained high temporal consistency across dense mushroom beds. These results suggest that depth-based geometric reasoning and deep learning approaches exhibit complementary strengths in dense production scenes. Combining the two may further enhance detection reliability and shape fidelity, supporting high-precision perception for autonomous mushroom harvesting. A comprehensive quantitative evaluation of such a hybrid framework will be investigated in future work. Full article

Maritime decarbonization has shifted from a long-term aspiration to an engineering and systems-integrated problem under near-term compliance pressure. International regulatory bodies, governments, and a wide array of private-sector coalitions will tighten greenhouse-gas fuel-emission standards from 2028, translating climate targets into enforceable cost signals and accelerating interest in alternative-fuel and retrofit pathways. This review synthesizes the state of the art (SoA) of maritime decarbonization by mapping where technological bottlenecks concentrate along the well-to-wake (WtW) value chain for the main candidate pathways: biofuels, LNG/bio-LNG, hydrogen, ammonia, e-methanol, and electrification, and by benchmarking them side-by-side using a unified framework designed to compare their realizable well-to-wake GHG-reduction potential under maritime operating constraints. Building on that comparative lens, this work aims to connect pathway readiness to the near-term market and regulatory reality, while the alternative-fuel-capable fleet is projected to expand rapidly, creating a structural capability vs. supply gap, in which, for example, ship readiness can outpace low-GHG fuel availability and bunkering rollout. The merged evidence indicates that near-term abatement will be dominated by scalable drop-in biofuels, whereas deep-sea options (ammonia/hydrogen and e-fuels) remain gated by upstream low-GHG production, port infrastructure, and safety/regulatory maturation. Nevertheless, mid-term deployment of low-GHG fuels can act as a system “relief valve”, reducing infrastructure lock-in and accelerating emissions reductions while zero-carbon fuel supply chains scale up. Full article

Urban blue-green spaces (UBGS) are crucial nature-based solutions for enhancing urban resilience and improving public health. This study examined the experiential relationships linking BGS use to human well-being among users of five urban parks in Delhi, India. Using an integrated experience-centered framework, we collected in-situ survey data (n = 411) to profile usage patterns, assess environmental quality, and quantify restorative outcomes grounded in Attention Restoration Theory (ART) and Stress Reduction Theory (SRT). Advanced analytical techniques, including ordinal logistic regression and interpretable machine learning (SHAP), were used to identify the key factors associated with user satisfaction. The results revealed that for these respondents, BGS appeared to function as an essential neighbourhood, with over 40% visiting three or more times per week. Although visual attractiveness was rated positively, deficits in noise buffering and amenities indicated a gap between aesthetic and functional qualities. Restorative benefits, including emotional calmness, mood refreshment, and fatigue recovery, were consistently reported among respondents. Analyses showed that embodied experiences, particularly post-visit relaxation and physical comfort, were more strongly associated with user satisfaction. SHAP interpretation highlighted seating adequacy, routine use, and thermal comfort as prominent contributors, suggesting somatic relief may be particularly salient. This study provides exploratory evidence from a Global South megacity and context-sensitive insights into how restorative processes operate under high-density urban conditions. The findings show that routine accessibility, basic amenities, and thermal comfort are central to the everyday functioning of blue-green spaces as urban infrastructure, underscoring the need for experience-responsive and equity-oriented urban greening policies in high-density cities. Full article

In China’s stock-based renewal agenda, many old residential communities display pronounced intergenerational overlap, in which grandparental childcare becomes a dominant pattern of outdoor-space use. Against the backdrop of age-structure shifts, population ageing, and persistently low fertility, community-level outdoor-space supply, distributive equity, and environmental adaptability have become key concerns in renewal practice. Yet, practitioners still lack a rankable, low-cost, and implementable evaluation-to-decision workflow. Using Xingshe Community in Dalian, China as an empirical case, this study establishes and tests an integrated “NLP–AHP–GBDT” assessment framework. Guided by policy discourse and planning theory, over 50 semi-structured interviews were processed via NLP-based semantic analysis and keyword mining to derive a two-tier indicator set (criterion and indicator layers). Seven specialists then applied the analytic hierarchy process to elicit indicator weights, and a resident survey was administered to generate weighted performance scores for diagnosing deficiencies. In the feedback-validation stage, we adopted both a qualitative Framework Method and a quantitative GBDT approach, first using the Framework Method to conduct feedback validation based on community residents’ open-ended evaluations. Subsequently, gradient boosting decision trees were used for supervised verification with renewal-scenario data, providing empirical backing for the weighting scheme and the resulting priority order for interventions. The findings suggest that outdoor spaces are broadly serviceable but fall short in intergenerational friendliness, reflecting a structural misalignment between intergenerational activity patterns and spatial provision. Based on the validated priorities, the study proposes modular, incremental micro-renewal measures focusing on safety and emergency accessibility, environmental comfort and caregiving–recreation coupling, and place identity with community organizational mobilization. Full article

Unsupervised change detection (UCD) from heterogeneous bitemporal optical–SAR imagery is challenging due to modality discrepancy, speckle/illumination variations, and the absence of change annotations. We propose MV-S2CD, a vision foundation model (VFM)-based framework that learns a modality-bridged latent space and produces dense change maps in a fully unsupervised manner. To robustly adapt pretrained VFM priors to heterogeneous inputs with minimal task-specific parameters, MV-S2CD incorporates lightweight modality-specific adapters and parameter-efficient low-rank adaptation (LoRA) in high-level layers. A shared projector embeds the two observations into a common geometry, enabling consistent cross-modal comparison and reducing sensor-induced domain shift. Building on the bridged representation, we design a dual-branch change reasoning module that decouples structure-sensitive cues from semantic-consistency cues: a structure pathway preserves fine boundaries and local variations, while a semantic-consistency pathway employs reliability gating and multi-scale context aggregation to suppress pseudo-changes caused by modality-specific nuisances and residual misregistration. For label-free optimization, we develop a difference-centric self-supervision scheme with two perturbation views and reliability-guided pseudo-partitioning, jointly enforcing pseudo-unchanged invariance, pseudo-changed/unchanged separability, and sparsity and edge-preserving regularization. Experiments on three heterogeneous optical–SAR benchmarks demonstrate that MV-S2CD consistently improves the Precision–Recall trade-off and achieves state-of-the-art performance among unsupervised baselines, while remaining backbone-flexible and efficient. Full article

Traditional navigation methods work well in known, static environments but degrade in real-world settings with dynamic and unpredictable obstacles. This paper presents Double Deep Q-Network with A* guidance (DDQNA), a hybrid navigation algorithm that enables an agent to traverse mazes containing static and dynamic obstacles while maintaining a low probability of collision. DDQNA combines A* guidance with Double Deep Q-Network (DDQN) learning using an $ϵ$-greedy policy, and it introduces a redesigned reward function and an improved action-selection mechanism to better exploit A*’s directional cues during training. We evaluate DDQNA in a custom Pygame simulation across 11 environments of increasing difficulty. Experimental results show that DDQNA consistently outperforms the standard DDQN and other state-of-the-art reinforcement learning baselines, achieving higher goal-reaching rates, fewer visited cells, shorter computation times, and higher cumulative rewards. These results indicate that DDQNA provides both effective navigation and computational efficiency in complex environments with static and dynamic obstacles. Full article

The experience of being acknowledged by one’s coach has been highlighted as important, but the pedagogical approach of being seen has not been empirically explored within sport. The purpose of this study was to investigate the extent to which young Norwegian football players experienced being seen by their head coach in football, as well as to examine gender differences in these experiences with a previous validated questionnaire, originally developed for students within physical education, but adapted for football. Using a list of all teams participating in the Boys 19 league and the Girls 17 league in Trøndelag County, 7 boys’ teams and 9 girls’ teams were randomly selected. A total of 212 players (107 boys and 105 girls) responded to the questionnaire. Participants’ ages ranged from 15 to 19 years. The results showed that 83 percent of the boys and 87 percent of the girls agreed (slightly to strongly) that they experienced being seen by their head coach during training or football matches. There were no significant gender differences regarding this experience, nor in four of the five underlying factors contributing to being seen. However, a significant gender difference was found according to good dialogue, where girls scored higher than boys when rating their coaches. Finally, the results indicated that players perceived their coach as most competent in facilitating good dialogue, and least competent in involving players in assessment and goal setting, and in creating opportunities for players to showcase themselves. Based on these results, coaches should actively create opportunities for dialogue before, during, and after training or matches, signaling openness through body language, tone, and availability so players feel comfortable initiating conversation. Coach education programs should emphasize communication strategies that promote psychological safety and belonging, including practical steps such as brief one-on-one conversations during warm-up or cool-down to help players feel seen without disrupting team flow. The gender difference in good dialogue highlights the importance of tailoring communication strategies to individual needs while ensuring that dialogue opportunities are accessible to all players. Full article