Search Results (3,304)

Landscape visual evaluation is a key method for assessing the value of visual landscape resources. This study aims to enhance the visual environment and sensory quality of urban landscapes by establishing standards for the visual comfort of urban natural landscapes. Using line-of-sight and multi-factor analysis algorithms, the method assesses spatial visibility and visual exposure of building clusters in the core urban areas of Harbin, identifying areas and viewpoints with high visual potential. Focusing on the viewpoints of landmark 3D models and the surrounding landscape’s visual environment, the study uses the city’s sky, greenery, and water features as key visual elements for evaluating the comfort of urban natural landscapes. By integrating GIS data, big data street-view photos, and image semantic recognition, spatial analysis algorithms extract both objective and subjective visual values at observation points, followed by mathematical modeling and quantitative analysis. The study explores the coupling relationship between objective physical visual values and subjective perceived visibility. The results show that 3D visual analysis effectively reveals the relationship between landmark buildings and surrounding landscapes, providing scientific support for urban planning and contributing to the development of a more distinctive and attractive urban space. Full article

The generation of 3D digital humans has traditionally relied on multi-view imaging systems and large-scale datasets, posing challenges in cost, accessibility, and real-time applicability. To overcome these limitations, this study presents an efficient pipeline that constructs high-fidelity 3D digital humans from a single frontal image. By leveraging generative AI, the system synthesizes additional views and generates UV maps compatible with the SMPL-X model, ensuring anatomically accurate and photorealistic reconstructions. The generated 3D models are imported into Unity 3D, where they are rigged for real-time motion synchronization using BlazePose-based lightweight pose estimation. To further enhance motion realism, custom algorithms—including ground detection and rotation smoothing—are applied, improving movement stability and fluidity. The system was rigorously evaluated through both quantitative and qualitative analyses. Results show an average generation time of 211.1 s, segmentation accuracy of 92.1%, and real-time rendering at 64.4 FPS. In qualitative assessments, expert reviewers rated the system using the SUS usability framework and heuristic evaluation, confirming its usability and effectiveness. This method eliminates the need for multi-view cameras or depth sensors, significantly reducing the barrier to entry for real-time 3D avatar creation and interactive AI-driven applications. It has broad applications in virtual reality (VR), gaming, digital content creation, AI-driven simulation, digital twins, and telepresence systems. By introducing a scalable and accessible 3D modeling pipeline, this research lays the groundwork for future advancements in immersive and interactive environments. Full article

Multiview clustering (MVC) is a proven, effective approach to boosting the various downstream tasks given by unlabeled data. In contemporary society, domain-specific multiview data, such as multiphase postoperative liver tumor contrast-enhanced computed tomography (CECT) images, may be vulnerable to exploitation by illicit organizations or may not be comprehensively collected due to patient privacy concerns. Thus, these can be modeled as incomplete multiview clustering (IMVC) problems. Most existing IMVC methods have three issues: (1) most methods rely on paired views, which are often unavailable in clinical practice; (2) directly predicting the features of missing views may omit key features; and (3) recovered views still have subtle differences from the originals. To overcome these challenges, we proposed a novel framework named fuzzy clustering combined with information theory arithmetic based on feature reconstruction (FCITAFR). Specifically, we propose a method for reconstructing the characteristics of prevailing perspectives for each sample. Based on this, we utilized the reconstructed features to predict the missing views. Then, based on the predicted features, we used variational fuzzy c-means clustering (FCM) combined with information theory to learn the mutual information among views. The experimental results indicate the advantages of FCITAFR in comparison to state-of-the-art methods, on both in-house and external datasets, in terms of accuracy (ACC) (77.5%), normalized mutual information (NMI) (37.9%), and adjusted rand index (ARI) (29.5%). Full article

How can local governments in the Global South effectively implement and sustain digital public participation initiatives, and what specific roles do public officials and knowledge intermediaries play in catalysing and supporting this digital transformation? In this paper, we respond to this query by examining our experiences as researchers in implementing an ongoing multi-year applied research project on e-participation and policy modelling in various South African municipalities. The project and the country’s ongoing public participation initiatives align with government policy emphasising citizen-centric public service delivery through consultation, transparency, and accountability. We aim to highlight the practical aspects of introducing e-participation mechanisms in local governance structures with different human and material resource capacity levels, which is the case in Global South contexts. Our central question is as follows: How can public officials, working alongside researchers and knowledge intermediaries, navigate the sustainable adoption of e-participation through participatory design, system awareness, and bricolage? We explore this question from the perspective of researchers leading the implementation of a multi-year, participatory action-research project which aims to pilot e-participation in six municipalities across South Africa. In the paper, we analyse the interplay of various socio-technical factors influencing the early stages of implementation and use of e-participation tools in local government. Our findings highlight the importance of building socio-technical agency of front-line public participation officials, exploring malleable technologies that are flexible to adaptation, facilitating peer-learning amongst officials on what works in similar contexts, and having a system view within and across pilots. Full article

With the ever-increasing volume of maritime traffic, the risks of ship navigation are becoming more significant, making the use of advanced multi-source perception strategies and AI technologies indispensable for obtaining information about ship navigation status. In this paper, first, the ship tracking system was optimized using the Bi-YOLO network based on the C2f_BiFormer module and the OC-SORT algorithms. Second, to extract the visual trajectory of the target ship without a reference object, an absolute position estimation method based on binocular stereo vision attitude information was proposed. Then, a perception data fusion framework based on ship spatio-temporal trajectory features (ST-TF) was proposed to match GPS-based ship information with corresponding visual target information. Finally, AR technology was integrated to fuse multi-source perceptual information into the real-world navigation view. Experimental results demonstrate that the proposed method achieves a mAP0.5:0.95 of 79.6% under challenging scenarios such as low resolution, noise interference, and low-light conditions. Moreover, in the presence of the nonlinear motion of the own ship, the average relative position error of target ship visual measurements is maintained below 8%, achieving accurate absolute position estimation without reference objects. Compared to existing navigation assistance, the AR-based navigation assistance system, which utilizes ship ST-TF-based perception data fusion mechanism, enhances ship traffic situational awareness and provides reliable decision-making support to further ensure the safety of ship navigation. Full article

Intracranial aneurysms (IAs), a significant medical concern due to their prevalence and life-threatening nature, pose challenges regarding diagnosis owing to their diminutive and variable morphology. There are currently challenges surrounding automating the segmentation of IAs, which is essential for diagnostic precision. Existing deep learning methods in IAs segmentation tend to emphasize semantic features at the expense of detailed information, potentially compromising segmentation quality. Our research introduces the innovative Dual-Path Fusion Network (DPF-Net), an advanced deep learning architecture crafted to refine IAs segmentation by adeptly incorporating detailed information. DPF-Net, with its unique resolution-preserving detail branch, ensures minimal loss of detail during feature extraction, while its cross-fusion module effectively promotes the connection of semantic information and finer detail features, enhancing segmentation precision. The network also integrates a detail aggregation module for effective fusion of multi-scale detail features. A view fusion strategy is employed to address spatial disruptions in patch generation, thereby improving feature extraction efficiency. Evaluated on the CADA dataset, DPF-Net achieves a remarkable mean Dice similarity coefficient (DSC) of 0.8967, highlighting its potential in automated IAs diagnosis in clinical settings. Furthermore, DPF-Net’s outstanding performance on the BraTS 2020 MRI dataset for brain tumor segmentation with a mean DSC of 0.8535 further confirms its robustness and generalizability. Full article

Power generation is affected and structural instability may occur when biofouling attaches to the rotor of tidal stream turbines (TSTs). Image signals are used to identify biofouling for biofouling recognition, thus achieving on-demand maintenance, optimizing power generation efficiency, and minimizing maintenance costs. However, image signals are sensitive to background interferences, and underwater targets blend with the water background, making it difficult to extract target features. Changes in water turbidity can affect the effectiveness of image signal biofouling recognition, which can lead to reduced recognition accuracy. In order to solve these problems, a multi-view and multi-type feature fusion (MVTFF) method is proposed to recognize rotor biofouling on TSTs for applications in TST operation and maintenance. (1) Key boundary and semantic information are captured to solve the problem of background feature interference by comparing and fusing the extracted multi-view features. (2) The local geometric description and dependency are obtained by integrating contour features into multi-view features to address the issue of the target mixing with water. The mIoU, mPA, Precision, and Recall of the experimental results show that the method achieves superior recognition performance on TST datasets with different turbidity levels. Full article

This paper presents a novel methodology to generate Digital Elevation Models (DEMs) in flat areas, incorporating river channels from relatively coarse initial data. The technique primarily utilizes filtered dense point clouds derived from SfM-MVS (Structure from Motion-Multi-View Stereo) photogrammetry of available crewed aerial imagery datasets. The methodology operates under the assumption that the aerial survey was carried out during low-flow or drought conditions so that the dry (or almost dry) riverbed is detected, although in an imprecise way. Direct interpolation of the detected elevation points yields unacceptable river channel bottom profiles (often exhibiting unrealistic artifacts) and even distorts the floodplain. In our Fluvial Domain Method, channel bottoms are represented like “highways”, perhaps overlooking their (unknown) detailed morphology but gaining in general topographic consistency. For instance, we observed an 11.7% discrepancy in the river channel long profile (with respect to the measured cross-sections) and a 0.38 m RMSE in the floodplain (with respect to the GNSS-RTK measurements). Unlike conventional methods that utilize active sensors (satellite and airborne LiDAR) or classic topographic surveys—each with precision, cost, or labor limitations—the proposed approach offers a more accessible, cost-effective, and flexible solution that is particularly well suited to cases with scarce base information and financial resources. However, the method’s performance is inherently limited by the quality of input data and the simplification of complex channel morphologies; it is most suitable for cases where high-resolution geomorphological detail is not critical or where direct data acquisition is not feasible. The resulting DEM, incorporating a generalized channel representation, is well suited for flood hazard modeling. A case study of the Ranchería river delta in the Northern Colombian Caribbean demonstrates the methodology. Full article

Image registration is a prerequisite for many multi-source remote sensing image fusion applications. However, due to differences in imaging factors such as sensor type, imaging time, resolution, and viewing angle, multi-source image registration faces challenges of multidimensional coupling such as radiation, scale, and directional differences. To address this issue, this paper proposes a Siamese network based on cross-domain robust feature decoupling as an image registration framework (CRS-Net), aiming to improve the robustness of multi-source image features across domains, scales, and rotations. Firstly, we design Siamese multiscale encoders and introduce a rotation-invariant convolutional layer without additional training parameters, achieving natural invariance to any rotation. Secondly, we propose a modality-independent decoder that utilizes the self-similarity of feature neighborhoods to excavate stable high-order structural information. Thirdly, we introduce cluster-aware contrastive constraints to learn discriminative and stable keypoint pairs. Finally, we design three multi-source remote sensing datasets and conduct sufficient experiments. Numerous experimental results show that our proposed method outperforms other SOTA methods and achieves more accurate registration in complex multi-source remote sensing scenes. Full article

Multi-view subspace clustering enhances clustering performance by optimizing and integrating structural information from multiple views. Recently, anchor-based methods have made notable progress in large-scale clustering scenarios by leveraging anchor points to capture data distribution across different views. Although these methods improve efficiency, a common limitation is that they typically select an equal number of anchor points from each view. Additionally, during the graph fusion stage, most existing frameworks use simple linear weighting to construct the final consensus graph, overlooking the inherent structural relationships between the data. To address these issues, we propose a novel and flexible anchor graph fusion framework which selects an appropriate number of anchor points for each view based on its data space, creating suitable anchor graphs. In the graph fusion stage, we introduce a regularization term which adaptively and flexibly combines anchor graphs of varying sizes. Moreover, our approach incorporates both global and local information between views, enabling a more accurate capture of the cluster structure within the data. Furthermore, our method operates with linear time complexity, making it well suited for large-scale datasets. Extensive experiments on multiple datasets demonstrate the superior performance of our proposed algorithm. Full article

Cooperative visual tracking involving unmanned aerial vehicles (UAVs) in low-altitude environments is a dynamic and rapidly evolving domain. Existing models encounter challenges with targets, such as scale variation, appearance similarity, and frequent occlusions, which hinder the effective use of target information for cross-view identity association. To address these challenges, this study introduces a model for multi-view, multi-target tracking in low-altitude scenes involving UAVs (MVTL-UAV), an effective multi-target tracking model specifically designed for low-altitude scenarios involving UAVs. The proposed method is built upon existing end-to-end detection and tracking frameworks, introducing three innovative modules: loss reinforcement, coupled constraints, and coefficient improvement. Collectively, these advancements enhance the accuracy of cross-view target identity matching. Our method is trained using the DIVOTrack dataset, which comprises data collected from a single UAV and two handheld cameras. Empirical results indicate that our approach achieves a 2.19% improvement in cross-view matching accuracy (CVMA) and a 1.95% improvement in the cross-view ID F1 metric (CVIDF1) when compared to current state-of-the-art methodologies. Importantly, the model’s performance is improved without compromising computational efficiency, thereby enhancing its practical value in resource-constrained environments. As a result, our model demonstrates satisfactory performance in various low-altitude target tracking scenarios involving UAVs, establishing a new benchmark in this research area. Full article

With the rapid development of artificial intelligence, automated artifact recognition technology has gradually replaced the traditional manual quality evaluation method. The existing samples of CT images containing artifacts are small, and the relationships between the images are of great significance. In this study, firstly, a method for CT image artifact recognition was developed by transforming the problem into a node classification framework. Secondly, the characteristics of this complex network and the features of the CT image texture were extracted. Finally, the combination of the complex network’s characteristics and CT image texture features was viewed as node attribution; the relationship between different nodes was analyzed using a graph attention network; and classification was carried out. The integration of multi-order neighbor features in the MNFF-GNN model improves the representation of motion artifact regions, targeting the limitations of traditional methods and convolutional neural networks (CNNs). The model demonstrates potential as a clinical tool, particularly in resource-constrained settings, by effectively identifying artifacts even with limited data, with an accuracy of 90.9%, which is an improvement of 9.73%. This innovative approach leverages graph neural networks (GNNs), which are particularly effective at capturing both local and global relationships within graph-structured data. Full article

Numerous studies leverage pose estimation to extract human keypoint data and then classify sitting postures. However, employing neural networks for direct keypoint classification often yields suboptimal results. Alternatively, modeling keypoints into other data representations before classification introduces redundant information and substantially increases inference time. In addition, most existing methods perform well only under a single fixed viewpoint, limiting their applicability in complex real-world scenarios involving unseen viewpoints. To better address the first limitation, we propose KeypointNet, which employs a decoupled feature extraction strategy consisting of a Keypoint Feature Extraction module and a Multi-Scale Feature Extraction module. In addition, to enhance multi-view recognition capability, we propose the Multi-View Simulation (MVS) algorithm, which augments the viewpoint information by first rotating keypoints and then repositioning the camera. Simultaneously, we propose the multi-view sitting posture (MVSP) dataset, designed to simulate diverse real-world viewpoints. The experimental results demonstrate that KeypointNet outperforms the other state-of-the-art methods on both the proposed MVSP dataset and the other public datasets, while maintaining a lightweight and efficient design. Ablation studies demonstrate the effectiveness of MVS and all KeypointNet modules. Furthermore, additional experiments highlight the superior generalization, small-sample learning capability, and robustness to unseen viewpoints of KeypointNet. Full article

Visual SLAM is widely applied in robotics and remote sensing. The fusion of Gaussian radiance fields and Visual SLAM has demonstrated astonishing efficacy in constructing high-quality dense maps. While existing methods perform well in static scenes, they are prone to the influence of dynamic objects in real-world dynamic environments, thus making robust tracking and mapping challenging. We introduce DyGS-SLAM, a Visual SLAM system that employs dual constraints to achieve high-fidelity static map reconstruction in dynamic environments. We extract ORB features within the scene, and use open-world semantic segmentation models and multi-view geometry to construct dual constraints, forming a zero-shot dynamic information elimination module while recovering backgrounds occluded by dynamic objects. Furthermore, we select high-quality keyframes and use them for loop closure detection and global optimization, constructing a foundational Gaussian map through a set of determined point clouds and poses and integrating repaired frames for rendering new viewpoints and optimizing 3D scenes. Experimental results on the TUM RGB-D, Bonn, and Replica datasets, as well as real scenes, demonstrate that our method has excellent localization accuracy and mapping quality in dynamic scenes. Full article

Biomolecular adsorption has great significance in medical, environmental, and technological processes. Understanding adsorption equilibrium and binding kinetics is essential for advanced process implementation. This requires identifying intrinsic determinants that predict optimal adsorption properties at bio–hybrid interfaces. Solid-binding peptides (SBPs) have targetable intrinsic properties involving peptide–peptide and peptide–solid interactions, which result in high-affinity material-selective binding. Atomic force microscopy investigations confirmed this complex interplay of multi-step peptide assemblies in a cooperative modus. Yet, most studies report adsorption properties of SBPs using non-cooperative or single-step adsorption models. Using non-cooperative kinetic models for predicting cooperative self-assembly behavior creates an oversimplified view of peptide adsorption, restricting implementing SBPs beyond their current use. To address these limitations and provide insight into surface-level events during self-assembly, a novel method, the Frequency Response Cooperativity model, was developed. This model iteratively fits adsorption data through spectral analysis of several time-dependent kinetic parameters. The model, applied to a widely used gold-binding peptide data obtained using a quartz crystal microbalance with dissipation, verified multi-step assembly. Peak deconvolution of spectral plots revealed distinct differences in the size and distribution of the kinetic rates present during adsorption across the concentrations. This approach provides new fundamental insights into the intricate dynamics of self-assembly of biomolecules on surfaces. Full article