Search Results (46)

Aiming at the problems of glare interference, local overexposure and detail loss caused by artificial light sources such as vehicle lamps and street lamps in nighttime road scenes, as well as the challenges of existing glare suppression models with large parameters, high computational complexity and difficulty in deploying on edge devices, this paper proposes a lightweight glare suppression network (LGSNet) based on ghost depthwise separable convolution and Lightweight Parallel Attention. Based on the U-Net architecture, the network introduces ghost depthwise separable convolution blocks (GhostDSC) in the encoder and decoder, which generates ghost features through cheap linear transformations by exploiting feature map redundancy, significantly reducing model parameters and computational costs while maintaining feature representation ability. Meanwhile, a Lightweight Parallel Attention (LPA) module is designed in the decoder stage, which integrates channel attention and pixel attention in parallel, enhancing the network’s attention to glare regions and edge details with extremely low parameter increment to improve detail recovery accuracy. In addition, a joint loss function consisting of background loss, glare loss and reconstruction loss is constructed to collaboratively optimize glare suppression and detail preservation. Experimental results on the public Flare7K++ dataset and the self-built nighttime road glare dataset NRGD show that the proposed method has only 7.45 M parameters, much lower than standard U-Net and Uformer. It achieves competitive results on full-reference metrics such as PSNR, SSIM, LPIPS and no-reference metrics such as NIQE, BRISQUE, PIQE, and can effectively suppress various types of glare interference and restore obscured scene details. It achieves a superior trade-off between model complexity and enhancement performance, significantly reducing the parameter count and computational overhead compared to heavy baselines, thereby offering a highly efficient solution for resource-aware glare suppression tasks. Full article

To address the challenges of dynamic obstacles, limited perception, and multi-UAV coordination constraints in complex urban environments, a hierarchical control framework based on a virtual leader-follower architecture is proposed, covering global planning, local obstacle avoidance, and formation coordination. In the global planning layer, a dynamic adaptive strategy rapidly exploring random tree star (DASRRT*) algorithm is proposed. To address the low sampling efficiency and limited path extension in dense environments that affect traditional RRT*, a hybrid guided sampling strategy, inefficient node optimization strategy, and perception-based adaptive step size strategy are designed. Additionally, a multi-objective cost function is introduced to provide smoother trajectories that better comply with dynamic constraints for trajectory tracking. In the local obstacle-avoidance layer, a distributed controller is constructed based on an improved artificial potential field method, integrating collision avoidance control laws derived from a spring-damper model, dynamic obstacle-avoidance laws that account for obstacle velocities, and formation coordination control laws grounded in consensus theory. In the coordination control layer, a real-time local target selection strategy is established to guide the virtual leader to precisely track the global path, and a dual-mode switching mechanism based on environmental complexity is constructed to dynamically adjust the priority between formation maintenance and autonomous obstacle-avoidance tasks. Comparative experimental results show that the proposed DASRRT* algorithm reduces path planning time by an average of 34.78% and shortens path length by 1.15%. Simulation results for formation flight demonstrate that the proposed hierarchical control framework can adaptively adjust control modes in response to changes in environmental complexity, exhibiting strong adaptability to complex environments and a good ability to generalize to various scenes. Full article

To address the challenge of efficiently and cost-effectively generating images of intangible cultural heritage (ICH) furniture that can adapt to diverse modern spatial contexts for visual communication, this paper proposes and constructs an Generative Artificial Intelligence (AIGC) virtual studio system based on ComfyUI. The system is designed for ICH furniture designers, cultural communicators, and digital preservation practitioners, aiming to overcome the bottlenecks of scene switching encountered in traditional photography and 3D modeling. First, furniture images and user scene descriptions are collected, and a dual lexicon consisting of AI prompts and user prompts is constructed. The analytic hierarchy process (AHP) is then applied to weight and filter prompt combinations, forming a quantifiable and integrated prompt system. Second, a visual workflow incorporating ControlNet and IPAdapter nodes is built in ComfyUI to enable the transfer of ICH furniture images to various preset spatial scenes. Finally, a Likert-scale comparison is conducted between the experimental group (using AHP-weighted prompts) and the control group (using unweighted prompts). The results show that the experimental group achieves significant improvements in image realism, style consistency, and cultural communication effectiveness. The images generated by this system can be directly used for digital display, e-commerce product pages, design proposals, and cultural archives of ICH furniture. The method is applicable to the context-aware AIGC generation of traditional furniture and home products, provided that a certain amount of image data and a ComfyUI environment are available. This study provides a reusable technical pathway for the modern visual presentation of ICH furniture and offers methodological support and empirical evidence for the integration of AIGC into environmental design. Full article

Traditional lifting operations rely heavily on manual experience, which often leads to high operational risks and limited efficiency. To address these issues, this paper proposes an intelligent lifting system with digital operators, conductors, and supervisors, to improve safety and efficiency through multi-agent collaboration. The system uses a BEVFusion-based perception module to support target detection and collision warning during lifting operations. To handle unforeseen situations, a dynamic local lifting path planning method is designed to ensure safe lifting operations. Rather than proposing a fundamentally new algorithm, this study focuses on integrating perception and planning within a unified intelligent lifting system. The experimental results show that the system can support safe lifting operations under the tested conditions and demonstrate its feasibility in practical scenarios. Full article

Building reliable vehicle detection models for intelligent transportation systems calls for large, well-annotated datasets—yet gathering and labelling real traffic data remains both costly and labour-intensive. This paper introduces Traffic Synth, an automated pipeline that generates synthetic training datasets by altering real traffic camera images rather than constructing entirely artificial scenes. The system begins by detecting vehicles through instance segmentation and removing them from the frame. It then places new vehicles directly into the cleared regions using diffusion-based inpainting, all while retaining the original road layout, lighting, and camera perspective. Doing so preserves the realistic scene context while broadening the visual variety of vehicles in the dataset. To ensure that the resulting traffic looks physically plausible, we incorporate a lane-aware prompting mechanism that matches each vehicle’s orientation to the direction of travel as seen from the camera. The system further draws on a weighted vehicle brand database that mirrors the makes and colours commonly found on European roads to better match actual deployment conditions. Class-specific mask processing—involving anisotropic scaling and relative dilation—rounds out the pipeline by improving generation quality across different vehicle size categories. The final output is a set of images with automatically generated annotations in a standard object detection format. Full article

The utilization of Artificial Intelligence-Generated Content (AIGC) has attracted widespread attention in video content creation. To generate high-quality videos, this paper presents a controllable multimodal fusion architecture for AIGC-driven short-video production. This architecture employs hierarchical constraint mechanisms and a multimodal attention fusion mechanism to enhance video content coherence and user controllability. Specifically, a scene coherence scheme is first designed to construct graph-based global and transition-level constraints by integrating text descriptions, reference images, and audio features. By leveraging the extracted style vector data, preliminary video clips are then generated through a combination of the cross-modal fusion unit and the spatio-temporal consistency unit. Finally, a fine-grained adjustment mechanism is implemented to ensure logical consistency and stylistic uniformity in the AIGC-generated videos. Experimental results indicate that the proposed architecture improves generation quality, controllability, and cross-segment coherence under the adopted evaluation settings. Full article

The large-scale integration of renewable energy sources and power-electronic-interfaced devices has significantly weakened transient support capability and disturbance tolerance, posing new challenges to the secure and stable operation of modern power systems. Conventional stability analysis methods suffer from high computational burden, long execution time, and limited adaptability to diverse operating scenarios. The rapid development of artificial intelligence (AI) provides effective technical support for fast and accurate assessment of power-system security and stability. This paper presents a comprehensive review of AI-based methods and the interpretability for transient stability assessment (TSA) in modern power systems. First, an intelligent TSA framework is introduced, consisting of three key stages: sample construction and enhancement, intelligent algorithms and learning mechanisms, and model training and interpretability. Subsequently, existing methods for data augmentation, intelligent algorithms, learning mechanisms, and interpretability analysis are systematically reviewed, and the corresponding application scene, technical superiority and limitations are discussed. Finally, from a knowledge–data fusion perspective, four representative integration paradigms combining mechanism-based models and data-driven approaches are summarized, and the application prospects in power-system stability analysis are discussed. Full article

As a well-known World Cultural Heritage Site, the Historic Centre of Macao’s historical buildings possess a wealth of decorative patterns. These patterns contain cultural esthetics, geographical environment, cultural traditions, and other elements from specific historical periods, deeply reflecting the evolution of religious rituals and political and economic systems throughout history. Through long-term research, this article constructs a dataset of 11,807 images of local decorative patterns of historical buildings in Macau, and proposes a fine-grained image classification method using the ConvNeXt-L model. The ConvNeXt-L model is an efficient convolutional neural network that has demonstrated excellent performance in image classification tasks in fields such as medicine and architecture. Its outstanding advantages lie in limited training samples, diverse image features, and complex scenes. The most typical advantage of this model is its structural integration of key design concepts from a Transformer, which significantly enhances the feature extraction and generalization ability of samples. In response to the objective reality that the decorative patterns of historical buildings in Macau have rich levels of detail and a limited number of functional building categories, ConvNeXt-L maximizes its ability to recognize and classify patterns while ensuring computational efficiency. This provides a more ideal technical path for the classification of small-sample complex images. This article constructs a deep learning system based on the PyTorch 1.11 framework and compares ResNet50, EfficientNet-B7, ViT-B/16, Swin-B, RegNet-Y-16GF, and ConvNeXt series models. The results indicate a positive correlation between model performance and structural complexity, with ConvNeXt-L being the most ideal in terms of accuracy in decorative pattern classification, due to its fusion of convolution and attention mechanisms. This study not only provides a multidimensional exploration for the protection and revitalization of Macao’s historical and cultural heritage and enriches theoretical support and practical foundations but also provides new research paths and methodological support for artificial intelligence technology to assist in the planning and decision-making of historical urban areas. Full article

As intelligent vessel technology moves from the proof-of-concept stage to engineering applications, the performance testing and evaluation of autonomous collision avoidance algorithms have become core issues for safeguarding maritime traffic safety. The International Maritime Organization (IMO)’s Maritime Safety Committee (MSC), at its 109th session, agreed to a revised road map for the development of the Maritime Autonomous Surface Ships (MASS) Code; the field has experienced the development stages of single-vessel collision avoidance validation based on COLREGs, multimodal algorithm collaborative testing, and the current construction of a progressive validation system for the integration of a mix of virtual reality and actual reality. In recent years, relevant studies have achieved research achievements, especially in the compatibility of COLREGs and in accurate collision avoidance in complex situations, and other algorithm tests and evaluations have made great breakthroughs. However, a systematic literature review is still lacking. In this paper, we systematically review the research progress of autonomous collision avoidance performance testing and the evaluation of intelligent vessels; summarize the advantages and disadvantages of virtual testing, model testing, and full-scale vessel testing; and analyze the applicability and limitations of mainstream algorithms such as the velocity obstacle algorithm, the artificial potential field algorithm, and reinforcement learning. It focuses on the key technologies such as diverse scene generation, local scene slicing, and the construction of an evaluation index system. Finally, this paper summarizes the challenges faced by autonomous collision avoidance performance testing and the assessment of intelligent vessels and proposes potential technical solutions and future development directions in terms of virtual–real fusion testing, dynamic evaluation index optimization, and multimodal algorithm co-validation, aiming to provide a reference for the further development of this field. Full article

Augmented reality (AR) has become a research focus in computer vision and graphics, with growing applications driven by advances in artificial intelligence and the emergence of the metaverse. Panoramic cameras offer new opportunities for AR due to their wide field of view but also pose significant challenges for camera pose estimation because of severe distortion and complex scene textures. To address these issues, this paper proposes a lightweight, unsupervised deep learning model for panoramic camera pose estimation. The model consists of a depth estimation sub-network and a pose estimation sub-network, both optimized for efficiency using network compression, multi-scale rectangular convolutions, and dilated convolutions. A learnable occlusion mask is incorporated into the pose network to mitigate errors caused by complex relative motion. Furthermore, a panoramic view reconstruction model is constructed to obtain effective supervisory signals from the predicted depth, pose information, and corresponding panoramic images and is trained using a designed spherical photometric consistency loss. The experimental results demonstrate that the proposed method achieves competitive accuracy while maintaining high computational efficiency, making it well-suited for real-time AR applications with panoramic input. Full article

Spatial scenes, as fundamental units of geospatial cognition, encompass rich objects and spatial relationships, and their generation techniques hold significant application value in disaster simulation and emergency drills, delayed spatial reconstruction and analysis, and other fields. However, existing studies still face limitations in modeling complex spatial relationships during scene generation, leading to insufficient semantic consistency and geographical accuracy. The advancement of Geospatial Artificial Intelligence (GeoAI) offers a new technical pathway for the intelligent modeling of spatial scenes. Against this backdrop, we propose SceneDiffusion, a scene generation model embedded with spatial constraints, and construct a geospatial scene dataset incorporating spatial relationship descriptions and geographic semantics, aiming to enhance the understanding and modeling capabilities of GeoAI models for spatial information. Specifically, SceneDiffusion employs a spatial scene representation framework to uniformly characterize objects and their topological, directional, and distance relationships, enhances the interactive modeling of objects and relationships through a Spatial relationship Attention-aware Graph (SAG) module, and finally generates high-quality scene images conforming to geographic semantics using a Layout information-guided Conditional Diffusion (LCD) module. Both qualitative and quantitative experiments demonstrate the superiority of SceneDiffusion, achieving a 56.6% reduction in FID and a 35.3% improvement in SSIM compared to baseline methods. Ablation studies confirm the importance of multi-relational modeling with attention mechanisms. By generating scenes that satisfy spatial distribution constraints, this work provides technical support for applications such as emergency scene simulation and virtual scene construction, while also offering insights for theoretical research and methodological innovation in GeoAI. Full article

(1) Background: With the deep integration of e-commerce and video technology, live-streaming marketing has emerged globally and maintained rapid growth. However, most of the current research on live-streaming e-commerce marketing focuses on merchants’ sales strategies and consumers’ purchase intentions, and there is relatively little research related to the risks of live-streaming e-commerce marketing. Nevertheless, with the development of live-streaming e-commerce marketing and its integration with technologies such as artificial intelligence and virtual reality (VR), live-streaming e-commerce marketing still faces challenges such as unclear subject responsibility, difficulty in verifying the authenticity of marketing information, and uneven product quality. It also harbors problems such as the ethical misbehavior of AI anchors and the excessive beautification of products by VR technology. (2) Methods: This study systematically analyzes the scenarios of live-streaming marketing to elucidate the mechanisms of risk formation. Utilizing fault tree analysis (FTA) and risk checklist methods, risks are identified based on the three core elements of live-streaming marketing: “people–products–scenes”. Subsequently, the Delphi method is employed to refine the initial risk indicator system, resulting in the construction of a comprehensive risk indicator system comprising three first-level indicators, six second-level indicators, and 16 third-level indicators. A hesitant fuzzy multi-attribute group decision-making method (HFMGDM) is then applied to calculate the weights of the risk indicators and comprehensively assess the live-streaming marketing risks in live broadcast rooms of three prominent celebrity anchors in China. Furthermore, a detailed analysis is conducted on the risks associated with the six secondary indicators. Based on the risk evaluation results, targeted recommendations are proposed. This study aims to enhance consumers’ awareness of risk prevention when conducting live-streaming transactions and pay attention to related risks, thereby safeguarding consumer rights and fostering the healthy and sustainable development of the live-streaming marketing industry. (3) Conclusions: The results show that the top five risk indicators in terms of weight ranking are: Ethical Risk of the AI Anchor (A4), VR Technology Promotion Risk (F3), Anchor Reputation (A1), Product Quality (D1), and Logistics Distribution Service Quality (D2). The comprehensive live-streaming marketing risk of each live broadcast room is Y > L > D. Based on the analysis results, targeted recommendations are provided for anchors, MCN institutions, merchants, supply chains, and live-streaming platforms to improve consumer satisfaction and promote sustainable development of the live-streaming marketing industry. Full article

Recognizing low-resolution license plates from real-world scenes remains a challenging task. While deep learning-based super-resolution methods have been widely applied, most existing datasets rely on artificially degraded images, and common quality metrics poorly correlate with OCR accuracy. We construct a new paired low- and high-resolution license plate dataset from dashcam videos and propose a specialized super-resolution framework for license plate recognition. Only low-resolution images with OCR accuracy ≥5 are used to ensure sufficient feature information for effective perceptual learning. We analyze existing loss functions and introduce two novel perceptual losses—one CNN-based and one Transformer-based. Our approach improves recognition performance, achieving an average OCR accuracy of 85.14%. Full article

This study aims to propose a practical and realistic synthetic data generation method for object recognition in hazardous and data-scarce environments, such as construction sites. Artificial intelligence (AI) applications in such dynamic domains require domain-specific datasets, yet collecting real-world data can be challenging due to safety concerns, logistical constraints, and high labor costs. To address these limitations, we introduce object range expansion synthesis (ORES), a lightweight and non-generative method for generating synthetic image data by inserting real object masks into varied background scenes using open datasets. ORES synthesizes new scenes, while preserving scale and ground alignment, enabling controllable and realistic data augmentation. A dataset of 30,000 synthetic images was created using the proposed method and used to train an object recognition model. When tested on real-world construction site images, the model achieved a mean average precision at IoU 0.50 (mAP50) of 98.74% and a recall of 54.55%. While recall indicates room for improvement, the high precision highlights the practical value of synthetic data in enhancing model performance without requiring extensive field data collection. This research contributes a scalable approach to data generation in safety-critical and data-deficient environments, reducing dependence on direct data acquisition, while maintaining model efficacy. It provides a foundation for accelerating the deployment of AI technologies in high-risk industries by overcoming data bottlenecks and supporting real-world applications through practical synthetic augmentation. Full article

Current energy-saving lighting control algorithms often face the dilemma of local optimality, which limits the energy-saving potential and comfort improvement of indoor lighting systems. The control parameters of the lighting system are optimized using a genetic simulated annealing algorithm to achieve the global optimal solution and enhance energy-saving efficacy in indoor lighting. The local search ability of the algorithm is enhanced by simulated annealing processing of excellent individuals after genetic operation. The genetic probability is adaptively adjusted according to the number of iterations and the fitness of the population, so that the algorithm enriches the population diversity in the early stage and avoids the “premature” convergence of the algorithm. A lamp illuminance model based on an artificial neural network and an indoor natural illuminance model based on a workbench are proposed to evaluate the lighting comfort, which provides a basis for constructing the fitness function of the optimization algorithm. Through the simulation experiment, the genetic simulated annealing algorithm is applied to the lighting scene introduced in this paper and compared with the traditional particle swarm optimization algorithm and genetic algorithm, the lighting energy saving performance is significantly improved. Full article