Search Results (648)

The extraction of architectural structural line features can simplify the 3D spatial representation of built environments, reduce the storage and processing burden of large-scale point clouds, and provide essential geometric primitives for downstream modeling tasks. However, existing 3D line extraction methods suffer from incomplete and fragmented contours, with missing or misaligned intersections. To overcome these limitations, this study proposes a patch-level framework for 3D line extraction and structural optimization from building point clouds. The proposed method first partitions point clouds into planar patches and establishes local image planes for each patch, enabling a structured 2D representation of unstructured 3D data. Then, graph-cut segmentation is proposed to extract compact boundary contours, which are vectorized into closed lines and back-projected into 3D space to form the initial line segments. To improve geometric consistency, regularized geometric constraints, including adjacency, collinearity, and orthogonality constraints, are further designed to merge homogeneous segments, refine topology, and strengthen structural outlines. Finally, we evaluated the approach on three indoor building environments and four outdoor scenes, and experimental results show that it reduces noise and redundancy while significantly improving the completeness, closure, and alignment of 3D line features in various complex architectural structures. Full article

Wetland ecosystems, particularly marsh wetlands, are vital for carbon cycling, yet the accurate estimation of the fraction of absorbed photosynthetically active radiation (FPAR) in these environments is challenging due to their complex structure and limited field data. This study employs the large-scale remote sensing data and image simulation framework (LESS), a 3D radiative transfer model, to simulate FPAR and vegetation indices (VIs) under controlled conditions, including variations in vegetation types, soil types, chlorophyll content, solar and observation angles, and plant density. By simulating 8064 wetland scenes, we overcame the limitations of field measurements and conducted comprehensive quantitative analyses of the relationship between the FPAR and VI (which is essential for remote sensing-based FPAR estimation). Nine VIs (NDVI, GNDVI, SAVI, RVI, EVI, MTCI, DVI, kNDVI, RDVI) effectively characterized FPAR, with the following saturation thresholds quantified: inflection points (FPAR.inf, where saturation begins) ranged from 0.423 to 0.762 (mean = 0.594) and critical saturation points (FPAR.sat, where saturation is complete) from 0.654 to 0.889 (mean = 0.817). The Enhanced Vegetation Index (EVI) and Soil-Adjusted Vegetation Index (SAVI) showed the highest robustness against saturation and environmental variability for FPAR estimation in reed (Phragmites australis) marshes. These findings provide essential support for FPAR estimation in marsh wetlands and contribute to quantitative studies of wetland carbon cycling. Full article

Single-image based camera auto-calibration holds significant value for improving perception efficiency in traffic surveillance systems. However, existing approaches face dual challenges: scarcity of real-world datasets and poor adaptability to multi-view scenarios. This paper presents a systematic solution framework. First, we constructed a large-scale synthetic dataset containing 36 highway scenarios using the CARLA 0.9.15 simulation engine, generating approximately 336,000 virtual frames with precise calibration parameters. The dataset achieves statistical consistency with real-world scenes by incorporating diverse view distributions, complex weather conditions, and varied road geometries. Second, we developed DeepCalib, a deep calibration network that explicitly models perspective projection features through the triplet attention mechanism. This network simultaneously achieves road direction vanishing point localization and camera pose estimation using only a single image. Finally, we adopted a progressive learning paradigm: robust pre-training on synthetic data establishes universal feature representations in the first stage, followed by fine-tuning on real-world datasets in the second stage to enhance practical adaptability. Experimental results indicate that DeepCalib attains an average calibration precision of 89.6%. Compared to conventional multi-stage algorithms, our method achieves a single-frame processing speed of 10 frames per second, showing robust adaptability to dynamic calibration tasks across diverse surveillance views. Full article

With the rapid growth in satellite types and numbers in space information networks, accurate and fast inter-satellite link prediction has become a core requirement for topology modeling and capability evaluation. However, the current space information networks are characterized by large scales and the coexistence of multi-orbit satellites, posing dual challenges to inter-satellite link prediction. Link state prediction demands higher accuracy with limited computing power, while diverse satellite communication antenna loads require stronger generalization to adapt to different scenarios. To address these issues, this paper proposes a fully connected neural network model based on Bayesian optimization. By introducing a weighted loss function, the model effectively handles data imbalance in the link states. Combined with Bayesian optimization, the neural network hyperparameters and weighted loss function coefficients are fine-tuned, significantly improving the prediction accuracy and scene adaptability. Experimental results show that the BO-FCNN model exhibited an excellent performance on the test dataset, with an F1 score of 0.91 and an average accuracy of 93%. In addition, validation with actual satellite data from CelesTrak confirms the model’s real-world performance and its potential as a reliable solution for inter-satellite link prediction. Full article

Object detection is used to automatically identify and locate specific objects within images or videos for applications like autonomous driving, security surveillance, and medical imaging. Protecting object detection models against adversarial attacks, particularly malicious patches, is crucial to ensure reliable and safe performance in safety-critical applications, where misdetections can lead to severe consequences. Existing defenses against patch attacks are primarily designed for stationary scenes and struggle against adversarial image patches that vary in scale, position, and orientation in dynamic environments.In this paper, we introduce SAR, a patch-agnostic defense scheme based on image preprocessing that does not require additional model training. By integration of the patch-agnostic detection frontend with an additional broken pixel restoration backend, Segment and Recover (SAR) is developed for the large-mask-covered object-hiding attack. Our approach breaks the limitation of the patch scale, shape, and location, accurately localizes the adversarial patch on the frontend, and restores the broken pixel on the backend. Our evaluations of the clean performance demonstrate that SAR is compatible with a variety of pretrained object detectors. Moreover, SAR exhibits notable resilience improvements over state-of-the-art methods evaluated in this paper. Our comprehensive evaluation studies involve diverse patch types, such as localized-noise, printable, visible, and adaptive adversarial patches. Full article

With the rapid growth of video platforms such as YouTube, Bilibili, and Dailymotion, an enormous amount of video content is being shared worldwide. In this environment, content providers are increasingly adopting methods that restructure videos around highlight scenes and distribute them in short-form formats to encourage more efficient content consumption by viewers. As a result of this trend, the importance of highlight extraction technologies capable of automatically identifying key scenes from large-scale video datasets has been steadily increasing. To address this need, this study proposes SPOT (Spatial Perceptual Optimized TimeSformer), a highlight extraction model. The proposed model enhances spatial perceptual capability by integrating a CNN encoder into the internal structure of the existing Transformer-based TimeSformer, enabling simultaneous learning of both the local and global features of a video. The experiments were conducted using Google’s YT-8M video dataset along with the MR.Hisum dataset, which provides organized highlight information. The SPOT model adopts a regression-based highlight prediction framework. Experimental results on video datasets of varying complexity showed that, in the high-complexity group, the SPOT model achieved a reduction in mean squared error (MSE) of approximately 0.01 (from 0.090 to 0.080) compared to the original TimeSformer. Furthermore, the model outperformed the baseline across all complexity groups in terms of mAP, Coverage, and F1-Score metrics. These results suggest that the proposed model holds strong potential for diverse multimodal applications such as video summarization, content recommendation, and automated video editing. Moreover, it is expected to serve as a foundational technology for advancing video-based artificial intelligence systems in the future. Full article

Maritime unmanned aerial vehicle (UAV) ship detection faces challenges including variations in ship pose and appearance under multiple viewpoints, occlusion and confusion in dense scenes, complex backgrounds, and the scarcity of ship datasets from UAV tilted perspectives. To overcome these obstacles, this study introduces a high-quality dataset named Marship-OBB9, comprising 11,268 drone-captured images and 18,632 instances spanning nine typical ship categories. The dataset systematically reflects the characteristics of maritime scenes under diverse scales, viewpoints, and environmental conditions. Based upon this dataset, we propose a novel detection network named YOLO11-UAVShip. First, an oriented bounding box detection mechanism is incorporated to precisely fit ship contours and reduce background interference. Second, a newly designed CK_DCNv4 module, integrating deformable convolution v4 (DCNv4) and a C3k2 backbone structure, is developed to enhance geometric feature extraction under aerial oblique view. Additionally, for ships with large aspect ratios, SGKLD effectively addresses the localization challenges in dense environments, achieving robust position regression. Comprehensive experimental evaluation demonstrates that the proposed method yields a 2.1% improvement in mAP@0.5 and a 2.3% increase in recall relative to baseline models on the Marship-OBB9 dataset. While maintaining real-time inference speed, our approach greatly enhances detection accuracy and robustness. This work provides a practical and deployable solution for intelligent ship detection in UAV imagery. Full article

As the demand for air transportation continues to grow, airspace congestion, flight delays, operational costs, and safety have become important and challenging issues. There are various optimization problems in air transportation, which involve large-scale data, complex operational scenes, multiple optimization objectives, and dynamic environments. In addition, besides conventional commercial aviation, the development of urban air mobility brings new features to air transportation. Evolutionary computation (EC) algorithms have emerged as a promising approach for solving optimization problems in air transportation. This article introduces a hierarchical taxonomy to systematically review the application of EC algorithms in air transportation. At the first level, related studies are categorized into commercial aviation and urban air mobility based on their application domains. At the second level, studies are further classified according to different operational scenes. A comprehensive review of relevant studies in the literature is presented according to the above taxonomy. In addition, future research directions and open issues are discussed to support and inspire further advancements in this field. Full article

High-resolution remote sensing images suffer from large intra-class variance, high inter-class similarity, and significant scale variations, leading to incomplete segmentation and imprecise boundaries. To address these challenges, Transformer-based methods, despite their strong global modeling capability, often suffer from feature confusion, weak detail representation, and high computational cost. Moreover, existing multi-scale fusion mechanisms are prone to semantic misalignment across levels, hindering effective information integration and reducing boundary clarity. To address these issues, a Category-Guided Transformer (CIGFormer) is proposed. Specifically, the Category-Information-Guided Transformer Module (CIGTM) integrates global and local branches: the global branch combines window-based self-attention (WSAM) and window adaptive pooling self-attention (WAPSAM), using class predictions to enhance global context modeling and reduce intra-class and inter-class confusion; the local branch extracts multi-scale structural features to refine semantic representation and boundaries. In addition, an Adaptive Wavelet Fusion Module (AWFM) is designed, which leverages wavelet decomposition and channel-spatial joint attention for dynamic multi-scale fusion while preserving structural details. Extensive experiments on the ISPRS Vaihingen and Potsdam datasets demonstrate that CIGFormer, with only 21.50 M parameters, achieves outstanding performance in small object recognition, boundary refinement, and complex scene parsing, showing strong potential for practical applications. Full article

Human perception of urban streetscapes plays a crucial role in shaping human-centered urban planning and policymaking. Traditional studies on safety perception often rely on labor-intensive field surveys with limited spatial coverage, hindering large-scale assessments. To address this gap, this study constructs a street safety perception dataset for Wuhan, classifying street scenes into three perception levels. A convolutional neural network model based on transfer learning is developed, achieving a classification accuracy of 78.3%. By integrating image-based prediction with spatial clustering and correlation analysis, this study demonstrates that safety perception displays a distinctly clustered and uneven spatial distribution, primarily concentrated along major arterial roads and rail transit corridors by high safety levels. Correlation analysis indicates that higher safety perception is moderately associated with greater road grade, increased road width, and lower functional level while showing a weak negative correlation with housing prices. By presenting a framework that integrates transfer learning and geospatial analysis to connect urban street imagery with human perception, this study advances the assessment of spatialized safety perception and offers practical insights for urban planners and policymakers striving to create safer, more inclusive, and sustainable urban environments. Full article

Durian is a major tropical crop in Southeast Asia, but its yield and quality are severely impacted by a range of pests and diseases. Manual inspection remains the dominant detection method but suffers from high labor intensity, low accuracy, and difficulty in scaling. To address these challenges, this paper proposes EN-YOLO, a novel enhanced YOLO-based deep learning model that integrates the EfficientNet backbone and multimodal attention mechanisms for precise detection of durian pests and diseases. The model removes redundant feature layers and introduces a large-span residual edge to preserve key spatial information. Furthermore, a multimodal input strategy—incorporating RGB, near-infrared and thermal imaging—is used to enhance robustness under variable lighting and occlusion. Experimental results on real orchard datasets demonstrate that EN-YOLO outperforms YOLOv8 (You Only Look Once version 8), YOLOv5-EB (You Only Look Once version 5—Efficient Backbone), and Fieldsentinel-YOLO in detection accuracy, generalization, and small-object recognition. It achieves a 95.3% counting accuracy and shows superior performance in ablation and cross-scene tests. The proposed system also supports real-time drone deployment and integrates an expert knowledge base for intelligent decision support. This work provides an efficient, interpretable, and scalable solution for automated pest and disease management in smart agriculture. Full article

Scene text understanding, serving as a cornerstone technology for autonomous navigation, document digitization, and accessibility tools, has witnessed a paradigm shift from traditional methods relying on handcrafted features and multi-stage processing pipelines to contemporary deep learning frameworks capable of learning hierarchical representations directly from raw image inputs. This survey distinctly categorizes modern scene text recognition (STR) methodologies into three principal paradigms: two-stage detection frameworks that employ region proposal networks for precise text localization, single-stage detectors designed to optimize computational efficiency, and specialized architectures tailored to handle arbitrarily shaped text through geometric-aware modeling techniques. Concurrently, an in-depth analysis of text recognition paradigms elucidates the evolutionary trajectory from connectionist temporal classification (CTC) and sequence-to-sequence models to transformer-based architectures, which excel in contextual modeling and demonstrate superior performance. In contrast to prior surveys, this work uniquely emphasizes several key differences and contributions. Firstly, it provides a comprehensive and systematic taxonomy of STR methods, explicitly highlighting the trade-offs between detection accuracy, computational efficiency, and geometric adaptability across different paradigms. Secondly, it delves into the nuances of text recognition, illustrating how transformer-based models have revolutionized the field by capturing long-range dependencies and contextual information, thereby addressing challenges in recognizing complex text layouts and multilingual scripts. Furthermore, the survey pioneers the exploration of critical research frontiers, such as multilingual text adaptation, enhancing model robustness against environmental variations (e.g., lighting conditions, occlusions), and devising data-efficient learning strategies to mitigate the dependency on large-scale annotated datasets. By synthesizing insights from technical advancements across 28 benchmark datasets and standardized evaluation protocols, this study offers researchers a holistic perspective on the current state-of-the-art, persistent challenges, and promising avenues for future research, with the ultimate goal of achieving human-level scene text comprehension. Full article

Maritime navigation safety relies on high-precision perception systems. However, hazy weather often significantly compromises system performance, particularly by reducing image quality and increasing navigational risks. Although image dehazing techniques provide an effective solution, the lack of dedicated overwater dehazing datasets limits the generalization of dehazing algorithms. To overcome this problem, we present a large-scale overwater paired image dehazing dataset: Overwater-Haze. The dataset contains 21,000 synthetic overwater hazy images generated based on the atmospheric scattering model (ASM), categorized into Mist, Moderate, and Dense subsets based on varying haze concentrations, and 500 real overwater hazy images, which form the Real-Test portion of the test set. In order to meet the requirements for background interference mitigation, image diversity, and high quality, we performed extensive data augmentation and developed a comprehensive dataset creation pipeline. Our evaluation of five dehazing algorithms shows that models trained on Overwater-Haze achieve 9.96% and 10.47% lower Natural Image Quality Evaluator (NIQE) and Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) scores than pre-trained models on real overwater scenes, demonstrating the value of Overwater-Haze in assessing algorithm performance in overwater environments. Full article

In recent years, indoor user identification via Wi-Fi signals has emerged as a vibrant research area in smart homes and the Internet of Things, thanks to its privacy preservation, immunity to lighting conditions, and ease of large-scale deployment. Conventional deep-learning classifiers, however, suffer from poor generalization and demand extensive pre-collected data for every new scenario. To overcome these limitations, we introduce SimID, a few-shot Wi-Fi user recognition framework based on identity-similarity learning rather than conventional classification. SimID embeds user-specific signal features into a high-dimensional space, encouraging samples from the same individual to exhibit greater pairwise similarity. Once trained, new users can be recognized simply by comparing their Wi-Fi signal “query” against a small set of stored templates—potentially as few as a single sample—without any additional retraining. This design not only supports few-shot identification of unseen users but also adapts seamlessly to novel movement patterns in unfamiliar environments. On the large-scale XRF55 dataset, SimID achieves average accuracies of 97.53%, 93.37%, 92.38%, and 92.10% in cross-action, cross-person, cross-action-and-person, and cross-person-and-scene few-shot scenarios, respectively. These results demonstrate SimID’s promise for robust, data-efficient indoor identity recognition in smart homes, healthcare, security, and beyond. Full article

As an important input parameter of the ecological network, the accuracy and detail with which forest cover is extracted directly constrain the accuracy of forest ecological network construction. The development of medium- and high-resolution remote sensing technology has provided an opportunity to obtain accurate and high-resolution forest coverage data. As forests have diverse contours and complex scenes on remote sensing images, a model of them will be disturbed by the natural distribution characteristics of complex forests, which in turn will affect the extraction accuracy. In this study, we first constructed a rather large, complex, diverse, and scene-rich forest extraction dataset based on Sentinel-2 multispectral images, comprising 20,962 labeled images with a spatial resolution of 10 m, in a manually and accurately labeled manner. At the same time, this paper proposes the Dynamic Large Kernel Segformer and conducts forest extraction experiments in Liaoning Province, China. We then used forest coverage as an input parameter and classified the forest landscape patterns in the study area using a landscape spatial pattern characterization method, based on which a forest ecological network was constructed. The results show that the Dynamic Large Kernel Segformer obtains 80.58% IoU, 89.29% precision, 88.63% recall, and a 88.96% F1 Score in extraction accuracy, which is 4.02% higher than that of the Segformer network, and achieves large-scale forest extraction in the study area. The forest area in Liaoning Province increased during the 5-year period from 2019 to 2023. With respect to the overall spatial pattern change, the Core area of Liaoning Province saw an increase in 2019–2023, and the overall quality of the forest landscape improved. Finally, we constructed the forest ecological network for Liaoning Province in 2023, which consists of ecological sources, ecological nodes, and ecological corridors based on circuit theory. This method can be used to extract large areas of forest based on remote sensing images, which is helpful for constructing forest ecological networks and achieving coordinated regional, ecological, and economic development. Full article