Search Results (1,607)

Holographic synthetic aperture radar (HoloSAR) enables 360° three-dimensional reconstruction by incoherently stacking tomographic subaperture images. However, after conventional subaperture-wise TomoSAR reconstruction and non-coherent integration, the resulting 3D imagery suffers from severe dynamic range imbalance due to angle-dependent scattering responses: wide-angle strong scatterers are repeatedly amplified, whereas narrow-angle weak structures are buried below the noise floor. To address this post-processing challenge, we propose a joint statistical filtering framework operating on the reconstructed subaperture-domain 3D images that fuses the coefficient of variation, inter-subaperture correlation, and spectral entropy with adaptive discriminative-power weighting; target screening is then performed via a Gaussian mixture model-based Bayesian optimal threshold. For pixels classified as weak targets, a percentile-matching energy-balancing transformation is applied to adaptively rescale their energy to the main-target reference level while preserving relative amplitude relationships. Experiments on real-world Ku-band UAV circular SAR data demonstrate that the proposed method effectively compresses the dynamic range, suppresses background noise, and recovers weak narrow-angle structures that are lost in traditional non-coherent superposition, yielding more complete and interpretable HoloSAR 3D reconstructions. Quantitative evaluation on Ku-band UAV circular SAR data demonstrates that the proposed method improves the Target-to-Background Ratio by 0.7 dB (to 11.2 dB), achieves a Background Suppression Ratio of −5.2 dB, increases the Structural Completeness Index by 156% (to 1428.1), and compresses the original dynamic range imbalance, which exceeds 50 dB, while preserving scene physical realism (ENL ≈ 7.4 × 10⁻³). Full article

As autonomous-driving scenarios become increasingly complex, object detection in road environments remains challenging, especially for small-scale, visually ambiguous, and partially occluded targets. These difficulties are closely related to the loss of fine-grained spatial information caused by repeated downsampling and the limited consistency of multi-scale feature fusion. To address these issues, this paper proposes MFP-YOLOv11 (Multi-dimensional Focused P2 YOLOv11), a YOLOv11-based detector with enhanced multi-scale feature fusion for complex road-scene object detection. The proposed method improves the YOLOv11 architecture from the perspectives of high-resolution feature preservation, deep contextual representation, and multi-scale feature fusion consistency. Specifically, a Multi-Scale Dynamic Alignment Feature Fusion module (MDAF) is designed as the main fusion component to enhance multi-scale feature representation by modelling channel-, spatial-, and scale-level relationships among features at different resolutions. In addition, C3Ghost is selectively employed in shallow high-resolution stages to partially offset the additional computational cost introduced by the enhanced architecture, AIFI-RepBN is introduced to strengthen deep contextual representation, and Detect-P2 is added to provide high-resolution prediction compensation for small-scale object detection. Experimental results on the SODA10M dataset show that MFP-YOLOv11 achieves an mAP@0.5 of 0.697 and an mAP@0.5:0.95 of 0.483, corresponding to absolute gains of 7.0 and 5.7 percentage points over the YOLOv11 baseline, respectively. Comparative experiments, ablation studies, component-wise analysis, and qualitative visualizations show the contribution of the proposed modifications to detection performance in representative complex road scenes. Cross-dataset testing on the KITTI dataset further evaluates the performance of the proposed method under heterogeneous road-scene distributions. Overall, MFP-YOLOv11 improves Recall and mAP in complex road-scene object detection, while introducing higher computational complexity than the original baseline model. Full article

When UAV(Unmanned Aerial Vehicle) carry out wildlife inspection for biodiversity protection, there are challenges such as low target, complex background, variable shape and serious occlusion, which lead to insufficient accuracy and a high misjudgment rate of the existing lightweight detection model. We propose an improved lightweight YOLOv8n model, which aims to achieve higher accuracy and more real-time animal target detection under the UAV platform. To address the issue of small target features being easily lost in the deep network, we introduce a dynamic upsampling convolution for accurate feature-aware upsampling, which can effectively reconstructs target details and suppress background noise. In order to enhance the feature discrimination ability of the model in complex environments, a convolution block attention mechanism was integrated in the model, and the key features of the target were adaptively focused through the channel–spatial dual attention mechanism. Finally, in order to improve the positioning accuracy in dense and occluded scenes, we used MPDIoU loss function to optimize the bounding box regression, and achieve more stable and accurate alignment by minimizing the vertex distance between the prediction box and the real box. Experiments on public data sets show that the detection accuracy and efficiency of the proposed model are significantly improved compared with the original YOLOv8n: the number of model parameters is reduced by 10.7%, the amount of calculation is reduced by 9.9%, and the inference speed is improved by 25%. In terms of comprehensive performance, our method achieved a mAP@0.5 of 96.4%, a mAP@0.5:0.95 improvement of 6.0 percentage points, and an F1 score of 93.5%, while also significantly reducing the false positive rate. Experiments on self-made aerial animal data sets further fully verify that the algorithm can achieve high-precision real-time animal target detection in the actual UAV platform. Full article

Learning-based multi-view 3D reconstruction pipelines, such as transformer-based approaches, enable the accurate reconstruction of 3D scenes from multiple images, but their deployment across the edge–cloud continuum is challenging due to high computational demands and large intermediate data transfers. Effective pipeline scheduling in the continuum must therefore balance latency constraints with the cost of cloud resource usage. In this work, we address cost-aware scheduling under latency constraints for a multi-stage 3D reconstruction pipeline consisting of depth estimation, transformer-based multi-view fusion, and point cloud merging with export to a rendering-ready representation. We implement a service-oriented pipeline where each stage can be executed either on edge or cloud nodes, and we experimentally characterize its performance on representative hardware platforms. The results show a strong imbalance between the computational time and communication latency across platforms, mainly due to large intermediate data. Based on these insights, we propose an online scheduler that dynamically selects stage placements to minimize the cloud cost while satisfying latency constraints. The scheduler incorporates a top-K edge selection mechanism that reduces the decision complexity by jointly considering the network conditions and node utilization. Simulation results parameterized with real-system measurements show that the proposed approach effectively reduces cloud usage while meeting latency constraints, outperforming the baseline strategies based on single-node pipeline execution. Full article

Assimilation of all-sky radiance (ASR) observations informs atmospheric states and cloud distributions; however, it does not always lead to improved analyses or forecasts. In particular, directly updating hydrometeor fields introduces substantial uncertainty into ASR assimilation. This study examines the impact of dynamic observation errors on analyses and precipitation forecasts under different hydrometeor control variable (HCV) configurations. Observation errors are prescribed using a fifth-order polynomial model as a function of a cloud impact parameter, allowing spatiotemporally varying (i.e., scene-dependent) errors that adapt to cloud conditions. Results indicate that dynamic observation errors generally improve cloud analyses and associated thermodynamic fields. By contrast, constant errors tend to overweight ASR observations in heavily cloud-affected regions, thereby degrading analysis quality. The advantages of dynamic errors are more pronounced when solid-phase hydrometeors are included in the HCV, as these strongly influence brightness temperature (BT) analysis and the representation of convective cloud tops. Among all experiments, those combining dynamic errors with direct updates of solid-phase hydrometeors produce the most realistic BT and reflectivity analyses, as well as the greatest improvements in precipitation forecasts. These results underscore the importance of cloud-dependent observation error modeling in ASR assimilation, particularly when solid-phase HCVs are employed. Full article

In Unmanned Aerial Vehicle (UAV) object detection tasks, complex lighting conditions and variable weather render robust all-weather perception challenging when relying solely on the visible modality. Although infrared modalities can provide complementary information, the reliability of individual modalities is highly scene-dependent. Existing multimodal detection methods typically adopt static fusion strategies, which ignore spatial heterogeneity of modal reliability and under-explore spatial-frequency collaborative representation, thus limiting detection robustness in dynamic environments. To address these issues, this paper proposes a Dual-domain Enhanced Adaptive Fusion Network (DEAF-Net), with two core innovative modules to tackle the above challenges. First, the Dual Domain Progressive Refinement (DDPR) module mitigates feature degradation caused by poor imaging conditions via the joint design of frequency-domain learnable filtering and scale-aware contextual refinement in the spatial domain, effectively suppressing noise, enhancing textures, and yielding a purified feature basis for fusion. Second, the Consistency–Discrepancy Guided Fusion (CDGF) strategy leverages the selective scanning mechanism of VMamba to model consistent and differential patterns across modalities, dynamically generates local modal contribution maps for adaptive fusion, and integrates global scene prior via entropy weights for calibration. Extensive experiments on the DroneVehicle and VEDAI datasets show that DEAF-Net outperforms mainstream multimodal detection methods, achieving mAP@0.5 scores of 81.9% and 76.2%, respectively, while delivering improved robustness in low-light, dense fog, and sparse-category scenarios. Full article

Adaptive bitrate streaming over HTTP relies on carefully constructed bitrate ladders and ordered sets of bitrate–resolution pairs to deliver optimal perceptual quality under fluctuating network conditions. While content-aware methods based on convex hull optimisation have substantially improved ladder efficiency for Video-on-Demand, they require exhaustive multi-resolution pre-encoding that is computationally prohibitive under the real-time constraints of live streaming. This challenge is compounded by the H.266/Versatile Video Coding (VVC) standard, which offers approximately 50% compression gains over HEVC at 8–10× the encoding complexity. This paper presents LiveCH-VVC, a latency-aware dynamic bitrate ladder prediction framework for VVC-encoded live streaming over Low-Latency DASH (LL-DASH) with CMAF packaging. The framework introduces four integrated modules: (i) a Lightweight Dual-Path CNN (LDP-CNN), obtained via teacher–student knowledge distillation (∼5 M parameters, 148 ms GPU inference), that jointly extracts spatial–temporal features from raw frames and compression-domain statistics from a fast VVC probe encode; (ii) an adaptive scene change detector with exponential moving average thresholding (F1 = 0.925) that triggers ladder updates only upon significant complexity shifts; (iii) a temporally augmented XGBoost multi-label classifier that predicts latency-constrained Pareto-optimal bitrate–resolution pairs; and (iv) an online adaptation engine that integrates Common Media Client Data (CMCD) feedback from CDN edge servers for continuous closed-loop refinement. Comprehensive evaluation on 81 UHD sequences (∼4050 CMAF segments) from three benchmark datasets demonstrates an average BD-Rate of $+0.68\%$ relative to the per-segment oracle convex hull $5.4\times$ better than the state-of-the-art ARTEMIS framework ($+3.67\%$) while achieving 73.3% encoding time savings, 2.37 s end-to-end latency, and a QoE score of 81.6 in live simulation with 100 concurrent clients. Ablation analysis confirms that the dual-path compression-domain branch ($+0.44$ pp) and temporal context augmentation ($+0.35$ pp) are the primary performance drivers, while the online adaptation mechanism provides $42\%$ relative improvement over extended streaming sessions. Full article

To address the critical challenges of multi-scale temporal dynamics and sensor-intrusiveness in driver fatigue detection, this paper proposes the Multi-Temporal Fusion Attention Network (MTFA-Net). The framework integrates two core innovations: a Multi-scale Temporal Adaptive Fusion (MTAF) module that dynamically weights short-, mid-, and long-term behavioral features via a scene-aware modulator, and a Physiological–Behavioral Cross-modal Adversarial Alignment (PBCAA) network that implicitly infers latent physiological states (e.g., HRV) from facial videos using adversarial learning and mutual information maximization. Experimental results on RLDD and NTHU-DDD datasets demonstrate that MTFA-Net achieves state-of-the-art accuracy (92.8%) while maintaining high interpretability and real-time efficiency, providing a robust, non-intrusive solution for intelligent cockpit safety. Full article

Visible and infrared (IR) image fusion has become an important strategy for improving computer vision performance under low illumination, occlusion, and some poor-visibility conditions. By integrating complementary textural information from visible images with thermal or IR cues, VIR fusion can enhance object localization, detection robustness, and facial-expression recognition (FER). This review examines VIR fusion techniques and datasets for computer vision applications, with object detection (OD) considered as a relatively mature scene-level task and FER considered as an emerging human-centered application. It summarizes major multimodal datasets, compares early-fusion approaches, including sensor- and feature-level fusion, with late-fusion approaches, including score- and decision-level fusion, and discusses representative machine learning and deep learning methods. The review also evaluates commonly used performance metrics and identifies current limitations, including dataset imbalance, sensor misalignment, limited demographic diversity in facial-expression datasets, computational complexity, and weak real-time generalization. Finally, key application areas, including surveillance, healthcare, remote sensing, autonomous systems, and human–computer interaction, are discussed. This review highlights the need for better-aligned multimodal datasets, standardized evaluation protocols, lightweight fusion architectures, and robust models capable of operating in dynamic real-world environments. Full article

Small object detection is fundamentally constrained by the lack of discriminative fine-grained features. Although introducing higher resolution detection scales can improve performance, it also amplifies background noise. In addition, the independently decoupled design of conventional detection heads is insufficient to address the persistent challenges of missed detections and false positives for small objects. To this end, we propose MSIA-YOLO, a YOLOv11-based detector with multi-scale semantic interaction and alignment, optimized from three complementary perspectives: feature modeling, high resolution semantic compensation, and task coordinated alignment. First, Receptive Field Attention Convolution (RFAConv) is integrated into the backbone to enhance critical local details, such as edge and texture cues, via receptive field aware attention. Second, to alleviate fine detail attenuation caused by repeated downsampling, we construct a CHSP-P2 small object detection framework with an additional P2 branch. A scale sequence fusion mechanism is further introduced to perform high resolution semantic compensation through cross scale hybrid inputs. Finally, we design a DTIA-Head (Dynamic Task Interaction and Alignment Head), which promotes joint optimization of classification and localization through dynamic task interaction and spatial alignment. Extensive experiments on the public datasets VisDrone, TinyPerson, and RSOD show that, compared with the YOLOv11n baseline, MSIA-YOLO improves mAP50 by 7.7%, 10.3%, and 1.0%, respectively, while also outperforming several advanced detectors. These results demonstrate the effectiveness and generalization capability of the proposed method in small object, dense object, and complex scene object detection scenarios. Full article

The accurate detection of unmanned aerial vehicles (UAVs) in various sizes played an important role in the practical applications. Yet the preceding works suffered from the missing inference, the false alarms, and the poor accuracy due to the the adverse scene conditions, as well as the mutable scales. To solve the problems, a hierarchical attention promoted cross-scale learning framework was proposed in this paper. First, the hierarchical attention mechanism was introduced in the backbone to generate the multi-scale features of targets, so they can be discerned and located at different scales. The resulting features were further delivered to the neck, in which two branches of features were built, respectively. The former was obtained by the target-specific feature operator, while the latter was generated by the upsampling operation. The dual branches were further connected in the quasi-residual structure. So the content of targets can be protected well, and the detail information can be reconstructed. Finally, the dynamic focusing loss measurement was presented to regress the bounding box of the target, so the learning effectiveness of presented the architecture can be promoted. To verify the proposed method, multiple rounds of experiments were performed. The results demonstrated that small and weak drones can be detected accurately, especially in adverse lighting and weather conditions. The evaluation metric of mean average precision rate (mAP) can be improved by 18.5% (YOLO6) on the collected dataset. Full article

Despite growing policy support for active travel, the fatality rate of vulnerable road users has remained persistently high in recent years, while the emergence of autonomous vehicles has further increased the complexity of mixed traffic environments. Interactions between cyclists and motorized vehicles are a major contributor to these fatalities, highlighting the urgent need for effective cyclist protection strategies. As one of the most widely adopted active transport modes, cycling safety cannot be assessed solely through crash statistics; understanding cyclists’ perceived safety is equally critical, as it reflects how infrastructure design and dynamic traffic conditions influence cycling behavior. In this study, we propose a cyclist safety perception framework that combines vision–language models with interpretable machine learning to analyze perceived safety in mixed traffic scenarios. A vision–language model is employed to generate semantic descriptions of traffic scenes, while an Explainable Boosting Machine quantifies both individual and interactive contributions of traffic-related features. By integrating visual information with road attributes extracted from OpenStreetMap, the proposed framework achieves a binary safety classification accuracy of 71% and a mean absolute error of 1.01 on a safety score scale ranging from 1 to 9. The results demonstrate the potential of combining multimodal perception and explainable models to support cyclist-centered safety assessment and inform sustainable and intelligent transportation system design. More specifically, the results show that protected cycling infrastructure is the most significant factor in improving perceived safety, whereas road construction has the opposite effect. Full article

Remote sensing scene classification remains challenging due to substantial object-scale variations, complex background interference, and high inter-class similarity. To address these issues, a lightweight classification framework, termed MDC-MobileNetV3, is proposed based on the MobileNetV3-Large backbone. The framework integrates a Multi-Scale Feature Extraction (MSFE) module for capturing spatial information at different receptive fields, a Dynamic Feature Weighted Fusion (DFWF) mechanism for adaptive feature recalibration, and the hierarchical CBAM attention strategy to enhance discriminative region representation. The model achieved high classification accuracies of 99.52%, 91.54%, 96.48%, 97.35%, 92.43%, and 99.72% on the UC Merced, WHU-RS19, NWPU-Resisc45, AID, CLRS, and PatternNet benchmark datasets, respectively, validating the effectiveness of the proposed framework, while maintaining a lightweight architecture with approximately 4.35 M parameters. In addition, Grad-CAM visualizations indicate that the model effectively focuses on semantically meaningful regions and suppresses irrelevant background information. The results confirm that the proposed framework provides a favorable trade-off between classification accuracy, model lightweight design, and model interpretability for remote sensing scene understanding. Full article

Shadows in high-resolution urban remote sensing imagery significantly degrade radiometric and structural information, thereby limiting the performance of downstream tasks such as classification and object extraction. Therefore, effective shadow removal is essential for improving the reliability of urban remote sensing applications. Existing methods still exhibit limitations in accurately detecting complex shadows, especially small-scale shadows and ambiguous boundaries, and shadow compensation in umbra regions often suffers from under-correction due to inadequate illumination modeling. To address these challenges, a physics-guided shadow removal framework that integrates lightweight shadow detection with illumination-aware compensation is proposed. A lightweight U-Net (LSDU) is designed to efficiently capture multi-scale shadow features, while a modified illumination intensity ratio method (MIIRM) is developed to explicitly model illumination differences between umbra and penumbra. Furthermore, a dynamic penumbra compensation method (MDPCM) is introduced to alleviate over-compensation effects in transition regions and improve radiometric consistency. Experiments on the Aerial Imagery Shadow Dataset (AISD) demonstrate that the proposed method achieves over 96% overall accuracy in shadow detection and the lowest RMSE in shadow compensation among existing state-of-the-art methods, while maintaining strong robustness across diverse urban scenes. Full article

Early smoke detection for forest fire prevention requires accurate and temporally stable decisions under dynamic clutter, tiny long-range targets, atmospheric degradation, and partial sensor unreliability. This paper presents FS-YOLOv3, a reliability-driven RGB–thermal smoke detector that extends a reproduced FS-YOLO baseline with two new modules: Cross-Temporal Consistency Alignment (CTCA) and Scene-Adaptive Expert Routing Fusion (SAERF). CTCA performs local short-horizon feature alignment and is evaluated with additional offset-field diagnostics to test whether the learned offsets correlate more strongly with annotated smoke expansion than with non-smoke motion. SAERF routes fused features to compact experts according to illumination, haze, texture ambiguity, and thermal reliability, with descriptor ablations and collinearity diagnostics used to examine routing stability. On the proposed clip-level RGB–thermal benchmark, FS-YOLOv3 improves over the reproduced FS-YOLO baseline from 93.7% to 96.3% mAP@0.5 and from 89.5% to 94.8% temporal alarm consistency (TAC), with 165 model FPS on Jetson AGX Orin under the default one-frame-look-ahead buffered inference setting. Comparisons with lightweight YOLO detectors, RGB-only and infrared-only controls, simple fusion strategies, and stronger temporal baselines provide deployment context, while the main technical evidence is the controlled gain obtained by enabling CTCA and SAERF on the same baseline architecture. To support reproducibility, the paper specifies the baseline interface, sensor and annotation protocol, sequence-disjoint split policy, temporal metrics, threshold sensitivity, causal CTCA behavior, SAERF descriptor analysis, and model-side versus end-to-end latency boundaries. The reproducibility package is organized to provide code, configuration files, split identifiers, evaluation scripts, diagnostic-statistic scripts, and illustrative sample annotations; redistribution of the full curated benchmark is handled through institutional data-review approval or controlled access when direct video release is restricted. Full article