Search Results (102)

Synthetic aperture radar (SAR) provides all-weather imaging but faces challenges in visual interpretation due to low contrast and coherent speckle noise. To address contrast deficiency and edge blurring in SAR-to-optical translation, we propose a Dual-Scale Aligned Network (DSAN) built upon Pix2PixHD. First, an asymmetric dual-prior architecture is designed: the global generator ingests low-resolution SAR images enhanced by histogram equalization to capture macroscopic structures, while the local generator utilizes original high-resolution SAR images to preserve microscopic details, alleviating the trade-off between contrast and fine textures. Second, a Dual-Scale Fusion Module (DSFM) coupling Large Kernel Attention and Collaborative Attention breaks scale barriers, enabling bidirectional cross-scale alignment and deep fusion. Third, a continuous differentiable soft-edge loss is formulated using logarithmic dynamic range compression to prevent highlights from dominating gradients and enforce boundary consistency across urban areas, water bodies, and farmlands. Experiments on the Nanjing and public SEN1-2 datasets demonstrate that DSAN outperforms state-of-the-art models—including Pix2PixHD, CycleGAN, MSTMNet, and ICMA—in perceptual distribution realism (FID) with the sharpest geometric boundaries. Ablation studies confirm the effectiveness of the asymmetric dual-prior design, DSFM, and the refined edge loss. Full article

Photovoltaic (PV) systems in arid regions experience substantial energy losses from dust accumulation, but automated cleaning can introduce risk when damaged modules are visually misclassified as dirty. Manual inspection is also impractical at utility scale. This study presents an edge-based cleaning-decision architecture in which vision proposes a cleaning request and independent electrical checks determine whether actuation is permitted. The prototype combines a YOLOv8n detector, INA219 voltage/current sensing, photodiode-based shading context, a Raspberry Pi 4, and an Arduino co-processor. Cleaning is allowed only when three conditions are satisfied: persistent dust detection, measured panel power below a predefined threshold, and the absence of an electrical structural-fault signature based on rolling-window voltage depression and instability. The detector was trained using 950 field-recorded frames containing 2850 annotated panel instances and achieved 77.3% mAP@0.5 on the validation set; across five retraining seeds, mAP@0.5 was $77.1\pm 1.1\%$. In a retrospective ablation of the recorded test campaign, the two verification gates reduced false or unsafe cleaning activations from five to one, while both unsafe activations involving the tested cracked module were vetoed. A 13.5 h three-day campaign recorded seven persistent visual dust requests; the power gate rejected six requests that did not justify cleaning, and the remaining request triggered a successful cleaning cycle. In that field event, panel power increased from 0.33 W to 7.48 W, corresponding to a 22.9-fold recovery. An assumption-based sensitivity analysis indicates potential water-cost savings from condition-based cleaning. An offline, template-constrained language model is used only for report generation and has no connection to actuation. Full article

Knowledge about Callinectes danae and Callinectes ornatus is thorough, although scarce in different ecological regions like Macaé, which are influenced by the Cabo Frio upwelling phenomenon in the southwestern Atlantic Ocean. This study analyzes spatiotemporal variation in the abundance of two swimming crab species in a region influenced by upwelling. Samplings took place from July 2013 to June 2014, on a monthly basis, with the aid of a shrimp fishing boat, in four different sampling sites. In total, 92 C. danae specimens were captured; C. ornatus was the most abundant species over the year; 1.436 individuals were captured. Both species were the most abundant in the shallowest sites and warmest seasons. Visual trends in temperature, salinity and sediment size (Phi) were observed for both species. Phi was the only significant variable associated with the sampled swimming crabs. The results indicated similar distribution between C. danae and C. ornatus, and a clear prevalence of C. ornatus, possibly due to C. danae’s estuarine dependence on its life cycle and to C. ornatus’s generalist behavior. The abundance of both species in Macaé is modulated by a combination of spatiotemporal and environmental variation in this upwelling region. Full article

Slender obstacles, such as ropes, cables, and rubber hoses, may interfere with the operation of autonomous street-sweeping vehicles because of their narrow shapes and weak visual features. This study presents RFP-YOLO26 as an applied detector-design and systems-integration approach that combines established SPDConv, C3k2_Faster_EMA, and SimAM modules with a fixed single-cycle feedback feature pyramid consisting of an initial top-down pass, one bottom-up feedback pass, and a second top-down refinement pass. Experiments were conducted on the proprietary USLO dataset using a random image-level split. On the current internal test set, RFP-YOLO26 achieved 97.9% mAP@0.5, 65.0% mAP@0.5:0.95, 98.1% precision, and 95.6% recall. Compared with YOLOv26n, these values represent increases of 2.9, 2.2, 1.7, and 4.3 percentage points, respectively. RFP-YOLO26 contains 4.21 M parameters and requires 9.9 GFLOPs, compared with 2.38 M parameters and 5.2 GFLOPs for YOLOv26n. Deployment on the Jetson Orin Nano indicates embedded execution feasibility under the reported configuration. The primary benchmark remains a seed-0 descriptive comparison. The supplementary five-seed analysis and the seed-0 principal-model comparison under route-disjoint Split A retained the same model ordering; the additional route-disjoint runs provided descriptive route-level summaries. However, the available evidence does not establish universal statistical superiority, external generalization, or improved operational safety. Full article

The digitalization of photovoltaic (PV) systems can support sustainable energy deployment by improving operational efficiency, system visibility, and energy extraction. However, many existing Internet of Things (IoT)-enabled solutions address monitoring and maximum power point tracking (MPPT) separately or depend on proprietary platforms, remote cloud services, and relatively costly hardware, which may restrict their accessibility and replication in small-scale and resource-constrained applications. This study presents the implementation and laboratory-scale experimental evaluation of an edge-IoT architecture that integrates real-time PV monitoring, embedded adaptive MPPT control, local data management, and visualization using low-cost hardware and open-source software. The proposed architecture combines an ESP32 microcontroller with a Raspberry Pi (RPi) local server to enable environmental and electrical sensing, edge-based control, message queuing telemetry transport (MQTT) communication, local data storage, and interactive visualization through the open-source Node-RED, InfluxDB, and Grafana platforms. An adaptive perturb-and-observe (AP&O) algorithm is implemented on the ESP32 to dynamically adjust the duty cycle of a DC–DC boost converter in response to changing operating conditions. The system is experimentally evaluated using a PV test bench equipped with a custom boost converter and sensing modules measuring eleven electrical and environmental parameters. The architecture achieved an average communication latency of 193 ± 23 ms and an average MPPT efficiency of 97.3 ± 0.54%. It also provided a power gain of 0.7 ± 0.5% compared with the conventional fixed-step perturb-and-observe method. By combining local processing, open-source software, low-cost components, and integrated monitoring and control, the proposed system reduces dependence on external cloud infrastructure while supporting responsive and accessible PV energy management. These results demonstrate its potential as a replicable technological framework for improving the operational sustainability and digital management of small-scale PV installations. Full article

Manual visual diagnosis of apple diseases suffers from low efficiency, strong subjectivity and poor scalability for large commercial orchards. Existing research mainly targets diseases on single plant organs, whereas full-growth-cycle detection has to cope with extreme multi-scale differences among lesions. For instance, Valsa canker on tree trunks leads to extensive cortical necrosis, while early-stage anthracnose on fruits appears as tiny spots spanning only a few pixels. These significant scale gaps necessitate robust spatial feature aggregation and anti-noise ability to resist complex background interference. Aiming to achieve rapid and precise detection of diseases on multiple apple organs including leaves, fruits, trunks and branches, this work presents an enhanced YOLOv11 model equipped with the Information Integration Attention (IIA) module. The IIA module is embedded into the key fusion layers of the backbone and neck networks. It strengthens the extraction of fine-grained lesion features, recovers spatial location information via a bidirectional attention mechanism, and suppresses noise induced by uneven lighting and intricate backgrounds. To guarantee stable convergence on low-resource computing devices, a tailored training scheme is designed. Experimental results on a seven-category dataset with 7406 images demonstrate that YOLOv11-IIA reaches a precision of 0.763, a recall of 0.819, mAP@50 of 0.857 and mAP@50-95 of 0.699, which achieves clear performance improvements over the original YOLOv11 (mAP@50 improved from 0.485 to 0.857) and other attention-augmented detectors. The model operates stably on an NVIDIA GTX 1050 4GB GPU with an inference speed of 16 FPS for 640 × 640 input images; comprehensive quantitative computational metrics including parameter count, FLOPs and memory consumption will be fully measured in subsequent UAV deployment experiments. The proposed method provides a reliable technical reference for intelligent apple disease monitoring in smart orchard systems. Full article

This paper presents the design and preliminary field validation of a portable, low-cost Internet of Things (IoT) station for georeferenced soil nutrient profiling in agricultural environments. The proposed system integrates a digital RS-485 NPK soil sensor, an ESP32 microcontroller, and a SIM7000G GSM/GPS module to enable on-site acquisition and real-time transmission of nitrogen (N), phosphorus (P), and potassium (K) measurements using the MQTT protocol. Data are serialized in JSON format and transmitted to a ThingsBoard cloud platform for remote storage and visualization. The portable architecture supports manual spatial sampling across multiple locations without reliance on fixed infrastructure, making it suitable for small- and medium-scale agricultural contexts with limited connectivity. Preliminary testing in a controlled lemon plantation demonstrated stable GSM connectivity, successful geotagging, and consistent cloud-based visualization, with an average acquisition–transmission cycle of 30–45 s per measurement. Spatial heat maps generated from collected data illustrate the system’s capability for indicative nutrient mapping. Although laboratory-grade validation is ongoing, the results confirm the technical feasibility of integrating low-cost sensing, cellular communication, and georeferenced data acquisition into a compact IoT unit. The system establishes a foundation for future calibration, large-scale field validation, and decision-support applications in precision agriculture. Full article

The automotive industry is evolving toward Software-Defined Vehicles (SDVs) enabled by centralized computing, cloud integration, and Over-the-Air (OTA) updates. Yet, prevailing SDV and Internet of Vehicles (IoV) simulators often treat each vehicle as a single monolithic node, obscuring the interplay between internal vehicle modules and the surrounding infrastructure in dense urban scenarios. This work proposes a modular SDV reference architecture embedded in a Software-Defined Internet of Vehicles (SD-IoV) framework together with a Software-in-the-Loop (SiL) co-simulation testbed built on Objective Modular Network Testbed in C++ (OMNeT++), Simulation of Urban MObility (SUMO), and Vehicles in Network Simulation (Veins). The architecture decouples perception, communication, decision, and actuation into typed replaceable modules and instantiates them across six co-existing agent types: an SDV; two human-driver vehicle classes with cognition modelled as a multi-stage Eye–Ear–Brain–Hand–Foot pipeline with reaction-delay sampling; a public transport bus; a Roadside Unit (RSU); and a Traffic Light (TL). Three platform-level mechanisms connect the agents to the infrastructure: a single shared world model with a three-layer line-of-sight funnel that serves visual-sensor queries and reuses the building polygons of the wireless shadowing model; a dual-CPU mobile-fog node implementing a cycles-per-frequency workload model with explicit end-to-end latency decomposition; and a three-plane intersection coordination fabric that combines 802.11p wireless with a wired RSU-to-TL star and a wired peer mesh between adjacent TLs. The initial results confirm that the implemented message paths and module interactions behave as specified, including directional Signal Phase and Timing (SPaT) reception, cross-junction handover, bus-side fog-offload latency accounting, and passive identification of Vehicle-to-Everything (V2X)-silent vehicles. Several architecture elements are specified but deliberately not exercised in the present evaluation and remain design targets for future work: the Roadside Unit (RSU) route planning and fog computing companion (and any multi-tier offloading comparison), non-line-of-sight SPaT reception, and a safety violation detection layer. Within the above scope, the testbed is positioned as a reusable foundation for module-level SDV research and as a basis for future extensions such as Joint Communication and Sensing (JCAS), energy-aware driving, and Hardware-in-the-Loop (HiL) integration. Full article

Traditional manual 10 kV live-line maintenance is accompanied by high personal risks and incomplete safety protection, while overall operational efficiency is limited. This paper develops an intelligent live-working robot based on a tracked insulated spider aerial vehicle. The system is equipped with vertical lifting modules and a pair of 6-DOF insulated manipulators to form a 13-DOF integrated motion platform. Binocular cameras, LiDAR, real-time insulation monitors, and electromagnetic interference detectors are integrated as multi-modal sensing hardware to achieve high-precision positioning of overhead lines and pole fittings. A master–slave collaborative control strategy combined with mixed reality (MR) and visual auxiliary force feedback is proposed to coordinate the tracked chassis, lifting structure, and dual manipulators. A four-dimensional full-cycle safety guarantee framework is further constructed, covering insulation protection, anti-interference communication, human–machine risk avoidance, and full-task supervision to support real-time early warning and motion interlock. Field tests on actual 10 kV distribution lines verify stable positioning performance under controlled test conditions, and no safety accidents occurred in all trials. The designed robotic system provides an optional technical scheme for intelligent unmanned live-line maintenance of distribution networks. Full article

Automatic inspection of small, irregular stamped parts remains challenging due to their compact size, random orientation on conveyors, and susceptible metallic surface reflections, coupled with local, weak, and densely distributed defects. This study presents an integrated vision-based dynamic defect detection and robotic sorting system to address these issues. The framework seamlessly unifies conveyor-based image acquisition, YOLO-CGMS-based defect recognition, hand–eye coordinate mapping, and Delta robot trajectory planning. To drive real-time visual perception, the YOLO-CGMS architecture modifies the YOLOv8n baseline by incorporating C2f-CRM, GRF-SPPF, MCA, and Inner-GIoU modules, optimizing small-defect feature extraction and bounding-box regression. Evaluated on a factory-collected dataset, YOLO-CGMS achieved an mAP50 of 88.7% and an inference speed of 236.23 frames/s, using only 2.8 M parameters and 7.3 GFLOPs. Compared with YOLOv8n, mAP and execution speed increased by 5.1 percentage points and 12.18 frames/s, respectively, while the parameter size and computational cost dropped by 0.2 M and 0.8 GFLOPs. Furthermore, physical sorting capability was validated on a developed prototype platform, yielding a mean hand–eye positioning error of 2.66 mm. Across 200 dynamic trials, the system successfully sorted 161 defective workpieces, translating to an 80.5% success rate and a mean cycle time of 2.6 s per part. These findings confirm that the proposed system reliably links closed-loop visual perception with physical execution, providing a practical foundation for the automated quality control of complex stamped components. Full article

The stroboscopic effect and phantom array effect caused by temporal light modulation (TLM) in light-emitting diode (LED) lighting are important temporal light artifacts (TLAs) that can influence visual perception, task performance, and visual comfort. This review systematically analyzes 40 studies published between 1998 and 2024 to provide a comprehensive overview of the current understanding of both effects. The reviewed literature covers visibility thresholds, influencing parameters, experimental methodologies, and assessment metrics. The analysis shows that reported visibility thresholds for the stroboscopic effect typically range from 550 to 1000 Hz, whereas thresholds for the phantom array effect may extend to 10–15 kHz, suggesting substantial differences in the underlying perceptual mechanisms. In addition to modulation frequency, modulation depth, waveform, duty cycle, luminance, retinal image motion, and observer factors have been identified as important determinants of visibility. The review further highlights significant methodological differences among studies, including variations in experimental design, stimulus generation, participant characteristics, and psychophysical procedures. Although the stroboscopic visibility measure (SVM) provides a standardized framework for evaluating the stroboscopic effect, no comparably validated metric is currently available for the phantom array effect. The review identifies major knowledge gaps regarding the interaction of influencing parameters and the lack of standardized assessment methods. Future research should focus on establishing unified experimental protocols and developing robust metrics for the phantom array effect to support comprehensive lighting standards that protect visual comfort, well-being, and consumer health. Full article

Wearable-sensor human activity recognition (HAR) plays a key role in health monitoring, elderly care, and human–computer interaction. Deep learning dominates the field, but two limitations remain. CNNs with fixed kernels cannot capture cross-scale temporal events such as gait cycles and postural transitions in a single layer, and softmax attention on small sensor datasets is often diluted by common-mode background responses across the sequence. We propose DMSCNet, an end-to-end framework with two modules. The Dilated Multi-Scale Branch Block (DMSB) combines a shared bottleneck, parallel dilated convolutions, a pooling bypass, and SE-based channel recalibration to widen the temporal receptive field under a controlled parameter budget. The Contrastive Temporal Attention (CTA) module adopts a dual-path differential design, in which the two paths learn overlapping but non-identical attention patterns and their subtraction suppresses shared low-level responses while preserving the discriminative positions each path locks onto, encoded with opposite signs. DMSB and CTA are cascaded into a DMSC Block and stacked residually. On UCI-HAR, USC-HAD, and RealWorld, DMSCNet reaches F1-scores of 97.65%, 91.80%, and 99.05%, outperforming nine baselines. Ablations confirm that SE acts along the channel axis and CTA along the temporal axis, and visualization reveals a dynamic–static dichotomy together with a signed bipolar encoding pattern produced by the dual-path subtraction. Full article

This paper presents Resilient Edge-IVA (Intelligent Video Analytics), an integrated framework designed to ensure real-time inference stability and high-speed embedding-based similarity search in resource-constrained edge computing environments. Conventional systems often face Quality of Experience (QoE) degradation caused by computational overhead and hardware-level bottlenecks. To address these challenges, this study proposes a “Whole-cycle” methodology employing a perception-driven, three-tier adaptive control algorithm. This algorithm dynamically modulates encoding parameters, such as resolution and bitrate, by utilizing real-time inference latency and CPU utilization as feedback signals. Furthermore, the framework incorporates an event-density-based Data Diet mechanism. This mechanism selectively adjusts video quality based on object detection results, preserving high-fidelity imagery for critical events while significantly reducing data volume during static intervals. The backend implements a hybrid storage architecture combining the Milvus vector database for CLIP-based high-dimensional visual embeddings with a PostgreSQL relational database for structured metadata. These systems are linked via a deterministic hash key to ensure data atomicity and facilitate high-speed, multi-dimensional embedding-based retrieval. Experimental evaluations conducted on a Raspberry Pi 5 and Hailo-8 NPU demonstrate that the proposed framework maintains a frame drop rate below 0.3% even under extreme workloads, providing a 13-fold improvement in operational stability over static configurations. The results also confirm a 54.2% reduction in total storage occupancy and a Hash Mapping Consistency (HMC) score of 0.89. These findings validate the framework’s effectiveness in reconciling real-time processing stability with storage efficiency. Building upon this baseline, future research will extend the framework to multi-class environments, targeting applications such as Intelligent Transport Systems (ITS). Full article

Aerosol-generating procedures (AGPs) expose healthcare personnel to airborne pathogens and require portable engineering controls that can be integrated into routine clinical workflows. We developed a portable, foldable negative-pressure aerosol-containment system (FNPACS) combining adaptive fan control, an H14 high-efficiency particulate air (HEPA) filter, and a disposable metal-oxide prefilter in a mobile filtration module. Bench performance was evaluated using pressure-flow testing in accordance with National Environmental Balancing Bureau (NEBB) procedures and International Organization for Standardization (ISO) 14644-3, polyalphaolefin aerosol challenge testing, and smoke visualization, while an exploratory clinical study assessed environmental contamination via real-time reverse-transcription PCR (rRT-PCR) in 11 patients (31 assay analyses). Bench testing demonstrated HEPA filtration efficiencies of 99.994–99.997%, stable negative-pressure generation across fan duty cycles, no detectable downstream breakthrough beyond the HEPA filter under the tested conditions, and effective inward airflow on smoke testing. A Lagrangian discrete phase model (DPM) particle-tracking simulation further characterized size-dependent aerosol-surrogate transport. Under HEPA-ON active-extraction conditions, 73.0–86.1% of simulated 0.3–10 µm water-equivalent particles were transported to the HEPA suction pathway, while 13.9–27.0% were deposited on internal wall surfaces. In the clinical evaluation, SARS-CoV-2 RNA detection on environmental swabs was limited and predominantly low level. The clearest reproducible signal occurred on the top interior surface under HEPA-OFF conditions, whereas HEPA-ON detections were isolated or presumptive high-Ct signals without reproducible confirmation. These findings provide preliminary engineering and usability support for FNPACS as a feasible near-source aerosol-control platform for AGPs. The patient swab component should be interpreted as an exploratory, proof-of-concept assessment rather than confirmatory evidence of clinical containment efficiency because several clinical cases had non-supportive patient-related controls and were therefore not used in the primary containment interpretation. Full article

To address the application requirements of dynamic simulation for sudden deep pavement potholes, this study presents an automated cover plate control device that integrates concealment, rapid response, and high load-bearing capacity, thereby overcoming the inherent contradiction between “portable yet weakly load-bearing” and “highly load-bearing yet inflexible” that has long limited conventional cover plate solutions. The core of the device comprises a cover plate mechanism consisting of a UHPC–Q235 composite cover plate, a distributed truss, and specially configured connecting rods, together with a winch hoisting mechanism, a hydraulic locking and rapid-release mechanism, and an embedded steel frame structure. Together, these modules realize a complete operational cycle of “closed load-bearing support → hydraulic release → gravity-driven rotation → winch reset.” Theoretical analysis and experimental measurements demonstrate that hydraulic release can be accomplished within 0.5 s, the cover plate can form a standard collapse pothole of 2000 mm in diameter within approximately 1 s, and a single cycle requires approximately 11 s, thereby faithfully reproducing the dynamic process of sudden pavement collapse. Refined mechanical design and ABAQUS finite element simulations verify that under the most adverse loading conditions, the stress in all structural components remains below the material design strength limit, with clear and reliable load transfer paths maintained in all operational states. The integrated camouflage design achieves over 95% visual and tactile similarity to the existing pavement surface, meeting the design requirement of concealment under normal conditions. The proposed device offers a high-fidelity physical simulation solution for autonomous vehicle perceptual training under emergent road hazards and for roadway safety assessment. Full article