Search Results (1,125)

Autonomous unmanned aerial vehicles (UAVs) must decide when to trust onboard perception, when to request edge support, and when to avoid acting under poor visual or communication conditions. This study develops a risk-aware edge-assisted UAV perception framework that combines calibrated visual confidence with next-window service-level agreement (SLA) feasibility. The local branch uses MobileNetV3-Small for fast onboard color recognition, while the edge branch uses ResNet-18 for stronger remote inference. Low-confidence samples are offloaded only when the SLA predictor estimates that the wireless link is feasible; otherwise, the system enters fallback, meaning that the current prediction is not treated as immediately actionable. The evaluation follows a hard cross-illumination split: indoor and fluorescent light samples are used for training and validation, and indoor night and sunlight samples are reserved for testing. Under this setting, the local model achieves 76.89% accuracy and 73.25% macro-F1, while the edge model achieves 81.26% accuracy and 77.58% macro-F1. The SLA predictor, trained on enhanced telemetry features while preserving the original target label, achieves 85.74% accuracy, 85.57% macro-F1, 0.9420 ROC-AUC, and 0.9585 PR-AUC on temporally held-out records. The joint policy achieves 93.23% coverage and 79.90% success over active decisions, using local inference for 82.76% of the samples, edge offloading for 10.47%, and fallback for 6.77%. These results indicate that the framework is best understood as a tunable risk management layer for UAV perception rather than a pure accuracy maximization classifier. It avoids blind offloading and reduces forced decisions when both visual confidence and communication feasibility are weak. Full article

Conventional full-space heating systems waste massive fossil-derived energy on unoccupied indoor areas and cause uncomfortable “warm head, cold feet” issues against sustainable building targets. To fill this gap and advance low-carbon indoor heating solutions for sustainable office development, this study proposes an innovative localized heating terminal combining radiant panels and downward laminar air supply. An experimental platform was established, with twelve testing cases covering varied supply air velocity, supply air temperature and radiant panel temperature to explore its thermal comfort and energy-saving sustainability performance. Experimental results demonstrate that, under the optimal operating condition (0.55 m/s airflow, 23.5 °C supply air, 36 °C radiant panel), the vertical head–foot temperature difference reduces to merely 1.2 °C, far below the 3–5 °C threshold of conventional heating equipment; the draught rate approaches zero to eliminate cold draft discomfort. Critically, 65–75% of total supplied heat concentrates within human-occupied zones, drastically cutting redundant heat loss and advancing building heating sustainability. The terminal features dual working modes: convection contributes 78.7–94.4% of total heat for rapid warm-up while radiant heat maintains stable long-term comfortable surroundings. Such flexible dual-mode design supports sustainable part-load operation matching intermittent office occupancy, making this terminal a feasible low-carbon option for modern sustainable office buildings prioritizing energy efficiency and a healthy indoor environment. Full article

Stable three-dimensional hand landmark reconstruction using low-cost RGB-D sensors is important for human–computer interaction, robot teleoperation, and vision-based motion analysis. RGB-based hand landmark detectors provide stable semantic 2D landmarks, but their depth output is not a metric measurement in the physical camera coordinate system. Stereo cameras can provide metric depth, but direct landmark-level back-projection is sensitive to invalid pixels, local depth holes, boundary noise, and partial occlusion. To address these problems, this paper presents a lightweight RGB-D sensing front-end that combines MediaPipe semantic hand landmarks with ZED2 stereo depth. The proposed pipeline detects 21 semantic hand landmarks in the RGB image, obtains landmark-level metric depth from the aligned ZED2 depth map using local median sampling, reconstructs 3D landmarks by camera back-projection, and further applies exponential moving average filtering and a bone-length consistency constraint. Experiments were conducted on a self-collected SVO dataset containing 13 hand actions and 26 recorded sequences, and an additional checkerboard-based reference-distance validation was performed to evaluate the metric depth sampling and 3D back-projection component. Compared with single-pixel sampling, the $5\times 5$ local median strategy slightly increased the valid-depth ratio from 0.9731 to 0.9738 and reduced the temporal smoothness metric from 1.7163 mm to 1.6902 mm. To further justify the temporal filtering choice, an additional comparison with the 1 Euro Filter was conducted using the reconstructed win5 trajectories. The 1 Euro Filter produced stronger smoothing, reducing the temporal smoothness metric to 0.196 mm, but also reduced the path-length ratio to 0.484, indicating substantial motion attenuation. EMA0.7 was therefore retained as a more balanced setting, reducing the temporal smoothness metric to 0.826 mm while maintaining a path-length ratio of 0.803. The BL0.5 bone-length constraint reduced the bone-length standard deviation from 2.0727 mm to 1.1995 mm with limited trajectory modification. The final configuration provides a practical low-cost RGB-D front-end for stable 3D hand landmark reconstruction under controlled indoor conditions. Full article

Poor indoor air quality, inadequate ventilation, and unnoticed local disturbances can reduce occupant well-being and compromise practical safety in smart-home and small-building environments. Although low-cost Internet-of-Things (IoT) sensing technologies are widely available, many monitoring systems remain focused on single-modality sensing and do not jointly evaluate environmental conditions, vibration activity, communication reliability, and gateway-side interpretation within one framework. This study presents the design, implementation, and proof-of-concept evaluation of a low-cost, privacy-conscious, non-imaging IoT-based indoor environment and safety-awareness monitoring framework built with ESP32/Arduino sensor nodes and a Raspberry Pi gateway. The system integrates carbon dioxide, temperature, humidity, gas-resistance/VOC-trend indication, and vibration sensing with MQTT-based communication and edge-side analytics. Controlled subsystem experiments showed that CO₂ concentration differentiated ventilation conditions, increasing from 395.47 ppm in the valid empty/open-door baseline to 1083.16 ppm in the closed occupied condition. Vibration states were distinguished using root-mean-square acceleration features across calm, surface-disturbance, footstep, play, and jump conditions. MQTT evaluation using 1000-message batches showed no observed message loss or duplicates across the tested QoS/network combinations, although latency and throughput varied by network configuration and QoS level. QoS 1 provided a practical balance between low latency and protocol-level delivery assurance in the tested local/Wi-Fi setting. A final integrated validation run further demonstrated synchronized acquisition from indoor environmental, vibration, and outdoor CO₂ reference publishers through the same Raspberry Pi gateway, with zero missing or duplicate sequence flags across the three streams. Overall, the findings indicate that lightweight open-source IoT hardware can support a reproducible building-level sensing and edge-analytics prototype for indoor environment and safety-awareness monitoring. Broader deployment in standard-sized rooms, multi-room buildings, and smart-city infrastructure remains future work. Full article

Single-view RGB-D observations are often affected by occlusion and restricted viewpoints, leading to incomplete object geometry and underestimated obstacle extents in indoor robot perception. This paper proposes a single-view scene completion framework that integrates candidate model retrieval and scale-aware registration. The framework first generates local RGB crops and partial point clouds through automatic instance segmentation; then retrieves complete candidate models by matching the local crops with multi-view rendered CAD images; and finally estimates candidate-to-observation rotation, translation, and scale to insert the selected aligned model into the original scene coordinate system. Experiments show that the retrieval module achieves Recall@1/Recall@5 of 80%/89%. The registration module reaches a success rate of 56.61%, outperforming the second-best method by 12.28 percentage points. More importantly, scene-level evaluation shows that the proposed method improves occupancy F1 from 0.445 to 0.523 and reduces boundary error from 0.202 m to 0.146 m compared with DiffCAD. These results indicate that the proposed framework improves navigation-oriented occupancy and obstacle-boundary recovery under CAD-library-based and segmentation-dependent single-view scene completion settings. Full article

Background: Monitoring external load in team sports is essential for performance optimization, injury prevention, and individualized training prescription. Although Local Positioning Systems (LPS) are widely used for indoor athlete tracking, they require wearable devices and specialized infrastructure. Recent advances in artificial intelligence and computer vision allow markerless athlete tracking; however, their validity for basketball remains insufficiently explored. Objective: To evaluate the validity of a deep-learning multi-camera computer-vision system for quantifying external-load variables in basketball compared with a commercial LPS. Methods: The framework integrated fisheye video acquisition, player detection, and pose estimation using YOLOv11x-Pose and player re-identification through ResNet-50 and FAISS similarity search. Positional data were transformed into real-world court coordinates to derive distance, acceleration, deceleration, player load, and average speed metrics. Outputs were compared with measurements obtained from Kinexon LPS. Results: Strong correlations were observed for total distance (r = 0.92), acceleration counts (r = 0.90), deceleration counts (r = 0.92), and player load (r = 0.81), while average speed showed a moderate-to-strong correlation (r = 0.66). ICC and Bland–Altman analyses indicated agreement between systems. Conclusions: The proposed computer-vision system demonstrated high agreement with LPS, supporting its use as a valid, non-invasive, and scalable solution for external load monitoring in basketball. Full article

In the western Hunan region, the fire pit serves as the primary space for heating, receiving guests, and sacrificial ceremonies. However, the prolonged use of wood as the main fuel for the fire pit poses a significant threat to indoor air quality and the health of residents. This study conducts field monitoring and evaluation of indoor air quality in traditional earthen residences in Western Hunan during winter. It employs software simulation to analyze the concentration of indoor pollutants in typical earthen dwellings. Three passive mitigation strategies—adjusting window size, installing interior partitions, and setting up passive smoke exhaust systems—are proposed, and their effectiveness is validated through simulation. The results indicate that the best air circulation performance occurs when the window sill height is between 0.9 and 1.5 m, and the window sill length is between 1.5 and 2.1 m. Installing partitions increases the average concentration of indoor pollutants in the fire pit and master bedroom areas by 2.33 and 3.05 times, respectively. Installing smoke exhaust systems above the fireplace can decrease indoor pollutant concentrations by more than 70%. The findings provide effective strategies for controlling health risks caused by indoor pollutants in winter without affecting local residents’ living habits and traditional customs. Full article

Tomato leaf diseases substantially reduce tomato yields and quality and remain a persistent challenge for efficient crop management. Although deep learning-based detectors have achieved strong accuracy in controlled benchmarks, many existing solutions are still difficult to transfer to resource-constrained agricultural systems because they rely on high-end GPUs, consume considerable power, and often lose performance after deployment on embedded devices. To address this practical gap, this study proposes HGS-YOLO, a system-oriented deployable lightweight adaptation of YOLOv11 for leaf-level tomato disease detection, together with an end-to-end edge sensing pipeline for low-power agricultural deployment. The main contribution lies in the coordinated system-level co-design of model structure, optimization, and deployment rather than in a novel detector architecture. Specifically, YOLOv11 is adapted through three coordinated modifications: an HGNetV2 backbone for efficient feature extraction, an HS-FPN neck with channel attention for lightweight multi-scale fusion, and an MPDIoU loss function for more stable localization optimization. Beyond the model architecture, the study establishes a complete engineering pipeline that includes training, optimization, post-training quantization, and hardware deployment with BPU acceleration on a D-Robotics RDK X5 handheld platform. Comprehensive benchmark experiments indicate that HGS-YOLO achieves 93.6% ${\mathrm{mAP}}_{50}$ and 72.1% mAP@[0.5:0.95] with 86.5% recall, only 1.3 M parameters, and a 3.1 MB model size, substantially reducing the model complexity and storage cost relative to the YOLOv11 baseline. A three-seed retraining comparison shows that HGS-YOLO trades roughly 0.5 ${\mathrm{mAP}}_{50}$ points for this compactness (a statistically significant but small concession) and recovers the cost on the deployment side: on the RDK X5 chip, HGS-YOLO is the fastest, most memory-efficient, and lowest-power model among all compared detectors. Indoor deployment tests using separately collected tomato leaf samples further achieve 90.3% ${\mathrm{mAP}}_{50}$, 82.3% recall, 89.0% precision, 25.0 ± 0.4 ms end-to-end latency, 40.0 ± 0.6 FPS, and 9.8 ± 0.4 W average system power. After PTQ, the ${\mathrm{mAP}}_{50}$ drops from 93.6% to 93.0% on the same benchmark; because this figure was measured under controlled imaging conditions, it is presented as an in-distribution reference point rather than as evidence of robustness in the open field. We also took the handheld system into a working tomato greenhouse for a small outdoor field round, where it ran end-to-end and produced on-device disease detections under natural sunlight, specular highlights, partial occlusion, background clutter, and handheld motion blur. These results show that HGS-YOLO reaches a good balance of accuracy, efficiency, and deployability and that it works in the field on an independent small-scale test; validating it more widely across sites, seasons, and weather is left to future work. Full article

In environments where GNSS signals are unavailable—such as indoor spaces, underground facilities, and forested areas—autonomous UAV navigation faces challenges related to localization uncertainty and limited onboard sensing capability. This study proposes a lightweight navigation framework using a single Intel RealSense D435i depth camera, integrating RTAB-Map SLAM, DWA-based local planning, and a direction-oriented frontier exploration strategy. The proposed exploration strategy introduces heading consistency into frontier target selection to support navigation in directionally constrained environments. The system is implemented within the ROS framework and evaluated in Gazebo/ArduPilot SITL simulation environments under low-, medium-, and high-density obstacle configurations. The results show that the system successfully completed autonomous traversal and return-to-home missions across all scenarios, with traversal RMSE values of 0.195 m, 0.197 m, and 0.420 m and return RMSE values of 0.295 m, 0.474 m, and 1.084 m, respectively. Qualitative dynamic-obstacle tests further demonstrate the system’s capability for local map updating and replanning. It should be noted that the current evaluation is primarily simulation-based and conducted in simplified environments. Therefore, the results are interpreted as initial system-level validation rather than full real-world deployment verification. The proposed system should not be directly interpreted as a ready-to-deploy real-world UAV navigation solution. Future work will focus on physical UAV experiments and more realistic GNSS-denied environments. Full article

Indoor service robots often face challenges in target localization and robotic grasping under cluttered backgrounds, partial occlusion, and viewpoint variations. To address these issues, this study proposes a vision-guided robotic grasping framework based on an improved feature matching algorithm termed Mahalanobis-accelerated Scale-Invariant Feature Transform Plus (MSIFT+). The proposed method integrates Mahalanobis distance metric reconstruction with a dynamic Best-Bin-First (BBF) search strategy to improve matching robustness and computational efficiency. A multi-scenario indoor dataset was constructed to evaluate the proposed method under rotational variation, weak-texture, and partial occlusion conditions. The results demonstrate that the MSIFT+ algorithm significantly outperforms other methods in cross-scenario consistency and adaptability to weakly textured targets. Furthermore, a binocular vision-guided robotic grasping system was developed and validated through practical robotic experiments. Experimental results confirm that the MSIFT+ algorithm enhances detection performance for small and clustered targets in complex environments. The proposed framework provides an effective and reliable solution for robotic object localization and grasping in complex indoor environments. Full article

The emergence of Artificial Neural Networks (ANNs) and their deep learning form called Artificial Intelligence (AI) opened a new path to improve energy efficiency and the indoor environment. A small collaborating network team is now extending the passive house approach, in a book entitled Retrofitting, the Energy and Environment of Buildings (Gruyter Publishers), and presenting generalized AI modeling in the following paper. This concept uses a long-term neural network with a short-term memory (LSTM) and three stages (training, validation, and test) for optimalization to hourly data collected for one full year. The non-residential buildings are less affected by the space occupants. This paper examines the feasibility of a uniform, climate modified technology, as our objective is to create a universal and affordable approach to buildings assisting in slowing the rate of climate change. Hence, the idea of creating a generalized neural network for predicting electricity consumption linked with weather conditions was born. This network is to forecast the electricity consumption for buildings linked to the local weather conditions, but different categories of buildings are put together in one set. While this will lower the large set precision, still our question is if such a network would work. If so, in the future we will create multi-variant, local residential systems with the capability of predicting energy use. Full article

This study investigated the degradation behavior of a polyurethane acrylate coating/Q345B steel system under the coastal atmospheric conditions of Wenchang, Hainan, and evaluated the correlation between indoor accelerated tests and outdoor exposure. Outdoor exposure tests, single-factor accelerated tests (UV irradiation and neutral salt spray), and a multi-factor cyclic accelerated test combining UV, salt spray, humidity, and thermal cycling were conducted. Coating degradation was characterized by morphological observation, gloss measurement, adhesion testing, and electrochemical impedance spectroscopy. The results showed that after 8 months of outdoor exposure, localized rust spots, blistering, and under-film corrosion appeared on the coating surface. The gloss loss rate reached 15.72% after 3 months, while adhesion decreased from 5.83 MPa to 2.39 MPa during prolonged exposure. UV irradiation mainly affected gloss degradation, whereas corrosive media penetration played a dominant role in adhesion loss and electrochemical deterioration. Compared with single-factor tests, the multi-factor cyclic accelerated test exhibited the highest correlation with outdoor exposure. The corresponding correlation coefficients for gloss loss, adhesion, and low-frequency impedance modulus were 0.9764, 0.9988, and 0.9929, respectively, while the gray relational coefficients reached 0.8334, 0.8467, and 0.7977. These results demonstrate that the multi-factor cyclic accelerated test more accurately reproduces the degradation behavior and failure characteristics observed in the coastal atmosphere of Hainan. The proposed method provides a practical approach for indoor–outdoor correlation analysis and durability evaluation of protective coatings in marine atmospheric environments. Full article

Visually impaired users face significant challenges in navigating complex indoor environments due to limited spatial awareness and lack of real-time semantic guidance. This paper proposes a multimodal navigation system integrating environmental perception with vision-language models (VLMs). It provides context-aware and explainable guidance without requiring additional infrastructure. The proposed system combines RTAB-Map for localization, YOLO-World for open-vocabulary object detection, and a lightweight language model for semantic reasoning and natural language interaction. To evaluate our system, experiments are conducted using the RePOPE benchmark to assess hallucination in vision-language understanding. Real-world indoor navigation experiments are also performed. The results show that integrating perception with language-based reasoning improves precision by up to 2.29% and consistently enhances F1-score compared to baseline VLM approaches. Real-world experiments further demonstrate reliable navigation performance, including multi-floor path planning and obstacle-aware guidance. Hence, the proposed system effectively enhances spatial understanding and reduces hallucination, providing a practical and scalable solution for assistive navigation. Full article

Unmanned Aerial Vehicle (UAV), particularly rotary-wing platforms such as quadcopters and octocopters, has evolved from controlled remote sensing platforms into autonomous agents capable of active task execution. This evolution from collect-then-analyze workflows to closed-loop perception, reasoning, and action signifies a paradigm shift toward Embodied AI, unlocking opportunities for the low-altitude economy. However, current research on UAV Embodied AI (UAV-EAI) often implicitly frames the field as a direct extension of indoor robotics or autonomous driving, which overlooks the fundamental distinctions of aerial agents. To bridge this gap, we introduce a comparative framework contrasting UAV-EAI with Indoor-EAI and Autonomous Driving Embodied AI (AD-EAI). By systematically decomposing the domain into nine key dimensions, we (i) analyze core tasks such as perception, localization, and exploration; (ii) review enabling infrastructure, including simulators and datasets; and (iii) categorize modeling methods ranging from physics-centric control to cognition-centric models. Our analysis demonstrates that the convergence of 6-DoF motion space, kilometer-scale unstructured environments, and stringent on-device constraints establishes a research regime qualitatively different from ground-based agents. These factors significantly impede the migration of existing VLM/LLM-based embodied systems for UAVs. Finally, we summarize open challenges and outline promising directions for the next generation of UAV-EAI. Full article

Traditional visual Simultaneous Localization and Mapping (SLAM) systems achieve high accuracy in static environments. However, in indoor dynamic scenes with frequent object motions, the presence of moving objects severely violates the scene rigidity assumption, often leading to significant performance degradation and tracking instability. To explicitly address this challenge, this paper introduces LIG-SLAM, a resource-efficient visual SLAM solution that extends the ORB-SLAM3 architecture. By incorporating dynamic object perception and geometric constraints, the system achieves robust localization in dynamic indoor environments, while its inference efficiency is significantly enhanced through targeted optimization. Specifically, a YOLOv5-based instance segmentation network is employed to obtain pixel-level segmentation of dynamic regions. To mitigate the erroneous rejection of static feature points, epipolar geometric constraints are incorporated to improve the accuracy of dynamic feature selection. Furthermore, a RANSAC-based depth consistency check is adopted to further enhance accuracy and alleviate the effects of epipolar degeneracy. Unlike conventional semantic SLAM frameworks, the proposed system incorporates ONNX-based optimization, thereby accelerating inference and improving real-time performance. Empirical evaluations conducted on TUM dynamic datasets indicate that the developed approach surpasses ORB-SLAM3 by a substantial margin, achieving a reduction of over 90% in terms of the Absolute Trajectory Error (ATE). Compared with existing semantic SLAM approaches, it achieves improvements in both accuracy and real-time performance, particularly in challenging indoor dynamic scenarios. Full article