Sensors最新文献

Detecting small insulator defects in unmanned aerial vehicle (UAV) imagery remains challenging due to low resolution, complex backgrounds and scale variation, which degrade the performance of existing detectors. This study aims to develop a highly efficient and accurate model for real-time insulator defect inspection on resource-constrained UAV platforms. This paper proposes POLD-YOLO, a novel lightweight object detector based on YOLO11. The key innovations include: (1) A backbone enhanced by a PoolingFormer module and Channel-wise Gated Linear Units (CGLUs) to boost feature extraction efficiency; (2) An Omni-Dimensional Adaptive Downsampling (OD-ADown) module for multi-scale feature extraction with low complexity; (3) A Lightweight Shared Convolutional Detection Head (LSCD-Head) to minimize the number of parameters; (4) A Focaler-MPDIoU loss function to improve bounding box regression. Extensive experiments conducted on a self-built UAV insulator defect dataset show that POLD-YOLO achieves a state-of-the-art mAP@0.5 of 92.4%, outperforming YOLOv5n, YOLOv8n, YOLOv10n, and YOLO11n by 3.6%, 1.6%, 1.4%, and 1.6%, respectively. Notably, it attains this superior accuracy with only 1.55 million parameters and 3.8 GFLOPs. POLD-YOLO establishes a new Pareto front for accuracy-efficiency for onboard defect detection. It demonstrates great potential for automated power line inspection and can be extended to other real-time aerial vision tasks.

Electrical impedance tomography (EIT) provides noninvasive, high-temporal-resolution imaging for medical and industrial applications. However, accurate image reconstruction remains challenging due to the severe ill-posedness and nonlinearity of the inverse problem, as well as the limited robustness of existing single-source learning-based methods in real measurement scenarios. To address these limitations, a data-constrained and physics-guided Multi-Source Conditional Diffusion Model (MS-CDM) is proposed for EIT image reconstruction. Unlike conventional conditional diffusion methods that rely on a single measurement or an image prior, MS-CDM utilizes boundary voltage measurements as data-driven constraints and incorporates coarse reconstructions as physics-guided structural priors. This multi-source conditioning strategy provides complementary guidance during the reverse diffusion process, enabling balanced recovery of fine boundary details and global topological consistency. To support this framework, a Hybrid Swin-Mamba Denoising U-Net is developed, combining hierarchical window-based self-attention for local spatial modeling with bidirectional state-space modeling for efficient global dependency capture. Extensive experiments on simulated datasets and three real EIT experimental platforms demonstrate that MS-CDM consistently outperforms state-of-the-art numerical, supervised, and diffusion-based methods in terms of reconstruction accuracy, structural consistency, and noise robustness. Moreover, the proposed model exhibits robust cross-system applicability without system-specific retraining under multi-protocol training, highlighting its practical applicability in diverse real-world EIT scenarios.

Oxygen permeability (Dk) is a key parameter for evaluating the ability of contact lenses to supply oxygen to the cornea. Although the polarographic method has been standardized as a reference technique for Dk measurement, conventional polarographic electrode cells are limited to a narrow central measurement area of approximately 4 mm in diameter, which may not adequately represent oxygen transport under actual wearing conditions. In this study, a modified polarographic electrode cell enabling wide-field oxygen permeability measurement over an expanded central area with a diameter of 11 mm was developed and evaluated under ISO 18369 measurement conditions. The performance of the proposed system was evaluated by comparing its accuracy, repeatability, and relative error with those of a conventional polarographic electrode cell using plano hydrogel contact lens samples with different uniform thicknesses. The Dk values obtained using the modified measurement cell did not show a statistically significant difference compared to those measured with the conventional measurement cell (t = 2.682, p = 0.055), and the relative error between the two systems was 1.93%, meeting the ISO acceptance criteria for the development of a new testing method. These results demonstrate that wide-field Dk measurement can be achieved without compromising reliability, providing a more representative and ISO-compliant approach for contact lens oxygen permeability evaluation.

Cancer is one of the global health problems that affects millions of people every year. Biopsies are among the standard methods for detecting and confirming a cancer diagnosis. Performing this study manually poses several challenges due to tissue movement and the difficulty of precisely locating the target, as is often the case in lung biopsies. This study presents the design and implementation of an autonomous image processing algorithm included in a closed-loop controller that drives the activity of a multi-degree-of-freedom (six) robotic manipulator that performs emulated tissue biopsies. A realistic lung motion emulator, based on a two-degree-of-freedom robotic device with a photon emitter (to simulate radiopharmaceutical identification of cancerous tissue), was used to test the proposed automatic biopsy collector. Applying image processing to detect cancer tissue enables the identification of the centroid and tumor boundaries. Using the detected centroid coordinates, the reference trajectory of the end effector (biopsy needle) was automatically determined. A finite-time convergent controller was implemented to guide the robotic manipulator's motion towards the tumor position within a specified time window. The controller was evaluated using a digital twin representation of the entire robotic system and using an experimental device working on the simulated mobile tumor emulator. Evaluation of simulated tumor detection and reference trajectory tracking effectiveness was used to validate the operation of the proposed automatic robotic lung biopsy sampler. The application of the controller allows one to track the position of the emulated tumor with a deviation of 0.52 mm and a settling time of less than 1 s.

Most falls occur while walking, making gait quality a logical therapeutic target. Many temporo-spatial variables have been implicated in increased fall risk, but these are dependent upon kinematic parameters of the joints involved in the gait cycle. The widespread availability of wearable sensors has made the acquisition of kinematic data feasible, and those related to the ankle are most relevant, as they relate most closely to causes of falls, trips, slips, and mis-steps. The purpose of this study is to estimate the extent to which measures of ankle angular velocity (AV) during walking are associated with falls. This is a comparative study of ankle AV metrics between people who have or have not experienced a fall in the past year. Data came from experimental use of the Heel2Toe™ sensor in a variety of settings, including demonstrations and clinical research studies. The sample comprised 387 participants, of whom 68 (17.6%) self-reported falling in the past year. Logistic regression with a natural cubic spline with 3 degrees of freedom identified AV of the angle at heel strike to discriminate between fallers and non-fallers, and the regression parameters were used to propose an algorithm to estimate fall risk. Applying the algorithm to the existing data yielded a range of probabilities from 0.0480 to 0.7245 depending on age of the person assessed. Further testing of this algorithm in different samples is warranted.

For Autonomous Vehicles (AVs), recognizing traffic lights and signs is critical for safety because perception errors directly affect navigation decisions. Real-world disturbances such as glare, rain, dirt, and graffiti, as well as digital adversarial attacks, can lead to dangerous misclassifications. Current research lacks (i) temporal continuity (stable detection across consecutive frames to prevent flickering misclassifications), (ii) multi-field-of-view (FoV) sensing, and (iii) integrated defenses against both digital and natural degradation. This paper presents two principal contributions: (1) a three-layer defense framework integrating feature squeezing, inference-time temperature scaling (softmax τ = 3 without distillation training), and entropy-based anomaly detection with sequence-level temporal voting; (2) a 500 sequence dual-FoV benchmark (30k base frames, 150k with perturbations) from aiMotive, Waymo, Udacity, and Texas sources across four operational design domains. The unified defense stack achieves 79.8% mAP on a 100-sequence test set (6k base frames, 30k with perturbations), reducing attack success rate from 37.4% to 18.2% (51% reduction) and high-risk misclassifications by 32%. Cross-FoV validation and temporal voting enhance stability under lighting changes (+3.5% mAP) and occlusions (+2.7% mAP). Defense improvements (+9.5-9.6% mAP) remain consistent across native 3D (aiMotive, Waymo) and projected 2D (Udacity, Texas) annotations. Preliminary recapture experiments (n = 15 scenarios) show 2.5% synthetic-physical ASR gap (p = 0.18), though larger validation is needed. Code, models, and dataset reconstruction tools are publicly available.

The flexible foam piezoresistive sensor demonstrates significant potential for wearable strain-sensing applications due to its substantial deformation capacity, excellent flexibility, and cost effectiveness. However, conventional flexible foam piezoresistive sensors often struggle to simultaneously achieve high sensitivity, a wide pressure detection range, fast response and long-term stability. This paper employed a glucose-based sugar-templating method to fabricate a fine-pore (50 μm) foam structure complemented by a dual-filler strategy to enhance overall performance. A robust porous conductive network was constructed by embedding zinc oxide (ZnO) and multi-walled carbon nanotubes (MWCNTs) into a polydimethylsiloxane (PDMS) matrix. The resulting sensor exhibits outstanding piezoresistive properties, featuring a wide linear detection range (0-80% strain) and a high sensitivity of 9.02 kPa^-1 within the 0-10 kPa pressure range. It demonstrates rapid response/recovery times of 50/70 ms and maintains stable output performance even after 5000 compression cycles at 300 kPa. The sensor also exhibits negligible environmental interference and excellent long-term stability. When attached to finger joints, feet soles, or the throat, the sensor enables functions such as finger bending recognition, race-walking violation discrimination, gait analysis, and vocal fold vibration recognition, thereby demonstrating its considerable potential for application in human-computer interaction and human motion detection.

The development of bistatic noise radars is a promising contemporary direction in the field of radar technology. Two novel approaches are proposed in this study as further development of existing methods for their design. The first approach involves using a quantum-generated random number sequence for phase manipulation control, which is practically infinite in duration. This ensures additional electronic protection of the radar, since the phase manipulation control code will not repeat regardless of the duration of its operation. The second approach is related to the introduction of synchronized emissions from both antennas in a manner ensuring equality or controlled difference of their signals upon arrival at a predetermined point in space. This enables the formation of a controlled electromagnetic field. As a result, received-signal processing capabilities are improved, while additional electronic "stealth" is achieved by creating a fictitious electromagnetic center of the radar's resultant radiation (i.e., an effective RF phase center of the resultant emission) and complicating the determination of antenna locations. A block diagram and general algorithm for information processing of a bistatic radar with quantum-generated noise phase manipulation and non-directional antennas are proposed in this study.

Aboveground biomass (AGB) is a key indicator of vegetation productivity and terrestrial carbon stocks; therefore, robust AGB estimation is critical for assessing ecosystem services and carbon cycle research. Previous studies have largely focused on forest and cropland ecosystems. In contrast, roadside vegetation along highways and other linear transport corridors remains comparatively underexplored despite its potentially important role as a carbon sink. Here, we integrate field-measured AGB samples with GF-2 high-resolution satellite imagery to evaluate the suitability of multiple remote-sensing predictors and machine-learning algorithms for estimating AGB in highway roadside vegetation. Six remote-sensing variables were used as predictors, including four vegetation indices (Normalized Difference Vegetation Index (NDVI), Perpendicular Vegetation Index (PVI), Enhanced Vegetation Index (EVI), and Modified Soil-Adjusted Vegetation Index (MSAVI) and two-band ratios (B342 and B12/34). Five regression models-multiple linear regression (MLR), partial least squares regression (PLSR), random forest (RF), support vector regression (SVR), and extreme gradient boosting (XGBoost)-were developed and systematically compared under both single-variable and multi-variable scenarios. Model performance was evaluated using five-fold cross-validation, with the coefficient of determination (R²) and the root mean square error (RMSE) as metrics of evaluation. The results indicate that the RF model under the multi-variable scenario achieved the best overall performance, with a training R² of 0.83 and a testing RMSE of 0.84 kg·m^-2, substantially outperforming the other linear and non-linear models. The optimal RF model was further applied to GF-2 imagery to produce a spatially explicit AGB map for a 32 km highway segment and a 30 m roadside buffer on both sides, yielding an estimated total aboveground biomass of 566.97 t for the corridor. These findings demonstrate that combining high-resolution remote sensing with machine-learning approaches can effectively improve AGB estimation for linear roadside vegetation systems, providing technical support for ecological monitoring, roadside greening management, and carbon accounting for transport infrastructure.

Cross-domain data collaboration is a core requirement for the intelligent development of critical areas such as the Internet of Vehicles and intelligent transportation systems. In this scenario, vehicles and various sensors deployed roadside continuously generate massive amounts of time-series data, yet this data often forms "data silos" due to privacy regulations and a lack of trust between collaborating entities. Existing integrated schemes combining "Federated Learning + Blockchain" have achieved a certain degree of process traceability and automated payments, but risks of gradient-level privacy leakage persist, and inflexible and delayed incentive mechanisms result in low participation quality. To systematically address these bottlenecks, this paper proposes the Federated Learning with Assured Privacy and Reputation-Driven Incentives (FLARE) architecture, whose core innovation lies in the native integration of cryptographic security and mechanism design theory. It includes the Secure and Faithfully Executed Gradient aggregation (SafeGrad) protocol, which integrates partial homomorphic encryption and zero-knowledge proofs to provide verifiable privacy guarantees for gradient contributions while enabling efficient secure aggregation, defending against inversion attacks at the source; alongside this, it includes the Economy-on-Chain incentive (EconChain) mechanism, which designs an on-chain economic system based on blockchain, achieving precise measurement and sustainable incentivization of training process contributions through fine-grained instant micro-rewards and a dynamic reputation model. Experiments show that, compared to baseline schemes, FLARE can effectively enhance node participation enthusiasm and contribution quality without compromising model accuracy, providing a new paradigm with both strong security and high vitality for the trusted and efficient circulation of data.