High-resolution (<= 10 m) digital elevation models (DEMs) are essential for obtaining accurate terrain information and are integral to geographic analysis. However, a majority of currently available DEMs datasets possess a relatively coarse spatial resolution (>= 30 m), which limits the terrain features and details that can be accurately represented. Furthermore, due to the substantial production costs associated with high-resolution DEMs, these products are often unavailable or difficult to obtain in numerous countries and regions, particularly in less developed areas. Here, we introduced a novel method named the Spatial interpolation knowledge-constrained Conditional Generative Adversarial Network (SikCGAN). This method can generate high-resolution DEMs from publicly available data sources, specifically the photons collected by the Advanced Topographic Laser Altimeter System (ATLAS) carried by the Ice, Cloud and land Elevation Satellite-2 (ICESat-2). SikCGAN takes ICESat-2/ATLAS photons as the single data source and incorporates spatial interpolation knowledge constraints into a Conditional Generative Adversarial Network (CGAN) to generate DEMs at a 10-m spatial resolution. A case study conducted in boreal mountainous regions demonstrates SikCGAN's remarkable ability to produce highresolution and highly accurate DEMs, with an MAE of 22.09 m and RMSE of 29.25 m, which reduced error by 37 %-46 % compared to benchmark methods. Additionally, the results reveal that SikCGAN has remarkable resiliece to interference, including variations in spatial distance, terrain slope, and ATL03 photon count, this further elucidates and substantiates the effectiveness of SikCGAN. These findings demonstrate that SikCGAN provides innovative solutions for generating new high-resolution DEMs products and potentially supplementing existing ones to overcome their limitations.

Fringe projection profilometry (FPP) is a promising active optical three-dimensional (3D) measurement method in industrial scenarios. However, due to the limited dynamic range of a camera, achieving accurate 3D shape measurement of highly reflective surface is still a challenging task. In this paper, we design an ultrasonic atomization optimized measurement (UAOM) device to improve the reflectivity characteristics of objects with high reflectivity. The UAOM device sprays a microscopic water mist layer on the measured surface to weaken the impact of high reflection. In addition, the bidirectional reflection distribution function (BRDF) is combined with the phase error function for the analysis of the impact of the reflectivity characteristics. The relationship between the reflectance and the regional error sum is simulated, which is employed to establish evaluation indicators for the spraying parameter optimization. Finally, a data-driven spraying parameter optimization strategy is proposed to achieve high-precision 3D measurement. Experiment results demonstrate that the UAOM device achieves high dynamic range (HDR) measurement, with optimization effects better than those of other parameter settings. The proposed method further improves the accuracy and efficiency of 3D shape measurement while preserving the completeness of the point cloud. We believe that our method could be effectively applied to 3D measurement in industrial scenarios.

Partial point cloud registration is an essential and fundamental component of generating complete 3D shapes, aiming at converting partial scans into a unified coordinate system. However, existing point cloud registration methods suffer from inadequately rich local feature extraction and feature interaction. In addition, these methods still face challenges in modeling the global contextual information of point clouds sufficiently, which limits the improvement in registration effectiveness, especially for partial-to-partial point cloud registration with high noise. To overcome these issues, this paper proposes an enhanced PointNet and assignable weights transformer network (LFA-Net) for partial point cloud registration. The model achieves coarse-to-fine point cloud registration through three core modules. First, the Sufficient Local Feature Extraction Module (LFM) is constructed to extract various local feature information. Then, the Adequate Feature Aggregation Module (FAM) is designed to integrate the feature information from different point clouds. Finally, the Assignable Weights Transformer Module (ATM) is presented to stimulate the model’s global modeling ability during the registration process, enabling the selection of representative points for optimal point cloud registration. Extensive experiments conducted on ModelNet40 using partially overlapping point clouds illustrate the superior registration performance of LFA-Net compared with other state-of-the-art methods. Moreover, Numerous experiments on synthetic and real-word datasets further indicate that LFA-Net also has significant advantages in registering partial point clouds with noise and unseen categories, which demonstrates its excellent robustness and generalization ability for real-world practical application.

Rotor failures due to cracked blades are frequently observed in rotating machinery. The identification of cracking state of rotating blade based on vibration characteristics has garnered a lot of attention. However, nonlinear characteristics and vibration combining in radial, bending and torsional directions of a rotating blade induced by the crack breathing is yet not clear. This paper proposes a radial-bending-torsional dynamic model of rotating blade with breathing crack. A time-varying integration method is proposed for determining the crack state based on the strain energy release rate. The crack breathing behavior is described by Boolean operation and the numerical integration are applied to open or close the crack. The model is validated through modal analysis, vibration responses and contact state of crack surface. Frequency veering is changed between the 2nd flap and 1st edgewise frequency due to the existence of crack. Strong nonlinear behaviors are found in the radial and torsional vibrations because of the crack breathing. Nonlinearities are also found in the combined vibrations between the radial-bending and the bending-torsional directions. Radial and torsional vibration amplitude levels can be used as an indication of blade crack failure, but the applicability depends on the absolute response decided by the aerodynamic excitation and resonant vibration. These findings can serve as guidance in crack identification and cracking state monitoring of rotating blades.

The distributed measurement of low pressure utilizing common optical fibers without sensitization is desired but challenging in many industrial applications. In this paper, with the assistance of machine learning, the distributed measurement of low hydrostatic pressure is realized based on optical carrier-based microwave interferometry (OCMI) employing the common single-mode fiber (SMF). Firstly, the theoretical model of pressure sensitivity is established, and further investigated and validated by numerical simulation and finite element simulation. Subsequently, a distributed hydrostatic pressure measurement experiment is conducted utilizing a common SMF with cascaded weak light reflectors processed along the fiber core. The results indicate that it is difficult to measure low pressure through common fibers based on the traditional demodulation method. To overcome the above limitations, we propose to employ machine learning to analyze the microwave interference information, in order to achieve a one-to-one mapping with the hydrostatic pressure exerted on the sensing fiber. The implementation of distributed pressure measurement is based on the unique advantages of OCMI in terms of physical positioning and reconfigurable gauge length. Meanwhile, different microwave interferometric information is employed as inputs for comparison to select the most effective signals for optimal prediction. The results show that a satisfactory overall measurement and distributed measurement of low hydrostatic pressure can be achieved with the assistance of machine learning, where the accuracy of distributed measurement increases with the increase of Fabry-Perot interferometer (FPI) cavity length. The proposed strategy can be extended to other relatively short-distance spatially continuous distributed or long-distance quasi-distributed fiber sensing systems.

Gas-liquid two-phase flow is widespread in energy systems, and accurate measurement of its two-phase flow rate is vital to ensure process safety and improve efficiency. In this paper, a fiber-optic gas-liquid two-phase flow rate simultaneous sensing method based on optical carrier microwave interferometry (OCMI) is proposed. Since the gas-liquid two-phase flow has complex characteristics, the commonly used OCMI demodulation methods (including dip frequency tracking and phase demodulation methods) face challenges in measuring the two-phase flow rates simultaneously. Therefore, an artificial neural network (ANN) based demodulation method is developed. The impact of different inputs to the ANN model on the prediction results is investigated, where utilizing the amplitudes of the spatiotemporal reflection peaks as the input achieves the optimal performance. The experimental results of the 5-fold cross-validation demonstrate that the proposed method achieves gas flow rate prediction with a mean absolute error (MAE) of 0.94 f 0.15 m3/h and a mean absolute percentage error (MAPE) of 3.91 f 0.51 %, while the MAE and MAPE for predicting liquid flow rate are 0.13 f 0.04 m3/h and 4.87 f 0.61 %, respectively. In conclusion, the proposed fiber-optic gas-liquid two-phase flow rate sensing method based on OCMI and ANN provides new insights for the measurement and characteristic analysis of complex flows.

Accurate obstacle identification is essential for railway safety. Existing deep-learning-based railway obstacle detection methods rely on large training datasets, which are costly, time-consuming, and labor-intensive. Fewshot object detection (FSOD) addresses this issue by learning from limited data. However, current FSOD methods encounter challenges in precisely detecting multi-scale obstacles in real-world railway environments. Furthermore, ensuring robustness in complex and dynamic railway scenarios remains a significant hurdle. To address these issues, we present a few-shot multi-scale railway obstacle detection method via lightweight linear transformer and precise feature reweighting. The developed network consists of three modules. First, the Dual Branch and Accuracy Multi-scale Feature Extraction Module (DBM) uses a lightweight linear transformer and enhanced feature pyramid network to capture abundant global contextual information across different scales, particularly improving feature extraction quality for small obstacles. Then, the Robust and Well-directed Feature Reweighting Module (RWM) leverages meta-knowledge from support images to generate category-specific reweighting vectors, dynamically emphasizing key features for each obstacle class and improving detection accuracy. Finally, the Enhanced Few-shot Obstacle Prediction Module (EPM) redefines anchor boxes based on the railway obstacle dataset and introduces a novel loss function to increase the contribution of positive samples while suppressing hard-negative samples, thus enhancing detection robustness. Experimental results show that our model achieves optimal performance for railway obstacle detection under varying shot conditions. The mAP of LR-Net reaches 82.0% with 30 shots, providing a significant advantage over other widely used FSOD methods. Additionally, experiments on PASCAL VOC further demonstrate that LR-Net is robust enough to detect objects more effectively than existing FSOD models. Therefore, LR-Net holds great potential for real-world railway obstacle detection and other complex multi-target detection tasks.

Fringe projection profilometry (FPP) has become one of the most powerful techniques for three-dimensional (3D) non-contact measurement. However, in practical scenarios, the various reflectivity of the unknown measured objects often greatly makes the system unable to achieve the theoretical precision under the same system parameter settings. Therefore, the adaptively system parameter setting is essential to be developed. In this paper, we propose a novel metric model, i.e. the accuracy quality function, for initial accuracy evaluation using in-situ acquired images under the current parameter settings. The causes that potentially affects the ultimate accuracy are analyzed via theoretical derivation and further adopted within the evaluation model. In addition, an optimal exposure selection method based just two images is carried out to fast adjusting. Experimental results demonstrated that the proposed accuracy quality model aligns well with the actual condition. Under optimal exposure, it achieved a significant reduction in phase error by 36.15% and by 21.39% in low- and high- exposure, highlighting its strong performance and potential for high-accuracy and in-situ 3D shape measurement applications.

Overloaded truck transportation poses a significant threat to road safety. However, mainstream methods for overloaded truck identification suffer from low efficiency, limited monitoring range, and high costs, posing obstacles to curbing overloaded transportation. To tackle these challenges, this study proposes a novel approach called a multiaspect overloaded truck identification network (MAOTIN), which achieves accurate identification by analyzing truck trajectory data comprehensively. MAOTIN comprises three efficient and specific modules: an overloaded feature identification module (OFIM), a trajectory similarity identification module (TSIM), and a decision fusion module (DFM). Initially, the trajectory representation method was designed to transform the multidimensional spatiotemporal truck trajectory data into images, aggregating overload features while reducing dimensionality. Subsequently, the OFIM and TSIM are developed to comprehensively identify overloaded behavior from typical overloaded features and overloaded trajectories similarity features. Finally, the DFM adaptively and fully fuses feature images of different properties to obtain the ultimate identification result. To evaluate the performance of MAOTIN, this study conducted experiments on the constructed overloaded truck dataset. The results indicated that the model achieves an accuracy of 96.4% and 316 FPS, surpassing mainstream image classification networks. Moreover, MAOTIN performed a precision of 97.3% on practical application testing and assisted traffic police in apprehending 7591 overloaded trucks in one quarter, demonstrating its high practical value. Hence, MAOTIN enables accurate, rapid, and comprehensive identification of overloaded trucks and can be effectively applied to the overloaded identification tasks in urban traffic management.

Unmanned aerial vehicle (UAV) laser scanning (ULS) and backpack laser scanning (BLS) are two commonly employed technologies in precision forestry. However, data acquired by these two types of light detection and ranging (LiDAR) are distinct, with one capturing point clouds beneath the canopy and the other above. Consequently, there is minimal overlap in the point clouds collected by both methods, especially in dense forests, presenting significant challenges for data registration. Furthermore, many trees in forests (particularly broadleaf trees) have the tree tops and trunk centers not aligned vertically, which greatly increases the difficulty of the data registration methods based on tree position. To solve the above-mentioned problems, we here propose a novel and robust method to register ULS and BLS point clouds in forested areas. Our method consists of three key steps, that is, tree location extraction, quadrant search-based minimum spanning tree (MST) matching, and registration. The quadrant searching strategy dynamically searches for potential candidates in four quadrants centered on the initial tree locations. By constructing MSTs for the potential tree locations, triangle constraints require only four topologically similar tree locations to find one-to-one correspondences during the stepwise MST matching process. The proposed method was evaluated in five urban forest sample plots and one natural forest sample plot located in China, covering both coniferous and broadleaf forests. The results show that our method obtained good registration results on all six sample plots, with an averaged rotation error, translation error, pointwise error, and root-mean-square error (RMSE) of 0.012 rad, 0.354, 0.378, and 0.379 m, respectively. Comparative studies indicate that our method outperformed existing registration methods, demonstrating its effectiveness and robustness. Our method allows for the creation of a more complete picture of forest vertical structure and holds great potential for informing sustainable forest management practices and supporting critical ecological assessments.

Distance measurement technology is of great significance to scientific research and industrial production. As an emerging technology, optical-carried microwave scanning interferometry (OCMSI) technology has been applied in the field of high-precision distance measurement. However, OCMSI ranging often requires the aid of the vector network analyzers (VNAs), which limit the instrumentation and modularization of the OCMSI ranging system. To overcome this, the OCMSI amplitude spectrum detection and calculation technology is proposed in this article. First, a miniaturized real-time amplitude detection unit (ADU) is designed to demodulate the amplitude of the optical-carried microwave interference signal efficiently. The amplitude of this signal is converted into the amplitude spectrum containing distance information. Furthermore, the multisegment synthetic Fourier series fitting (MSFSF) algorithm is proposed to achieve the high accurate and repeatable distance calculation. In the 10 m range, experiments of measurements for various distances are promoted, the ranging accuracy is +/- 0.052 mm and the repeatability is 0.019 mm. These two indexes for the OCMSI ranging results are essentially in the same order of magnitude as using VNA. The experiment shows that the proposed OCMSI ranging method is of great significance to the related technologies promotion in practical applications.

The profound impact of light pollution on both natural and human systems is well-recognized. Particularly, light pollution at the building scale is inextricably intertwined with human living and has garnered increasing attention in recent years. However, the coarse spatial resolution of nighttime light data, coupled with the inadequacy of existing methods, have precluded detailed investigation into the light pollution at building scale. The high-resolution Glimmer Imager (GLI) sensor onboard the SDGSAT-1 satellite provides nighttime light data with a 40-meter resolution, offering new opportunities for precise assessment of light pollution at the building scale. To this end, this study introduces a novel approach for calculating light exposure at the building floor-level using SDGSAT-1 GLI data. Two measures, Floor Light Exposure Index (FLEI) and Building Light Exposure Index (BLEI), are proposed to quantify the cumulative nighttime light radiation received at each floor and building, respectively, thereby facilitating the analysis of variances in light exposure across different buildings and floors. Utilizing this approach, we computed the floor-level light exposure for 57,221 buildings within three core districts-Yuexiu, Haizhu, and Tianhe-of Guangzhou city, China. The results, perhaps for the first time, quantified the level of light exposure at the building scale, revealing substantial differences in light exposure both interbuilding and intra-building across various floors. Comparative analysis with field-collected data confirmed the robustness of our method and the reliability of the calculation results. We found that the light exposure is generally lower on lower floors, with a significant increase in light exposure above the 50th floor. Buildings in proximity to light sources and roads are more susceptible to light pollution, with light exposure in residential areas intensifying from the center to the periphery, and light exposure in commercial outskirts decreasing with increasing distance from the commercial center. The average FLEI in commercial zones is approximately 550 nW cm-2 sr-1 higher than that in residential areas. The approach and resultant building floor-level light exposure map generated by this study hold substantial promise in aiding the evaluation of various targets and indicators associated with multiple Sustainable Development Goals (SDGs) targets and indicators, including SDG 3 (Good Health and Well-being), SDG 11 (Sustainable Cities and Communities), and SDG 13 (Climate Action).

Hydrostatic pressure measurement is essential in many industries, such as oil and gas production, chemical processing, and environmental monitoring. Due to the minimal impact of small hydrostatic pressure on ordinary silica optical fibers, research on its measurement utilizing optical fiber sensing technology remains limited. In this article, a novel microwave photonics technique, termed optical carrier-based microwave interferometry (OCMI), is utilized for small hydrostatic pressure sensing with the assistance of a convolutional neural network (CNN). The theory of OCMI-based phase demodulation is established, and numerical simulations are conducted to investigate the factors affecting the axial displacement of the fiber core. In practical experiments, the phase demodulation method is applied to small hydrostatic pressure measurements; however, the results are suboptimal. Therefore, the CNN is developed to assist in the implementation of accurate small hydrostatic pressure sensing. The small hydrostatic pressures predicted by the well-trained CNN model are in good agreement with the actual values, with an error of less than 0.25 kPa. In addition, the prediction results from multiple Fabry-Perot interferometers (FPIs) demonstrate the feasibility and effectiveness of utilizing CNN for OCMI-based small hydrostatic pressure sensing. The introduction of machine learning broadens the application scope of the OCMI technique, allowing it to be employed for distributed sensing of a wider range of physical, chemical, and biological quantities.

We propose a technique to achieve high-speed and high-precision distance measurement via phase demodulation of broadband optical carrier-based microwave interferometry (OCMI). An in-phase and quadrature (I/Q) processing scheme is designed and incorporated to measure the phase shift induced by target distance. The results could be efficiently derived from a minimum of one pair of detected outputs with immunity to power fluctuations. To extend the non-ambiguous measurement range while maintaining high resolution, a multifrequency-based phase unwrapping procedure is implemented. In the meantime, a driving module is utilized to effectively amplify and stabilize the signal. Experiments were carried out to evaluate the feasibility and performance of the proposed OCMI distance measurement method, which exhibits good accuracy, stability, and reliability. The maximum residual error is found to be 0.084 mm and the relative error is less than 2 x 10(-4). Moreover, the method is capable to perform thousands of measurements within a few seconds, thus the OCMI-based dynamic target tracking has been achieved.

To investigate the characterization of the blade-coating contact force, this paper established a dissipative contact force model considering plastic deformation based on the principles of energy conservation and momentum conservation. First, the generality of the contact force model for the blade-coating rub-impact system was analyzed. Next, the contact force model was derived by the one-dimensional direct central impact between two spheres, which was divided into the following two phases: compression and restitution. The contact force from the established model and classic contact force model were compared with the sphere-impact experimental results to demonstrate its validity and accuracy. Finally, the proposed model was adapted to deal with the rub-impact problem. Applicability and accuracy were verified by comparing the experimental rub-impact force data. The coating’s plastic deformation can be well simulated by using this model. The calculated rub-impact force is feasible in blade-coating rub-impact fault to guide blade design and coating selection.

Optical carrier-based microwave interferometry (OCMI) has been widely concerned and studied due to its unique advantages in combining the strengths of optics and microwave. This paper theoretically and experimentally investigates the OCMI-based distributed measurement of temperature. The distributed temperature measurement is demonstrated experimentally using a single-mode fiber (SMF) with cascading weak optical reflectors inscribed along the fiber core, where any two reflectors are paired to define an intrinsic Fabry-Perot interferometer (IFPI). Spatially continuous distributed temperature demodulation is achieved by reconstructing the microwave interferogram of the IFPIs consisting of two adjacent reflectors. IFPIs with different cavity lengths consisting of two non-adjacent reflectors are also demodulated to study the temperature sensitivity at different spatial resolutions. Experimental results show that the IFPIs along the sensing fiber have a linear response to the temperature, especially the IFPI with the 30cm cavity length exhibits a better linear response, reversibility and stability in the temperature range of 35°C-75°C. Comparing with the experimental and theoretical values, this paper further theoretically investigates the effect of fiber coating layer on the temperature sensitivity of the sensing system, taking into account the physical and geometric properties of the fiber outer coating layer. In addition, a dual-path distributed temperature measurement based on spatial division multiplexing is demonstrated, validating the excellent multiplexing ability and application potential of the OCMI-based multi-path distributed measurement.

The pursuit of precise and efficient 3D shape measurement has long been a focal point within the fringe projection profilometry (FPP) domain. However, achieving precise 3D reconstruction for isolated objects from a single fringe image remains a challenging task in the field. In this paper, a deep learning -based frequencymultiplexing (FM) composite -fringe projection profilometry (DFCP) is proposed, where an end -to -end absolute phase retrieval network (APR -Net) is trained to directly recover the absolute phase map from a FM composite fringe pattern. The obtained absolute phase map exhibits exceptional precision and is devoid of spectrum crosstalk or leakage disturbance typically encountered in traditional FM techniques. APR -Net is intricately crafted, incorporating a nested strategy along with the concept of centralized information interaction. A diverse dataset encompassing various scenarios and free from spectrum aliasing is assembled to guide the training process. A seven -map loss calculation scheme is employed to guide the training process, of which the efficacy is proved through ablation experiments. In the first qualitative experiment, DFCP demonstrates comparable phase accuracy to ground truths with 47 fewer projected images, outperforming other three methods with mean absolute phase errors of 0.0052 rad, 0.1761 rad, 0.0169 rad, and 0.0139 rad. The second qualitative experiment and the quantitative evaluation respectively prove DFCP ' s capability in high dynamic range 3D measurement and in precise 3D measurement, with sphere diameter errors of 0.0780 mm and 0.0726 mm, and a spherical centroid distance error of 0.0555 mm.

The incursion of railway obstacles poses a serious risk to train operations, and numerous accidents occur during train shunting. However, existing algorithms still struggle with finding a compromise between detection accuracy and speed during train movement. Moreover, their accuracy and robustness are inadequate, specifically when handling small objects in complicated railway scenarios. To overcome these issues, this article proposes an efficient network using convolution and transformer (AE-Net) for performing accurate and real-time detection of railway obstacles to ensure driving safety. First, the enhanced and lightweight transformer module (ETM) is constructed to strengthen the model's global modeling ability. Then, the lightweight feature integration module (LIM) is presented to integrate multibranch feature information and reduce model complexity. Finally, the reinforced multiscale feature fusion module (RFM) is utilized to enhance the multiscale object detection capability, especially for small obstacles. The presented algorithm realizes 95.29% mAP and 145 frames/s on the railway dataset, which is superior to YOLOv5s. In addition, the experiment on MS COCO further shows that AE-Net can perform a considerably better detection than current state-of-the-art models. Hence, it is practicable to employ AE-Net in actual railway and further more complex multitarget scenarios.

High-precision and efficient 3D shape measurement is a long-pursued objective in fringe projection profilometry (FPP) domain. Frequency multiplexing (FM) is a prevailing solution given its relatively small number of projection patterns, but suffers from spectrum aliasing problem. In this paper, a novel deep learning-enabled frequency-multiplexing composite fringe projection profilometry (DFCP) is proposed, where an end-to-end absolute phase retrieval network (APRF-Net) is trained to recover the absolute phase map directly from a FM composite fringe pattern, with high precision and without any spectrum crosstalk or leakage disturbance. A seven-map loss calculation scheme is adopted to instruct training process and its effectiveness is proved by ablation experiments. Qualitative and quantitative experiments validate the superiority of DFCP to other four methods and its promising prospects in industrial measurement field.

Cost-efficient multi-objective synchronous ranging solutions are highly desired in many fields such as manufacturing and infrastructure. However, traditional laser ranging methods have limitations in absolute ranging and multi-channel expansion. In this paper, a multi-channel absolute distance measurement method based on optical carrier-based microwave scanning interferometry (OCMSI) is proposed. After microwave scanning and synchronous demodulation, the amplitude spectrums and phase spectrums of interference signals are established. The transmission signals of each channel can be separated and reconstructed by using the discrete Fourier inverse transform. Additionally, it is demonstrated that the designed global optimization algorithm for extracting free spectral range can effectively reduce the impact of detection errors and channel interference. Existing interferometers can achieve multi-channel parallel absolute distance measurement without the need for additional modulation, demodulation, and optoelectronic detection devices. Experimental results have shown that the system structure is simple, and the ranging accuracy of for 3 channels is higher than ± 60 μm within at least 35 m optical path.