Accurate Coordinates Research Articles

Comparative Analysis of Higher‐Order Ionospheric Delay on PPP Long‐Term Coordinate Time Series and Residual Modeling Using Horizontal Gradients and RINEX Data

AbstractHigher‐order ionospheric corrections, including second‐ and third‐order effects and signal bending, are essential for improving Global Navigation Satellite System (GNSS) time series accuracy. However, their influence on long‐term Precise Point Positioning (PPP) time series, particularly signal bending, remains underexplored. Most studies rely on Global Ionosphere Maps (GIMs) for second‐order delay corrections due to the complexity of RINEX‐based inversions. Analyzing data from 37 International GNSS Service stations (2009–2020), we found that higher‐order ionospheric effects predominantly impact the North component of mid‐ and low‐latitude stations. Second‐ and third‐order delays contribute 50% and 20% to annual and semi‐annual amplitudes, respectively, while signal bending accounts for 5% and 2%. Additionally, signals traveling along the magnetic field direction induce phase delays, with equatorial regions experiencing more frequent and intense ionospheric activity. This leads to maximum horizontal velocity impacts of 0.45 mm/yr at the equator and a distinct southern trend at mid‐ and low‐latitudes. GIM‐based corrections increase seasonal signal amplitudes and root mean square error (RMSE) at some stations due to discrepancies with RINEX‐based corrections, which generate higher‐order ionospheric residuals. These residuals contribute 48.6% of the RMSE in RINEX‐based corrections, surpassing the 39.8% from second‐ and third‐order delays. To address this, we propose a GIM‐based residual model incorporating horizontal gradients, reducing RMSE by 48%, 26%, and 52% for the East, North, and Up components, respectively. Monthly or quarterly gradient updates during quiet ionospheric periods ensure precise corrections, enhancing GNSS time series and coordinate system accuracy.

Impact of different range bias corrections on orbit and Earth rotation parameters determination using BDS-3 satellite laser ranging observations

Abstract Satellite laser ranging (SLR) is an important technique that determines geodetic parameters, and its observation processing often calibrates range bias corrections to offset systematic errors. However, the impact of different range bias calibration methods on estimating the BDS-3 satellite orbit and Earth Rotation Parameters (ERP) has not been fully studied. The aim of this study is to explore the impact of employing different SLR range bias corrections on the accuracy of SLR-based BDS-3 satellite orbit and ERP. Eight months of experimental analysis revealed that the station–satellite-pair-dependent range bias correction resulted in the optimal orbit accuracy. Regarding orbit differences relative to precise ephemerides and overlap differences, the 3D root-mean-square (RMS) of satellites manufactured by the China Academy of Space Technology (CAST) are 1.00 and 0.94 m, respectively. The corresponding values of satellites manufactured by the Shanghai Engineering Center for Microsatellites (SECM) are 0.98 and 0.90 m, respectively. The station–satellite-pair-dependent range bias correction performed the best in terms of pole coordinate accuracy. The RMS of the X P and Y P differences relative to the International Earth Rotation and Reference Systems Service (IERS) 20 C04 product are 1.32 and 1.41 mas, respectively. The solution using satellite-dependent range bias corrections has the optimal length of day (LOD) accuracy, with a 44.92 μs rms of the LOD difference. However, due to the apparent satellite-related error characteristic reflected in the SLR residual, the station-dependent range bias correction is unsuitable for simultaneously processing the SLR observations of all BDS-3 satellites.

An automatic detection method for cervical liquid‐based cells based on improved Yolov5s network

AbstractTo address the significant challenges of high false positive and false negative rates in existing algorithms for detecting cervical fluid‐based cells, an enhanced Yolov5s network is introduced. This paper details a novel approach that dynamically adjusts the weights of channels and the spatial attention in modules, substantially improving feature extraction from small objects and boosting the detection capabilities of the network. Furthermore, Mixup data augmentation technology is incorporated to counter the issue of imbalanced data categories in the custom dataset. The Complete Intersection over Union loss function is also employed to refine coordinate localization accuracy during training. Tested on the proprietary cervical cytology dataset, the modified Yolov5s achieves a mean Average Precision of 92.1%, surpassing the previous state‐of‐the‐art by 5.6%. This enhancement substantiates the efficacy of the proposed model. Code and models are accessible at https://github.com/youyi888/yolov5_CPCA.

Systematic Literature Review: Health Technology in Nursing

Digital health technologies such as telehealth, electronic health records (EHR), and artificial intelligence (AI) have transformed nursing by enhancing patient care, improving workflow efficiency, and expanding healthcare accessibility. This systematic literature review examines the current role of these technologies in nursing practice, focusing on their impact on patient outcomes, workflow optimization, and accessibility of healthcare services. Findings indicate that telehealth increases healthcare access for underserved populations, EHRs improve care coordination and documentation accuracy, and AI supports predictive care and clinical decision-making. However, challenges such as data security, usability, and ethical considerations remain. Addressing these issues through training, system improvements, and ethical guidelines is essential for optimizing the benefits of digital health technologies in nursing. This review provides insights for healthcare providers and policymakers, emphasizing the importance of technology integration and support in advancing nursing practices.

An Improved Low-Cost Dual-Antenna GNSS Dynamic Attitude Determination Method in Complex Environments

GNSS attitude determination has been widely adopted due to its high efficiency, absence of cumulative errors, and ease of installation. However, practical navigation and attitude determination systems often rely on low-cost receivers that struggle with substantial multipath effects, frequent cycle slips, and satellite signal loss, significantly impairing attitude determination accuracy in challenging urban environments. To address this issue, this contribution proposes a constrained dynamic prediction model (C-Dynamics), which enables more accurate initial coordinates and thereby increases the effectiveness of the constrained LAMBDA (CLAMBDA) technique. To evaluate the practical performance of C-Dynamics, two sets of real-world data collected from a vehicle platform were analyzed. The results demonstrate that C-Dynamics significantly enhances the accuracy of initial coordinate estimations across various environments. Compared with the lambda method, the CLAMBDA method + C-Dynamics method (CLAMBDA+CD) improves the fixing rate in the urban environment by 5.6%, and the accuracy of the heading angle, pitch angle, and baseline length improved by 66%, 70.9%, and 84.2%, respectively. Moreover, in challenging high obstruction environments, the fixing rate increased by 43.5%, while the accuracy of heading angle, pitch angle, and baseline length improved by 76.4%, 69.2%, and 94%, respectively. The proposed algorithm effectively addresses the low fixing rate and insufficient accuracy of the LAMBDA method in high obstruction environments and holds practical value for widespread adoption in the mass market.

Error analysis and accuracy evaluation method for coordinate measurement in transformed coordinate system

Multiple coordinate system transformations are required for engineering measurements of multi-faceted components. Traditional engineering measurements neglect coordinate errors after transformations, leading to inaccurate accuracy evaluations for coordinates. In this study, the effects of angular deviation and coordinate value magnitude on coordinate errors during transformations are first analyzed. Additionally, the transformation deviation of the three-point method is examined. Subsequently, an accuracy evaluation method for coordinate measurements is proposed to determine the scale scaling factor and the formula for calculating the variance of measuring coordinate errors. Finally, a coordinate accuracy evaluation method and evaluation formula that consider coordinate system transformation errors are proposed by self-checking. The validity of the proposed accuracy evaluation formula is confirmed through experiments. The coordinate measurement accuracy of the low-cost binocular camera is higher than that of the total station, whether or not coordinate system transformations are considered. Stereo-vision measurement technology is more suitable for small-scale engineering measurements.

Utilizing Fisheye Cameras and Mass Spectrometry Imaging to Obtain Probing Coordinates for Histological Samples

Detecting chemical compositions in histological samples using mass spectrometry often requires time-consuming user interaction with a probe to ensure it is positioned as closely as possible to a sampling region. Fisheye cameras can obtain images of samples with a wide field-of-view; however, barrel distortion makes it difficult to analyze them as a flat plane. This research project aimed to develop an application that unwarps live images of histological samples captured with a fisheye camera and calculates the exact image-to-real-world probing coordinates with minor user interaction. Python’s PyQt5 and OpenCV libraries were utilized to create interactive software that removes fisheye distortion, finds image-to-real-world coordinates, and segments images. Connected hardware consisted of a Prusa 3D printer, liquid micro junction-surface sampling probe, fisheye camera, and LED light strips. The printer provided a bed for capturing sample images and control of the camera and probe within 1/100 of a millimetre. The software was outlined to process at least 2 photos of checkerboards for the fisheye undistortion, capture a photo of a sample to be unwarped, and require the user to map 4 points from the image to probe coordinates. Using this approach, real-world coordinates could be found for any image location. The application successfully unwarps live photos and converts image-to-real-world coordinates with sub-millimeter accuracy. Users can take new calibration photos, control lighting, save photos, and check undistortion entirely within the application to ensure all parameters are satisfactory. Coordinates of significant regions are displayed or may be manually selected, making it easier to sample specific areas. The success of unwarping relies on the camera’s focus and height, lighting, and object positioning. Future development plans to improve robustness and coordinate accuracy, and reduce the amount of calibration needed.

Biofeedback and Exercise Load Affect Accuracy of Tongue Strength Exercise Performance.

Rehabilitative exercises require precise movement coordination and target accuracy for optimal effectiveness. This paper explores the impact of tongue strength exercises (TSE) performance accuracy on exercise outcomes, adherence, and participant confidence and motivation. An 8-week randomized clinical trial included 84 typically aging participants divided into four groups defined by access to biofeedback (present/absent) and TSE intensity dosing (maximal/submaximal) during a home exercise program (HEP). Retention, training, and HEP accuracy were tracked at biweekly visits and during HEP for participants with access to a biofeedback device. Associations with tongue strength outcomes, participant factors, biofeedback, and intensity dosing were analyzed. Exercise accuracy measures did not contribute to tongue strength outcomes at the end of 8weeks. Increased training accuracy (less practice required to achieve competency) was associated with higher participant confidence and better adherence to the HEP. The presence of biofeedback was associated with reduced adherence but better retention accuracy, while maximal intensity was associated with improvements in all accuracy measures compared to submaximal intensity exercise. These findings in typically aging participants suggest the need for tailored approaches in swallowing-related exercise programs, given the effects of biofeedback and exercise intensity on motor learning and exercise retention. Accuracy performance and its effect on clinical outcomes warrants study in clinical populations with dysphagia and with various rehabilitative approaches.Trial Registration Clincialtrials.gov: NCT04809558.

Exploring Phase Transition and Structural Complexity in the Mixed Cation Uranium Oxide CaUNb2O8.

The structures and high-temperature phase transition of CaUNb2O8 were studied in situ using synchrotron X-ray and neutron powder diffraction. Rietveld refinements provided an accurate description of the crystal structures of both the monoclinic fergusonite-type I2/b structure observed at room temperature and the tetragonal scheelite-type I41/a structure found at high temperatures. Bond valence sum analysis showed Nb5+ to be octahedrally coordinated in the monoclinic fergusonite-type structure, akin to other ANbO4 materials. Rietveld analysis of the variable temperature data allowed for the determination of accurate unit cell parameters and atomic coordinates, as well as revealing a reversible phase transition around ∼750 °C. The Nb-O bond distances display anomalous behavior, with a discontinuity in the longer Nb-O(1') distance coinciding with the phase transition suggestive of a reconstructive phase transition. Mode analysis identified the Γ2+ mode as the primary mode that drives the phase transition; this is linearly coupled to the induced spontaneous strain within the monoclinic fergusonite-type structure. Analysis of the temperature dependence of the Nb(z) positional parameter, as well as of the ϵ1-ϵ2 and ϵ6 strain parameters, showed that the phase transition is not strictly second order, with the critical exponent β ≠ 1/2. This study demonstrates the complex structural features of mixed cation metal oxides at elevated temperatures.

Validation of Tenths Stereotactic Coordinates Method Using Probabilistic Tractography of the Ansa Lenticularis in Parkinson's Disease Patients

To evaluate the accuracy of stereotactic coordinates to target the ansa lenticularis (AL) using 2 surgical planning methods, the conventional millimeter method (MM) and the normalized Tenths method (TM), assessed through individualized probabilistic tractography. Stereotactic targeting of the AL was assessed in 2 groups: 16 patients with Parkinson's disease and 16 healthy controls from Group 1, and 39 Parkinson's disease patients from Group 2. Structural and diffusion magnetic resonance imaging probabilistic tractography identified the AL based on the Schaltenbrand-Wahren Atlas. The MM defined stereotactic coordinates in millimeters, while the TM refined the planning by dividing the intercommissural line (AC-PC) distance into 10 equal parts, normalizing the "X," "Y," and "Z" coordinates for each patient. We subsequently compared the percentage of structural connectivity (%conn) of the AL with predefined regions of interest (ROIs), including the frontopontine-corticothalamic tracts, globus pallidus internus-ventral oral anterior, and ventral oral posterior, and quantified the streamlines in 142 brain hemispheres using the MM and TM coordinates. Despite anatomical variations in intercommissural (AC-PC) line lengths between both groups (22.5 ± 2.09mm and 24.4 ± 2.56mm, respectively; P= 0.002), as well as differences in magnetic resonance imaging acquisition parameters, we found that the TM significantly enhanced streamline identification and %conn compared to the MM. These enhancements were noted across ROIs: frontopontine-corticothalamic and globus pallidus internus-ventral oral anterior in both hemispheres, and globus pallidus internus-ventral oral posterior in the left (P < 0.001) and right hemispheres (P= 0.03). TM surpasses MM in identifying the structural connectivity between the AL and predefined ROIs, underscoring the advantages of coordinate normalization. However, variations in AC-PC line lengths and Euclidean distances between methods could lead to inaccuracies in the coordinate settings, potentially affecting the precision of structural connectivity and the efficacy of therapeutic outcomes.

Development of a GIS Tool to Find Fiber Cable Fault Using Python Scripting for ArcGIS in Amman City

Optical fiber cables are characterized by a larger bandwidth than other transmission media, which increases the amount of data transmitted per unit of time. Managing a fiber optic network using Geographic Information Systems (GIS) has benefits for the operation and maintenance of the communication network. The study aims to develop a GIS tool to detect fiber optic cable faults using Python Scripting for ArcGIS in the city of Amman. To achieve this goal, the Esri data model for telecommunications was used. The study concluded that it is possible to locate faults using the Python programming language, and the program provides accurate coordinates based on the precision of the OTDR device.

Evaluation of the errors of measuring residual stresses by the hole drilling method

A sample configuration with a specified distribution of residual stresses in depth was developed to elaborate modes for studying residual stresses using mechanical and physical methods. The sample formation technique is based on non-uniform plastic deformation of an aluminum beam of rectangular cross section according to the pure bending scheme. The control of the deformed state during loading was performed on the end surface of the sample by the field of normal deformations obtained using a digital image correlation system. The depth of the plastically deformed layer was 1.3 mm. The theoretical distribution of residual stresses obtained as a result of unloading of a plastically deformed sample was determined from the results of a numerical calculation of a finite element model, with allowance for the physical and mechanical characteristics, elastic-plastic hardening, as well as the deformation curve in true coordinates obtained as a result of uniaxial tension on elementary samples. A study of residual stresses inhomogeneous in depth was carried out by drilling holes in accordance with ASTM E837 on two opposite sides of the sample: the region of tension under loading and the area of compression, respectively. The control of the deformation response resulted from drilling was recorded using three-axis strain gauge rosettes. The results of the actual measurement of the longitudinal component of residual stresses were compared with their theoretical distribution obtained by a numerical method. The root-mean-square error in measuring residual stresses, relative to their theoretical distribution, for an aluminum alloy sample reaches 18.7 MPa. It should be noted that largest measurement errors were recorded at small depths, since they are characterized by small values of deformations comparable to the value of shot noise.

Mapping and spectroscopy of telecom quantum emitters with confocal laser scanning microscopy

Efficiently coupling single-photon emitters in the telecommunication C-band that are not deterministically positioned to photonic structures requires both spatial and spectral mapping. This study introduces the photoluminescence mapping of telecom C-band self-assembled quantum dots (QDs) by confocal laser scanning microscopy, a technique previously unexplored in this wavelength range which fulfills these two requirements. We consider the effects of distortions inherent to any imaging system but largely disregarded in prior works to derive accurate coordinates from photoluminescence maps. We obtain a position uncertainty below 11 nm for 10% of the QDs when assuming no distortions, highlighting the potential of the scanning approach. After distortion correction, we found that the previously determined positions are on average shifted by 428 nm from the corrected positions, demonstrating the necessity of this correction for accurate positioning. Then, through error propagation, the position uncertainty for 10% of the QDs increases to 110 nm.

LORE++: Logical location regression network for table structure recognition with pre-training

Table structure recognition (TSR) aims at extracting tables in images into machine-understandable formats. Current approaches address this issue by either predicting the adjacency of detected cells or direct generation of structural sequences. Nonetheless, these approaches either count on additional heuristic rules for post-processing, or involve the generation of extremely long-range sequences that lead to computational intricacy. In this paper, We redefine TSR as a LOgical location REgression paradigm, which effectively captures inherent logical dependencies and constraints among table cells. Correspondingly, we propose LORE, a novel approach for TSR. LORE simultaneously predicts accurate geometric coordinates of table cells and the logical structures of the entire table. Our proposed LORE is conceptually simpler, easier to train, and more accurate than other TSR paradigms. Moreover, to enhance the model’s spatial and logical representation capabilities, we propose two pre-training tasks, resulting in an upgraded version named LORE++. The incorporation of pre-training is proven to enjoy significant advantages, leading to a substantial enhancement in terms of accuracy, generalization, and few-shot capability compared to its predecessor. Experiments on standard benchmarks demonstrate the superiority of LORE++, which highlights the potential and promising prospect of the logical location regression paradigm for TSR.

Research on the optimization methods of common points layout for survey and alignment of particle accelerators

As a fourth-generation synchrotron light source based on a diffraction-limited storage ring, Hefei Advanced Light Facility (HALF) puts forward higher requirements for the alignment accuracy of the main components. Aggregated common points result in a loss of accuracy during the coordinate transformation required by accelerator alignment. To address this challenge, we proposed two methods: “aggregated points centralization (APC)" and “uniformity-weighted algorithm (UWA)" according to different usage scenarios. APC combines uniformity with the K-means algorithm to enhance the accuracy of coordinate transformation while reducing the number of common points. UWA calculates the uniformity in different directions and assigns weights to common points, reducing the accuracy loss. Simulations demonstrate that these two methods have strong superiority and stability with significantly improved accuracy. Applications of these 2 methods in the magnet unit pre-alignment experiment and tunnel network measurement show promising results. APC in pre-alignment can reduce the cost of building common points by 26% while maintaining the coordinate conversion accuracy. In tunnel network measurement, accuracy can be increased by 28% using UWA. The methods proposed offer broad applicability in the field of particle accelerator alignment and guiding alignment solutions for HALF.

Where Is That Crater? Best Practices for Obtaining Accurate Coordinates from LROC NAC Data

The Lunar Reconnaissance Orbiter Camera (LROC) Narrow Angle Camera (NAC) images and their derived products make up one of the highest-resolution and most spatially accurate data sets available for the Moon, making them a crucial resource for planners of landed lunar missions. However, it is essential to understand the best uses for each data type and the limits on the accuracy and resolution of the data sets available. With this understanding, users can better interpret and communicate their results. In this paper, we describe what assumptions may be made about the accuracy of LROC NAC images and the various derived products created by the LROC team. NAC digital terrain models and their corresponding orthophotos have the best accuracy of all NAC products, usually better than 10 m horizontally, and should be used where available. Other controlled NAC products usually have accuracies better than 30 m. For areas without controlled products, we describe how to process NAC images to obtain coordinates with the highest possible accuracy. We also recommend best practices for data users interacting with LROC data through online map servers, such as QuickMap or Lunaserv, and for processing LROC data locally using the US Geological Survey Integrated Software for Imagers and Spectrometers.

MODERN METHODS OF GEODESIC MAPPING OF TERRITORIES: USE OF GPS AND GNSS TECHNOLOGIES

The necessity and expediency of introducing into geodetic production modern satellite technologies based on the use of global navigation satellite systems (GNSS) became obvious in the early 90s of the XX century. New technical means and technologies based on DPS revolutionized the geodetic methods of coordinate determination for both industrial and scientific purposes. The main tasks of GNSS-meters are the calculation with varying accuracy of the current unknown coordinates of points and the rendering in nature of points with known coordinates, as well as a number of additional applications (calculation of distances, calculation of areas, coordinate geometry, breakdown, etc.). In addition to the need to coordinate objects, measurements for GIS also contain a number of additional tasks, among which, first of all, the need to record various attribute data tied to GIS objects. Active development of earth remote sensing technologies using GPS signals began in the late 1980s. and is conducted in several directions: development of technology for building global TEM geodetic maps (GIM); development of GPS cartography methods; development of assimilation models for operational forecasting of territory parameters. The study of remote monitoring technologies using GPS/GNSS signals and the study of the dynamics of cartographic changes of various origins with their help are the subject of this article. An evaluation of the characteristics (sensitivity, spatial and temporal resolution, volume of information received, measurement range) of ground networks of GPS/GNSS receivers designed for registration and monitoring of geodetic benchmarks that mark the territory and allow for the efficient construction of a cartographic module, which is very relevant under during hostilities on the territory of Ukraine.

PROBLEMS AND PROSPECTS OF LAND PROPERTY VALUATION BY GEODETIC METHODS

The article examines modern geodetic methods of land ownership assessment and their influence on effective management of land resources and economic development of the state. The main focus is on such methods as the use of GPS and GIS technologies, remote sensing of the Earth (DSR) and laser scanning (LiDAR). It was determined that the use of GPS and GIS technologies allows obtaining accurate coordinates of land plots in real time, which reduces the time and costs of conducting geodetic works. GIS technologies provide integration of various types of geospatial data, which allows for comprehensive analysis of topography, land cover, infrastructure and other factors. This makes the evaluation process more transparent and understandable for users. Earth Remote Sensing (EAR) uses satellite imagery and aerial photography to obtain up-to-date data over large areas, including hard-to-reach areas. DZZ allows to obtain detailed information about relief, vegetation, water resources and infrastructure, which is important for planning and management of land resources. Laser scanning (LiDAR) is one of the most modern methods that provides three-dimensional models of objects and territories with high accuracy. LiDAR allows you to quickly and accurately obtain data on the relief of the area, buildings, vegetation and other characteristics of land plots. The integration of data from various sources, such as laser scanning, GPS, GIS and land surveying, significantly increases the accuracy and reliability of land property valuation. The combination of these data allows for the creation of complex models of territories that include information about relief, land cover, infrastructure and water resources. The scientific results of the study show that modern geodetic methods significantly increase the efficiency and accuracy of land property assessment. This is the basis for making informed economic decisions and effective management of land resources. The use of innovative technologies, such as drones, satellite surveillance systems, artificial intelligence and machine learning, opens up new opportunities for the development of geodetic methods, ensuring sustainable development and rational use of natural resources.

A new novel recognition and positioning system of black light-absorbing volute for automation depalletizing development

Abstract In the application of vision measurement, the black light-absorbing object is difficult to reflect the structured light from infrared emitter of the RGB-D camera. Therefore, an image recognition algorithm based on reference environment information is proposed to acquire the spatial positioning information of black volutes in the depalletizing system. The hardware system of the depalletizing system is mainly constructed of an upper computer, a six-axis industrial robot, an RGB-D camera and an end adsorption device. Firstly, the horizontal position information of each volute placed on the cardboard is obtained by the depth differences between the cardboard and the volute. Then, the depth information of the volute is obtained by the upper cardboard depth through collecting the position of the end vacuum suction cup triggered by feedback signal from vacuum generator. Secondly, a regional planar hand-eye calibration method is developed to improve the calibration accuracy in two-dimensional coordinates. The regional calibration method divides the robot working area into four regions: upper left, lower left, upper right, and lower right. The transformation matrix of each region is calculated separately. Finally, the depalletizing experiment is conducted on the three types of volutes. It is concluded that the average positioning error of the grasping center point of each volute obtained by our method is 3.795 mm, and its standard deviation is 1.769 mm. The average value of regional planar hand-eye calibration error is 4.044 mm, and its standard deviation is 1.501 mm. Under a stack of materials with dimensions of 1350 mm × 1350 mm × 1500 mm, the maximum error is controlled within 15 mm. Additionally, when combined with the end feedback compensation mechanism, the success rate for grasping all three volutes reaches 100%.

Facial Action Unit detection based on multi-task learning strategy for unlabeled facial images in the wild

Facial Action Unit (AU) detection often relies on highly-cost accurate labeling or inaccurate pseudo labeling techniques in recent years. How to introduce large amounts of unlabeled facial images in the wild into supervised AU detection frameworks has become a challenging problem. Additionally, nearly every type of AUs has the problem of unbalanced positive and negative samples. Inspired by other multi-task learning frameworks, we first propose a multi-task learning strategy boosting AU detection in the wild through jointing facial landmark detection and AU domain separation and reconstruction. Our introduced dual domains facial landmark detection framework can solve the lack of accurate facial landmark coordinates during the AU domain separation and reconstruction training process, while the parameters of homostructural facial extraction modules from these two similar facial tasks are shared. Moreover, we propose a pixel-level feature alignment scheme to maintain the consistency of features obtained from two separation and reconstruction processes. Furthermore, a weighted asymmetric loss is proposed to change the contribution of positive and negative samples of each type of AUs to model parameters updating. Experimental results on three widely used benchmarks demonstrate our superiority to most state-of-the-art methods for AU detection.