Image Frames Research Articles

Position and heading estimation for indoor navigation of a micro aerial vehicle using vanishing point

Abstract Indoor navigation for micro aerial vehicles (MAVs) is challenging in GPS signal-obstructed indoor corridor environments. Position and heading estimation for a MAV is required to navigate without colliding with obstacles. The connected components algorithm and k-means clustering algorithm have been integrated for line and vanishing point detection in the corridor image frames to estimate the position and heading of the MAV. The position of the vanishing point indicates the position of the MAV (centre, left or right) in the corridor. Furthermore, the Euclidean distance between the image centre and mid-pixel coordinates at the last row of the image and the detected vanishing point pixel coordinates in the successive corridor image frames are used to compute the heading of the MAV. When the MAV deviates from the corridor centre, the position and heading measurement can send a suitable control signal to the MAV and align the MAV at the centre of the corridor. When compared with a grid-based vanishing point detection method heading accuracy of ±1⋅5°, the k-means clustering-based vanishing point detection is suitable for real-time heading measurement for indoor MAVs with an accuracy of ±0⋅5°.

Feasibility of fetal cardiac function and anatomy assessment by real-time spiral bSSFP MRI at 0.55T

BackgroundContemporary 0.55T MRI is promising for fetal MRI, due to the larger bore, reduced safety concerns, lower acoustic noise, and improved fast imaging capability. In this work, we explore improved fetal cardiac MRI (CMR) without relying on any synchronizing devices, prospective, or retrospective gating. PurposeTo determine the feasibility of real-time MRI evaluation of fetal cardiac function as well as cardiac and great vessel anatomies by using spiral balanced steady-state free precession (bSSFP) at 0.55T. MethodsA real-time spiral bSSFP pulse sequence for fetal CMR was implemented and optimized on a 0.55T whole-body MRI. Fetal CMR was prospectively performed between May 2022 and August 2023. The protocol included: 1) real-time images at standard cardiac views, for 10-20seconds/view and 40 to 43.6 ms/frame and 2) 4-9 stacks of slices at standard cardiac views that each cover the whole heart, with 15-30 slices/stack, and 2-5seconds/slice, at 320 to 349 ms/frame. Images were evaluated by a fetal cardiologist. Quantitative measurements of cardiothoracic area ratio and cardiac axis were compared with previous reports. Diagnostic accuracy was compared against postnatal echocardiographic findings. ResultsTwenty-nine participants were enrolled for 32 CMR exams, with mean maternal age 33.6±5.8 year (range 22-44 year) and mean gestational age 32.8±3.9 weeks (range 23-38 weeks). The proposed sequence enabled evaluation of the fetal heart in <30minutes in all cases (average 22minutes). Real-time MRI allowed easy adjustment of scan plan, automatic whole-heart volumetric sweeping, and flexible choice of reconstruction temporal resolution. For key cardiac anatomic features 60% were delineated well. Mean cardiothoracic area ratio and cardiac axis were 0.27±0.04 and 45.8±7.8. Diagnostic agreement with postnatal echocardiographic findings was 84%. ConclusionA spiral real-time bSSFP pulse sequence at 0.55T can provide both low framerate and high framerate fetal heart images without relying on maternal breath-hold, specialized gating devices, or cardiac gating. The low framerate images offer high diagnostic quality structural evaluations of the fetal heart, while the high framerate images capture fetal heart motion and may enable functional assessments.

Gait Analysis through Animated GIFs: A Novel Approach for Visualizing Step Dynamics

The field of prosthetic knee development has made great progress in recent years, notably with the use of machine learning (ML) approaches. Researchers made significant progress in enhancing the functionality, flexibility, and user experience of prosthetic knees using revolutionary machine learning techniques.Since gait analysis delivers part of the most important information about human motion patterns, it becomes critical in the development of a prosthetic knee. In this paper, some new techniques for gait analysis with feature extraction are proposed that include visualization using animated GIF images. This methodology extracts key parameters like step length and step width from the frames of a GIF image and can completely represent the dynamics of gait with respect to time.This methodology is particularly significant to design an efficient prosthetic knee since it shows how combining computer analysis and visual data may enhance gait analysis methods. For this study, brief walking footage of both healthy individuals and amputees are recorded, then turned into GIFs. Subsequently, these GIF data points are retrieved, making it possible to quantify step length and other essential metrics required to analyses gait patterns.Gait analysis is incorporated as part of the development process for these prosthetic knee joints due to the fact that it gives information on human motion patterns. The methods used in this paper provide novel ways of carrying out gait analysis through feature extraction and visualization using animated GIF images. This method would help in depicting the full picture of gait dynamics with time and assist in extracting important parameters such as step length and width from the frames of the GIF. The work, as described, falls squarely into the use of computer vision techniques for feature extraction and into time-series data analysis for trend identification within the broader application of machine learning in the development of the prosthetic knee. These techniques could be generalized toward designing better prosthetic knee design for more natural and fluent motion.

The selection of target areas for orbital imaging, as well as the application of diethylenetriaminepentaacetic acid orbital imaging, clinical factors, alkaline phosphatase, and thyrotropin receptor antibodies in the staging and grading of thyroid-associated ophthalmopathy, are subjects of research.

This study aimed to investigate whether patients with thyroid-associated ophthalmopathy (TAO) are in the active phase and explore their correlations with various clinical factors, serological tests, and orbital imaging parameters studied. It also aimed to evaluate the diagnostic value of different target areas in orbital imaging for assessing TAO inflammatory activity according to the American NOSPECS classification. Patients were stratified based on their NOSPECS grade to determine statistical differences among different stages. Receiver-operating characteristic (ROC) curves were used to assess the diagnostic efficacy of statistically significant data. Patients identified as active by orbital imaging were recommended for treatment to observe therapeutic outcomes. A total of 45 patients with thyroid-related eye disease who underwent 99mTc-diethylenetriaminepentaacetic acid single-photon emission computed tomography/computed tomography (CT) fusion imaging, alkaline phosphatase (ALP), thyrotropin receptor antibody (TRAb), free triiodothyronine, free thyroxine, thyroid-stimulating hormone serological tests, and clinical data collection from November 2023 to June 2024 were included. Clinical Activity Score (CAS) assessment, diplopia scores, and NOSPECS grading were conducted the day after imaging. Four rectus muscles were outlined as regions of interest on the optimal frame of extraocular muscle imaging and measured for maximum and mean radioactive counts, normalized against average counts of the patient's optic nerve level occipital bone region (UR1max, UR1mean). Tear gland radioactive uptake was similarly measured for maximum and mean counts normalized against the same region (UR2max, UR2mean). Exophthalmos and extraocular muscle thickening were assessed on CT scans. The correlations between different study parameters and CAS, as well as differences among different NOSPECS grades, were evaluated. ROC curves were used for statistically significant variables. Patients with discrepancies between orbital imaging and CAS results underwent treatment or follow-up to evaluate prognosis and staging. Active TAO status correlated significantly with UR1max, UR1mean, UR2max, UR2mean, ALP, TRAb, and age, using CAS and radiological imaging as standards. Among these, UR2max showed the strongest correlation. Significant differences (except ALP and TRAb) were found among different NOSPECS grades for the studied variables. Orbital volume, CAS results, radiological imaging, and diplopia scores also showed significant differences among different grades. Forty-two of 45 patients exhibited varying degrees of extraocular muscle thickening, confirming its reliability as a diagnostic criterion for TAO. The most common muscles affected were the inferior and medial rectus muscles, observed in 32 cases. High consistency was found between orbital imaging and CAS staging. Three patients diagnosed as active by imaging (including one with inconsistent CAS and imaging results) showed varying degrees of improvement posttreatment. Patients with nonactive imaging but inconsistent CAS results showed no progression during 3-month follow-up. ROC curves demonstrated high diagnostic efficacy for UR2max, with other indices also showing good diagnostic performance. Tear glands and extraocular muscles showed high diagnostic value, with tear glands demonstrating relatively higher value. Orbital imaging showed high consistency with CAS grading, providing an objective and comprehensive assessment of ocular involvement compared to CAS scoring alone. ALP and TRAb also demonstrated value in TAO staging, assisting clinical discrimination. Age may also play a significant role.

The research on dance motion quality evaluation based on spatiotemporal convolutional neural networks

With the rapid development of artificial intelligence and computer vision technology, dance action recognition and quality assessment have become a challenging and important research field. Traditional dance movement recognition methods often rely on manual feature extraction and expert scoring, which have problems such as strong subjectivity, low efficiency, and difficulty in handling complex movements. To address these issues, this study proposes a dance action recognition and quality assessment method based on Spatio Temporal Convolutional Neural Network (ST-CNN). Specifically, it includes a feature extraction network based on 3D spatiotemporal description operators and a multi-scale aggregated long short memory network for extracting spatial features of single frame images and fusing video sequence features composed of all frames. This approach can effectively capture dynamic changes in dance movements by combining information from spatial and temporal dimensions, thereby achieving more accurate recognition and evaluation. In addition, to address the high storage and computational requirements of convolutional neural networks during training, we integrated dance video sequences into an IoT architecture to address parallel recognition and evaluation of multiple videos. Finally, we validated the proposed method on the public datasets NTU-RGB 60 and NTU-RGB 120, and the experimental results demonstrated the effectiveness of the method.

Precision Timing of Eclipsing Binaries from TESS Full Frame Images: Method and Performance

Several hundreds of thousands of eclipsing binaries (EBs) are expected to be detected in the Transiting Exoplanet Survey Satellite (TESS) full frame images (FFIs). This represents a significant increase in the number of EBs available for eclipse timing variation studies. In this paper, we investigate the feasibility of performing precise eclipse timing of TESS EBs using the FFIs. To this end, we developed a fast, automated method and applied it to a sample of ∼100 EBs selected from the Villanova TESS EB catalog. Our timing analysis resulted in the detection of 10 new triple candidates with outer periods shorter than ∼1300 days. For five of them, we were able to constrain the outer orbit by analyzing independently the short-cadence (SC) and FFI data and to derive the minimum mass of the third body with a precision better than 4% for SC and 11% for FFI data. We then compared the results obtained from the two data sets and found that using the FFI data leads to (1) a degradation of both the accuracy and precision of the tertiary mass determination for the tightest EBs and (2) an overall underestimation of the third component’s mass. However, we stress that our main conclusions on the nature of the detected signals do not depend on which data set is used. This confirms the great potential of TESS FFIs, which will allow us to search for rare objects such as substellar circumbinary companions and compact triple stellar systems.

Bladder image stitching algorithm for navigation and referencing using a standard cystoscope

To aid in the diagnosis, monitoring, and surveillance of bladder carcinoma, this study aimed to develop and test an algorithm that creates a referenceable bladder map rendered from standard cystoscopy videos without the need for specialized equipment. A vision-based algorithm was developed to generate 2D bladder maps from individual video frames, by sequentially stitching image frames based on matching surface features, and subsequently localize and track frames during reevaluation. The algorithm was developed and calibrated in a 2D model and 3D anthropomorphic bladder phantom. The performance was evaluated in vivo in swine and with retrospective clinical cystoscopy video. Results showed that the algorithm was capable of capturing and stitching intravesical images with different sweeping patterns. Between 93% and 99% of frames had sufficient features for bladder map generation. Upon reevaluation, the cystoscope accurately localized a frame within 4.5 s. In swine, a virtual mucosal surface map was generated that matched the explant anatomy. A surface map could be generated based on archived patient cystoscopy images. This tool could aid recording and referencing pathologic findings and biopsy or treatment locations for subsequent procedures and may have utility in patients with metachronous bladder cancer and in low-resource settings.

Artificial Intelligence-Assisted Stimulated Raman Histology: New Frontiers in Vibrational Tissue Imaging

Frozen section biopsy, introduced in the early 1900s, still remains the gold standard methodology for rapid histologic evaluations. Although a valuable tool, it is labor-, time-, and cost-intensive. Other challenges include visual and diagnostic variability, which may complicate interpretation and potentially compromise the quality of clinical decisions. Raman spectroscopy, with its high specificity and non-invasive nature, can be an effective tool for dependable and quick histopathology. The most promising modality in this context is stimulated Raman histology (SRH), a label-free, non-linear optical process which generates conventional H&amp;E-like images in short time frames. SRH overcomes limitations of conventional Raman scattering by leveraging the qualities of stimulated Raman scattering (SRS), wherein the energy gets transferred from a high-power pump beam to a probe beam, resulting in high-energy, high-intensity scattering. SRH’s high resolution and non-requirement of preprocessing steps make it particularly suitable when it comes to intrasurgical histology. Combining SRH with artificial intelligence (AI) can lead to greater precision and less reliance on manual interpretation, potentially easing the burden of the overburdened global histopathology workforce. We review the recent applications and advances in SRH and how it is tapping into AI to evolve as a revolutionary tool for rapid histologic analysis.

Перспективи діагностики рухових розладів за допомогою методів комп’ютерного зору на базі мобільного пристрою

The research work investigated markerless video analysis technologies based on the analysis of the relative position of heterogeneous parts of object images in successive frames. Modern video motion capture systems are ready-made clusters of points in the form of plates with four markers for long limb segments, a ‘cap’ with markers for the head, etc. The main models used in mobile devices to estimate the movements of the upper limbs and the biomechanics of joint movement in real time were studied, namely PoseNet, MoveNet Thunder, MoveNet Lightning, and BlazePose in Light, Full, and Heavy versions. The models were evaluated for key characteristics such as speed, device impact, and support for hardware acceleration.

The Effect of Seeing Paintings or Photojournalistic Images Depicting Refugees on Their Infrahumanisation

Abstract Images are powerful cultural agents that can inform, shape and change the attitudes and behaviours of viewers. The ways in which marginalised groups are depicted in photographs shape people's attitudes towards them. For example, viewing photojournalistic images portraying refugees in large rather than small groups results in the infrahumanisation of refugees. However, the impact of artworks vs photojournalistic images depicting refugees on their infrahumanisation remains a key and unexplored topic. In this pre-registered study, we investigated whether viewing different types of visual images (e.g., paintings vs photographs) of refugees using distinct visual framings (e.g., large or small groups) influences viewers' infrahumanisation of refugees and the intensity and valence of the viewers' felt emotions. Contrary to our predictions, no evidence was found for an effect of visual framing (large vs small groups) and different image types (paintings vs photos) portraying refugees on their infrahumanisation. Moreover, and in line with our predictions, photojournalistic images were evaluated as more emotionally intense than paintings, whereas paintings rather than photojournalistic images engaged more positive emotions, demonstrating that different types of images involve distinct affective responses. Furthermore, exploratory findings revealed that increased positive appraisals of photojournalistic images depicting small groups rather than large groups led to greater humanisation of refugees. This suggests that positive emotions can decrease the infrahumanisation of marginalized groups, particularly when these are evoked by photojournalistic images. Overall, these findings shed new light on the effects of audience exposure to different forms of visual representation and their social and emotional consequences.

Automatically Counting Florida Manatees (Trichechus manatus latirostris) from Drone Images Using Object-Based Image Analysis

Florida manatees (Trichechus manatus latirostris) require frequent and extensive surveys to inform conservation efforts. Crewed aircraft surveys can be costly, dangerous, and logistically complex. Unoccupied aerial systems (UASs) can assist with these issues. While manual review of UAS imagery can be time- and labor-intensive, automated detection of manatees in aerial survey footage can help. We present an object-based image analysis workflow for the automated detection and count of Florida manatees in Google Earth Engine, a free platform for research that allows for scripts and imagery sharing. Training and testing datasets were built from randomly extracted image frames from two stationary, unoccupied aerial system videos over thermal refugia. The workflow captured most manatees (93.98 to 95.62% recall; 4.38 to 6.03% false negative rate), but also counted many objects as manatees incorrectly (4.24 to 14.77% precision; 998.40 to 3,885.54% false positive over the detectable rate). Sun glint, mud plumes, and water close to shore were common causes of false positives. While the automated count was too high, the workflow lays markers over each detection, allowing for quick manual review for more accurate (semi-automated) counts. This study is an early step in automated detection tools for Florida manatees in a cloud-based platform. Future efforts could explore other platforms or may improve this workflow by including new classes for confounding objects.

Movement Recognition and Injury Risk Assessment of Wushu Athletes Based on Computer Vision

This paper aims to study a method of movement recognition and injury risk assessment for Wushu athletes based on computer vision. Studying the optimization of Wushu athletes’ movement trajectory can effectively improve the athletes’ movement quality. Based on a hybrid real-time synchronization algorithm, the arm motion trajectory model of martial arts athletes is studied. A dynamic and static arm recognition algorithm is proposed, and the motion feature extraction method in Wushu movement is studied. Dynamic arm recognition typically relies on the collection of video or image sequences. These sequences contain the position, shape, and motion trajectory of the arm at different time points. Static arm recognition mainly relies on the acquisition of a single image or image frame. The dynamic arm recognition algorithm captures the motion trajectory and changes of the arm by processing video or image sequences, while the static arm recognition algorithm only processes individual images or image frames. On this basis, the design of the computer software architecture of the digital site system is completed. The real-time collection, analysis, display and storage of motion information and assembly configuration are realized. The simulation results show that the method has high accuracy and provides a powerful scientific basis for improving athletes’ movement injuries. To predict the risk of injury an athlete may suffer during training or competition.

Improving Visual Object Detection using General UFIR Filtering

Object detection is a fundamental task in computer vision, which involves the identification and localization of objects within image frames or video sequences. The problem is complicated by large variations in the video camera bounding box, which can be thought of as colored measurement noise (CMN). In this paper, we use the general unbiased finite impulse response (GUFIR) approach to improve detection performance under CMN. The results are compared to the general Kalman filter (GKF) and two detection methods: “Faster-RCNN” and “Tensorflow PASCAL Visual Object Classes (VOC)”. Experimental testing is carried out using the benchmark data ”Car4”. It is shown that GUFIR significantly improves the detection accuracy and demonstrates the properties of the effective tool for visual object tracking.

SAM-Net: Spatio-Temporal Sequence Typhoon Cloud Image Prediction Net with Self-Attention Memory

Cloud image prediction is a spatio-temporal sequence prediction task, similar to video prediction. Spatio-temporal sequence prediction involves learning from historical data and using the learned features to generate future images. In this process, the changes in time and space are crucial for spatio-temporal sequence prediction models. However, most models now rely on stacking convolutional layers to obtain local spatial features. In response to the complex changes in cloud position and shape in cloud images, the prediction module of the model needs to be able to extract both global and local spatial features from the cloud images. In addition, for irregular cloud motion, more attention should be paid to the spatio-temporal sequence features between input cloud image frames in the temporal sequence prediction module, considering the extraction of temporal features with long temporal dependencies, so that the spatio-temporal sequence prediction network can learn cloud motion trends more accurately. To address these issues, we have introduced an innovative model called SAM-Net. The self-attention module of this model aims to extract an inner image frame’s spatial features of global and local dependencies. In addition, a memory mechanism has been added to the self-attention module to extract interframe features with long temporal and spatial dependencies. Our method shows better performance than the PredRNN-v2 model on publicly available datasets such as MovingMNIST and KTH. We achieved the best performance in both the 4-time-step and 10-time-step typhoon cloud image predictions. On a cloud dataset consisting of 10 time steps, we observed a decrease in MSE of 180.58, a decrease in LPIPS of 0.064, an increase in SSIM of 0.351, and a significant improvement in PSNR of 5.56 compared to PredRNN-v2.

The view of intertextuality in graphic design

This study aims to reveal the existence of the concept of intertextuality in the field of graphic design. No product produced by humans can be considered independent of previous products; this situation demonstrates that past experiences and social interactions play an inevitable role in product creation. Especially in the production of literary works, individuals create new works influenced by previous ones. This interaction is defined by the concept of "intertextuality." The initial studies on intertextuality began within the framework of Bakhtin's "Conversationalism" theory and were later developed by theorists such as Kristeva, Barthes, Jenny, and Genette. With Genette's classification, the concept of intertextuality has become multidimensional. It has been found that this concept is not limited to literary products but also exists in fields such as music, painting, sculpture, architecture, and moving media. In this context, the special day designs shared by non-governmental organizations operating in Turkey on the Instagram platform were examined using visual intertextuality methods developed by Werne. The results showed that methods such as "Attaching to Image," "Framing Image and Text," and "Encouraging Thought in Image" were actively used. Additionally, it was determined that "Visual Citation" and "Clustering" methods were also employed, although less frequently.

Metaphorical Idioms in Extended Conceptual Metaphor Theory

Abstract In Extended Conceptual Metaphor Theory (Kövecses, 2020), I offered a comprehensive overhaul of “standard” conceptual metaphor theory. The present paper attempts to demonstrate how the new view of CMT can handle metaphorical idioms. To this end, I analyze four metaphorical idioms from the thematic area of money (throw money about, money slips through someone’s fingers, be a cash cow, money keeps someone/something afloat). The analysis assumes and starts out from the observation that money-related metaphors are based on two generic-level conceptual metaphors: money is a moving entity and money is a force. Extended CMT adds to CMT the notion of “mental space-level metaphors” that were largely ignored in “standard” CMT, but are given an important role in extended CMT. These are the metaphors that represent actual, contextual meanings in a metaphorical usage event. Traditional CMT-type analysis cannot account for the emergence of such idiomatic meanings because the mappings, or correspondences, of standard CMT work on a single, generic level (frame-, domain-, or even image schema level). However, the contextual meanings of naturally used metaphors (including those of metaphorical idioms) are much more information-rich and specific. The conceptual metaphors on the image schema, domain, and frame levels are offline structures in long-term memory, whereas the conceptual metaphors on the mental space level occur only online in working memory. In online communication, speakers mobilize the static image schema-, domain-, and frame-level metaphors at the mental space level, where they create highly specific mental space-level metaphors. Given this framework, it becomes possible to explain how and why the four metaphorical idioms have different contextual meanings (as represented by different mental space-level metaphors), but, at the same time, why they also share certain conceptual metaphors on the frame-, domain-, or image schema-level. Additionally, we gain new insight into how the emergence of novel metaphorical idioms occurs with the help of and constrained by a previously existing large system of hierarchically arranged conceptual metaphors.

Autonomous Cargo Grabbing System for Drones Using Cameras and ROS

Abstract. With the rapid development of low-altitude economy, the functional requirements for logistics UAVs are constantly improving. In this paper, an unmanned aerial vehicle system (UAV) is proposed to realize autonomous grasping of goods. First of all, a new type of grasping device is proposed, which can be easily mounted on the UAV. The camera image stream mounted on the UAV was obtained through camera calibration and corrected. Subsequently, the object recognition algorithm was used to process the image frames, successfully identify the goods to be captured, and calculate the position and direction relationship between the UAV and the target cargo. Next, the speed of the drone is adjusted by the PID controller to achieve a stable landing above the target cargo. Then, the drone is equipped with a robotic claw innovatively designed by our team to complete the gripping of the goods. Subsequently, the drone lifted off and began to deliver cargo. Throughout the grabbing process, a laptop equipped with Ubuntu and ROS systems communicates with the drone via Wi-Fi. The feasibility of the whole system was proved by experiments.

Vibration displacement measurement of bridge structural models using image super-resolution reconstruction and visual object detection network

Abstract Visual vibration measurement has emerged in the field of structural health monitoring in recent years, but it still has some shortcomings in terms of resolution, recognition rate and real-time performance. Considering the three aspects of recovering high-frequency image details, improving the compactness of the target bounding box, and reducing the computational time, we use the constructed image super-resolution reconstruction model and target detection model to measure the vibration displacement of the bridge structural model. First, we integrate the Transformer module into the Unet network with a simple structure. The Swin and Global Transformer Unet (SGTU) module constructed in this form can reduce the computational cost while reconstructing the large-resolution feature map target, and it can sharply edge information of the vibration target. We use the framework of the YOLOv5 algorithm as the backbone, and use the GhostBottleneck (GB) module to reduce the time for convolution operations to generate similar features. In addition, the proposed DWCBottleneck (DWCB) fusion module is also able to achieve high-level semantic fusion and network depth expansion with minimal computational cost. Finally, the center point offset of the bounding box predicted by the model can be used to obtain the displacement offset of the object in the image sequence. The position information of the target in the first frame image is used as the reference frame for calculating the offset, and the vibration displacement of the flexible structure in the image coordinate system is obtained by calculating the deviation of the displacement between the remaining frames and the first frame. We perform qualitative and quantitative comparisons in three aspects: video super-resolution reconstruction, visual detection robustness, and sensor vibration measurement displacement using a homemade vibration image dataset. The time–frequency domain displacement curves regressed by the visual vibration measurement algorithm are compared with the curves acquired after accelerometer acquisition, indicating the necessity of super-resolution reconstruction in visual vibration measurement.

Estimation of direction and zero errors of satellite laser terminals in low-light conditions based on machine learning

In the assembly, launch, and on-orbit operation of satellite optical communication terminals, small deviations are difficult to avoid, which can lead to pointing errors and challenges to the establishment of optical communication links. To estimate the pointing errors of on-orbit satellite terminals, a calibration algorithm is developed based on lunar surface imagery. First, a feature extraction algorithm for low-light images is employed to process consecutive frames of low-light images to obtain a lunar surface feature map. Then, by combining the feature map and error estimation model, predictions of direction errors and zero errors were achieved. The ground validation results demonstrate the effectiveness and feasibility of the proposed on-orbit error estimation algorithm under low-signal-to-noise-ratio conditions.

Frontal plane mechanical leg alignment estimation from knee x-rays using deep learning

ObjectiveLower limb malalignment can complicate symptoms and accelerate knee osteoarthritis (OA), necessitating consideration in study population selection. In this study, we develop and validate a deep learning model that classifies leg alignment as “normal” or “malaligned” from knee antero-posterior (AP)/postero-anterior (PA) radiographs alone, using an adjustable hip-knee-ankle (HKA) angle threshold. Material and MethodsWe utilized 8,878 digital radiographs, including 6,181 AP/PA full-leg x-rays (LLRs) and 2,697 AP/PA knee x-rays (2,292 with positioning frame, 405 without). The model’s evaluation involved two steps: In step 1, the model’s predictions on knee images cropped from LLRs were compared against the ground truth from the original LLRs. In step 2, the model was tested on knee AP radiographs, using corresponding same-day LLRs as a proxy for ground truth. ResultsThe model effectively classified alignment, with step one achieving sensitivity and specificity of 0.92 for a threshold of 7.5°, and 0.90 and 0.85 for 5°. For positioning frame images, step two showed a sensitivity of 0.85 and specificity of 0.81 for 7.5°, and 0.79 and 0.74 for 5°. For non-positioning frame images, sensitivity and specificity were 0.91 and 0.83 for 7.5°, and 0.9 and 0.86 for 5°. ConclusionThe model developed in this study accurately classifies lower limb malalignment from AP/PA knee radiographs using adjustable thresholds, offering a practical alternative to LLRs. This can enhance the precision of study population selection and patient management.