Point Detection Research Articles

Transformer Network-Aided Relative Pose Estimation for Non-cooperative Spacecraft Using Vision Sensor

The objective of the proposed work is to perform monocular vision-based relative 6-DOF pose estimation of the non-cooperative target spacecraft relative to the chaser satellite in rendezvous operations. In this work, the convolutional neural network (CNN) is replaced by the high-resolution transformer network to predict the feature points of the target satellite. The self-attention mechanism inside the transformer provides the advantage of overcoming the inadequacies of the translation equivariance, 2D neighborhood awareness, and long-range dependencies in CNN. First, the 3D model of the target satellite is reconstructed using the inverse direct linear transform (IDLT) method. Then, the pose estimation pipeline is developed with a learning-based image-processing subsystem and geometric optimization of the pose solver. The image-processing subsystem performs target localization using CNN-based architecture. Then, the key points detection network performs regression to predict 2D key points using the transformer-based network. Afterward, the predicted key points based on their confidence scores are projected onto the corresponding 3D points, and the pose value is computed using the efficient perspective-n-point method. The pose is refined using the non-linear iterative Gauss–Newton method. The proposed architecture is trained and tested on the spacecraft pose estimation dataset and it shows superior accuracy both in translation and rotation values. The architecture has shown robustness against the drastically changing clutter background and light conditions in the space images due to the self-attention mechanism. Moreover, this method consumes less computation resources by using fewer floating-point operations and trainable parameters with low input image resolution.

Mixtures of regressions using matrix-variate heavy-tailed distributions

AbstractFinite mixtures of regressions (FMRs) are powerful clustering devices used in many regression-type analyses. Unfortunately, real data often present atypical observations that make the commonly adopted normality assumption of the mixture components inadequate. Thus, to robustify the FMR approach in a matrix-variate framework, we introduce ten FMRs based on the matrix-variate t and contaminated normal distributions. Furthermore, once one of our models is estimated and the observations are assigned to the groups, different procedures can be used for the detection of the atypical points in the data. An ECM algorithm is outlined for maximum likelihood parameter estimation. By using simulated data, we show the negative consequences (in terms of parameter estimates and inferred classification) of the wrong normality assumption in the presence of heavy-tailed clusters or noisy matrices. Such issues are properly addressed by our models instead. Additionally, over the same data, the atypical points detection procedures are also investigated. A real-data analysis concerning the relationship between greenhouse gas emissions and their determinants is conducted, and the behavior of our models in the presence of heterogeneity and atypical observations is discussed.

A novel immune-related lncRNA signature predicts the prognosis and immune landscape in ccRCC.

As one of the most common tumors, the pathogenesis and progression of clear cell renal cell carcinoma (ccRCC) in the immune microenvironment are still unknown. The differentially expressed immune-related lncRNA (DEirlncRNA) was screened through co-expression analysis and the limma package of R, which based on the ccRCC project of the TCGA database. Then, we designed the risk model by irlncRNA pairs. In RCC patients, we have compared the area under the curve, calculated the Akaike Information Criterion (AIC) value of the 5-year receiver operating characteristic curve, determined the cut-off point, and established the optimal model for distinguishing the high-risk group from the low-risk group. We used the model for immune system assessment, immune point detection and drug sensitivity analysis after verifying the feasibility of the above model through clinical features. In our study, 1541 irlncRNAs were included. 739 irlncRNAs were identified as DEirlncRNAs to construct irlncRNA pairs. Then, 38 candidate DEirlncRNA pairs were included in the best risk assessment model through improved LASSO regression analysis. As a result, we found that in addition to age and gender, T stage, M stage, N stage, grade and clinical stage are significantly related to risk. Moreover, univariate and multivariate Cox regression analysis results reveals that in addition to gender, age, grade, clinical stage and risk score are independent prognostic factors. The results show that patients in the high-risk group are positively correlated with tumor infiltrating immune cells when the above model is applied to the immune system. But they are negatively correlated with endothelial cells, macrophages M2, mast cell activation, and neutrophils. In addition, the risk model was positively correlated with overexpressed genes (CTLA, LAG3 and SETD2, P<0.05). Finally, risk models can also play as an important role in predicting the sensitivity of targeted drugs. The new risk model may be a new method to predict the prognosis and immune status of ccRCC.

Establishment of a 3D esthetic analysis workflow on 3D virtual patient and preliminary evaluation

BackgroundIn esthetic dentistry, a thorough esthetic analysis holds significant role in both diagnosing diseases and designing treatment plans. This study established a 3D esthetic analysis workflow based on 3D facial and dental models, and aimed to provide an imperative foundation for the artificial intelligent 3D analysis in future esthetic dentistry.MethodsThe established 3D esthetic analysis workflow includes the following steps: 1) key point detection, 2) coordinate system redetermination and 3) esthetic parameter calculation. The accuracy and reproducibility of this established workflow were evaluated by a self-controlled experiment (n = 15) in which 2D esthetic analysis and direct measurement were taken as control. Measurement differences between 3D and 2D analysis were evaluated with paired t-tests.Results3D esthetic analysis demonstrated high consistency and reliability (0.973 < ICC < 1.000). Compared with 2D measurements, the results from 3D esthetic measurements were closer to direct measurements regarding tooth-related esthetic parameters (P<0.05).ConclusionsThe 3D esthetic analysis workflow established for 3D virtual patients demonstrated a high level of consistency and reliability, better than 2D measurements in the precision of tooth-related parameter analysis. These findings indicate a highly promising outlook for achieving an objective, precise, and efficient esthetic analysis in the future, which is expected to result in a more streamlined and user-friendly digital design process.This study was registered with the Ethics Committee of Peking University School of Stomatology in September 2021 with the registration number PKUSSIRB-202168136.

Interactive simulations as a tool for logistics and maintenance of IFMIF-DONES

Pre-configured virtual reality (VR) simulations of the logistics and maintenance processes have proven to be useful for identifying potential design issues as well as planning operations during an early design phase of facility. But VR simulations can also be used to deeply explore the feasibility of these procedures in a more interactive manner, so that we can identify potential risks and difficulty levels from early stages and study different maintenance strategies to assist the maintenance worker during these procedures. This article presents a framework to design and validate logistics and maintenance procedures in complex facilities, such as the International Fusion Materials Irradiation Facility DEMO Oriented Neutron Source (IFMIF-DONES). Our framework begins with a preparatory phase where essential information about the procedures and Computer-Aided Design (CAD) models is compiled into a comprehensive Virtualization Task Document (VTD). Differently from previous work, this VTD allows representation of parallel tasks. We implement the interactive version of the virtual environment, where the different maintenance and logistics equipment, as well as a virtual maintenance worker is controlled by the user (the person executing the interactive simulation). We have validated this interactive framework with two simulations for the installation process of the Superconducting Radio Frequency Linear accelerator (SRF Linac) modules in IFMIF-DONES. In one simulation (the automatic one), the procedures are reproduced as they are planned, while in the second simulation (the interactive one) the user freely controls the movements of the moving parts of the crane, grab and release plant equipment, move platforms, etc. Based on our simulations, the interactive version allows easier detection of potential points of collisions as well as more precise assessment of the difficulty of the tasks to be performed.

Automatic diagnosis of depression based on attention mechanism and feature pyramid model.

Currently, most diagnoses of depression are evaluated by medical professionals, with the results of these evaluations influenced by the subjective judgment of physicians. Physiological studies have shown that depressed patients display facial movements, head posture, and gaze direction disorders. To accurately diagnose the degree of depression of patients, this paper proposes a comprehensive framework, Cross-Channel Attentional Depression Detection Network, which can automatically diagnose the degree of depression of patients by inputting information from the facial images of depressed patients. Specifically, the comprehensive framework is composed of three main modules: (1) Face key point detection and cropping for video images based on Multi-Task Convolutional Neural Network. (2) The improved Feature Pyramid Networks model can fuse shallow features and deep features in video images and reduce the loss of miniscule features. (3) A proposed Cross-Channel Attention Convolutional Neural Network can enhance the interaction between tensor channel layers. Compared to other methods for automatic depression identification, a superior method was obtained by conducting extensive experiments on the depression dataset AVEC 2014, where the Root Mean Square Error and the Mean Absolute Error were 8.65 and 6.66, respectively.

Computational methodology to support functional vision assessment in premature infants: A viability study.

Premature newborns have a higher risk of abnormal visual development and visual impairment. To develop a computational methodology to help assess functional vision in premature infants by tracking iris distances. This experimental study was carried out with children up to two years old. A pattern of image capture with the visual stimulus was proposed to evaluate visual functions of vertical and horizontal visual tracking, visual field, vestibulo-ocular reflex, and fixation. The participants' visual responses were filmed to compose a dataset and develop a detection algorithm using the OpenCV library allied with FaceMesh for the detection and selection of the face, detection of specific facial points and tracking of the iris positions is done. A feasibility study was also conducted from the videos processed by the software. Forty-one children of different ages and diagnoses participated in the experimental study, forming a robust dataset. The software resulted in the tracking of iris positions during visual function evaluation stimuli. Furthermore, in the feasibility study, 8 children participated, divided into Pre-term and Term groups. There was no statistical difference in any visual variable analyzed in the comparison between groups. The computational methodology developed was able to track the distances traveled by the iris, and thus can be used to help assess visual function in children.

A self-supervised contrastive change point detection method for industrial time series

Manufacturing process monitoring is crucial to ensure production quality. This paper formulates the detection problem of abnormal changes in the manufacturing process as the change point detection (CPD) problem for the industrial temporal data. The premise of known data property and sufficient data annotations in existing CPD methods limits their application in the complex manufacturing process. Therefore, a self-supervised and non-parametric CPD method based on temporal trend-seasonal feature decomposition and contrastive learning (CoCPD) is proposed. CoCPD aims to solve CPD problem in an online manner. By bringing the representations of time series segments with similar properties in the feature space closer, our model can sensitively distinguish the change points that do not conform to either historical data distribution or temporal continuity. The proposed CoCPD is validated by a real-world body-in-white production case and compared with 10 state-of-the-art CPD methods. Overall, CoCPD achieves promising results by Precision 70.6%, Recall 68.8%, and the mean absolute error (MAE) 8.27. With the ability to rival the best offline baselines, CoCPD outperforms online baseline methods with improvements in Precision, Recall and MAE by 14.90%, 11.93% and 43.93%, respectively. Experiment results demonstrate that CoCPD can detect abnormal changes timely and accurately.

ERROR ANALYSIS OF VISUAL ODOMETRY FOR A SMALL SIZE UNMANNED AERIAL VEHICLE

Abstract. Usage of small size Unmanned Aerial Vehicle (UAV) with autonomous flight capability became widespread at both civil and military applications because of its low costs and ease of use. However, inertial or GPS based positioning and orientation sensors can be disabled at battlefields and the UAV losses its path in a short time. Visual odometry becomes a solution for the aforementioned hassle. Real-time detection of ground control points, matching the same control points at the stereo pair images and correcting the position and orientation data with least square adjustment are the challenges of visual odometry. In this study, error analysis of position and orientation of a UAV flying through mountainous region which cannot obtain any augmenting data for position and orientation is conducted by error propagation law. The flight of UAV is simulated with exact initial position and orientation data. Optic images of ground obtained by nadir directed camera are georeferenced using the digital elevation model of the region, interior and exterior camera parameters. The digital elevation model is used to correct the relief displacement. The stereo-pair image is obtained when the UAV flies 200 m and image coordinates of the common control points are detected by colinearity equations. Position and orientation of UAV is corrected by least square adjustment and the process is repeated for each obtained image acquired at 200 m interval. The analysis revealed that the precisions of horizontal and vertical positioning becomes 75 and 200 meter, respectively. The precision of roll angle becomes worse than 0.5 degree, while the precisions of pitch and yaw angle are estimate to be better that 0.1 degree.

Modeling Shallow Landslide Runout Distance in Eocene Flysch Facies Using Empirical–Statistical Models (Western Black Sea Region of Türkiye)

Uncertainties related to runout distances in shallow landslide analyses may not only affect lives but may also result in economic losses. Owing to the increase in shallow landslides, which are especially triggered by heavy rainfall, runout distances have been investigated to decipher whether applications of a functional runout distance are feasible. This paper aims to give insights into the modeling of the shallow landslide runout probability in Eocene flysch facies in the Western Black Sea region of Türkiye. There are two main stages in this study—which are dominated by empirical models, the detection of initiation points, and propagation—which help us to understand and visualize the possible runout distances in the study area. Shallow landslide initiation point determination using machine learning has a critical role in the ordered tasks in this study. Modified Holmgren and simplified friction-limited model (SFLM) parameters were applied to provide a good approximation of runout distances during the propagation stage using Flow-R software. The empirical model parameters suggested for debris flows and shallow landslides were investigated comparatively. The runout distance models had approximately the same performance depending on the debris flow and shallow landslide parameters. While the impacted total runout areas for the debris flow parameters were predicted to amount to approximately 146 km2, the impacted total runout areas for the shallow landslide parameters were estimated to be about 101 km2. Considering the inclusion of the RCP 4.5 and RCP 8.5 precipitation scenarios in the analyses, this also shows that the shallow landslide and debris flow runout distance impact areas will decrease. The investigation of runout distance analyses and the inclusion of the RCP scenarios in the runout analyses are highly intriguing for landslide researchers.

Investigation on high temperature point detection of spontaneous combustion of loose coal based on optimal acoustic signal

Selecting sound source signals in acoustic temperature measurement technology is particularly important and is a key to improving the accuracy of acoustic temperature measurements. Pseudorandom, linearly swept, and pulsed signals are selected as research objects for this study. The decay of the three signals as they propagate through a loose coal, the frequency band and the period of the linearly swept signal are analyzed. The results showed that the attenuation coefficient of the linear sweep signal is less sensitive to temperature, and the attenuation coefficient of the low-frequency sound wave is smaller. When the lower limit of the frequency band of the sweep signal is closer to the upper limit of the frequency band, the main peak value of the cross-correlation coefficient is smaller. The main peak of the cross-correlation curve of low-band narrowband signals is greater than that of high-band narrowband signals. The cross-correlation effect is more significant for the 600–1000 Hz sweep signal. Moreover, the strongest effect is determined when the period is 0.1 s. Finally, the temperature of anthracite loose coal was measured according to the optimal signal. The maximum absolute error in the measurement results was 1.23 °C, and the maximum relative error was 4.22%.

Shape Recognition and Corner Points Detection in 2D Drawings Using a Machine Learning Long Short-Term Memory (LSTM) Approach

Creating a 2D geometry model from an image poses challenges for CAD users due to factors such as noise, segmentation difficulties, complex geometric structures, scale and perspective variations, and the need for CAD system compatibility. In this paper, we propose a novel deep learning approach utilizing Long-Short Term Memory (LSTM) to address these challenges. Our approach decomposes the shapes in the images into line and curve segments and accurately locates their intersection points. To enhance the model’s performance, we introduce two distinct types of features (angle and curvature features) and optimize the model through hyperparameter tuning. The resulting model exhibits robustness against noise, varying image sizes, and can effectively locate different types of intersection points. To evaluate the proposed model, we have developed a Python-based software and conducted experiments on a dataset comprising of 200 shapes with seven different resolutions. Comparative analysis against a state-of-the- art method (TCVD) from the literature demonstrates that our approach achieves higher accuracy in terms of line, curve, and intersection point detection.

Combined effect mechanism of linear loading and disturbance with different amplitudes on sandstone

To comprehend the stress state and response characteristics of materials under complex conditions, researchers have decomposed stress states into fundamental paths and investigated diverse path combinations. To ensure comparability, four identical samples were carefully selected from a pool of 100 samples using ultrasonic tests based on the wave speed and waveform characteristics. These samples underwent specially designed stress paths to analyze the combined effects of linear loading and perturbation. Our result analysis centred on the perturbation amplitude and stress levels during composite action, revealing intricate relationships between the stress levels, strain, and nonlinear/linear energy evolution under complex stress paths. Simultaneously, 3D surface fractures were precisely reconstructed using the YOLOv5 and FAST feature point detection algorithms, elucidating the evolving patterns of the fractures. As a result of our study, the rotation trend of the main fracture was validated by integrating mechanics and P-wave reflection rules. Notably, our experimental results closely aligned with the theoretical predictions, showing the reliability of our study. These findings can significantly contribute to guiding safety protocols in the field of underground engineering.

One level deep convolutional neural network for facial key points detection

Facial landmark detection has a lot of applications in face recognition, face alignment, facial expression recognition, video surveillance and security systems. In the existing literature, there are multiple methods utilizing convolutional neural networks (CNNs) that address this problem in various ways. In many cases, the models use a tree-like structure of CNNs to achieve better results. This paper proposes a combination of three parallel deep convolutional neural networks (DCNNs) to estimate the accurate localization of each keypoint. The first one focuses on the whole face to outperform five points, including the eyes, nose, and mouth corners. The second one focuses on the eyes-nose parts to outperform three points, specifically the eyes and nose. The last one focuses on the nose-mouth parts to outperform three points, namely the nose and mouth corners. Further, we combine all outputs of the three DCNNs and take the average value of each detected key point as the final output. In the first step, we improvthe the parameter efficiency and accuracy of each DCNNs through a set of experiments using the labeled face parts in-the-wild database (LFPW) and the helen facial feature dataset (Helen). Then, we demonstrate that our approach yields more accurate estimations of facial key points than two state-of-the-art methods and commercial software in terms of accuracy.

Change point detection in dynamic Gaussian graphical models: The impact of COVID-19 pandemic on the U.S. stock market

Change point detection in dynamic Gaussian graphical models: The impact of COVID-19 pandemic on the U.S. stock market

Problem solved: A reliable, deterministic method for JPEG fragmentation point detection

Recovery of deleted JPEG files is severely hindered by fragmentation. Current state-of-the-art JPEG file recovery methods rely on content-based approaches. That is, they consider whether a sequence of bytes translates into a consistent picture based on its visual representation, treating fragmentation indirectly, with varying results. In contrast, in this paper, we focus on identifying fragmentation points on bit-level, that is, identifying whether a candidate next block of bytes is a valid extension of the current JPEG. Concretely, we extend, implement and exhaustively test a novel deterministic algorithm for finding fragmentation points in JPEGs. Even in the worst case scenario, our implementation finds over 99.4 % of fragmentation points within 4 kB – i.e., within the standard block size on NTFS and exFAT file systems. As such, we consider the problem of detecting JPEG fragmentation points solved.

An encoding approach for stable change point detection

Without imposing prior distributional knowledge underlying multivariate time series of interest, we propose a nonparametric change-point detection approach to estimate the number of change points and their locations along the temporal axis. We develop a structural subsampling procedure such that the observations are encoded into multiple sequences of Bernoulli variables. A maximum likelihood approach in conjunction with a newly developed searching algorithm is implemented to detect change points on each Bernoulli process separately. Then, aggregation statistics are proposed to collectively synthesize change-point results from all individual univariate time series into consistent and stable location estimations. We also study a weighting strategy to measure the degree of relevance for different subsampled groups. Simulation studies are conducted and shown that the proposed change-point methodology for multivariate time series has favorable performance comparing with currently available state-of-the-art nonparametric methods under various settings with different degrees of complexity. Real data analyses are finally performed on categorical, ordinal, and continuous time series taken from fields of genetics, climate, and finance.

Individual Tree Segmentation Based on Seed Points Detected by an Adaptive Crown Shaped Algorithm Using UAV-LiDAR Data

Unmanned aerial vehicle–light detection and ranging (UAV-LiDAR) provides a convenient and economical means of forest data acquisition that can penetrate canopy gaps to obtain abundant ground information, offering huge potential in forest inventory. Individual tree segmentation is a prerequisite to obtain individual tree details but is highly dependent on the accuracy of seed point detection. However, most of the existing methods, such as the local maximum (LM) and CHM-based methods, are strongly dependent on the window size, and, for individual tree segmentation, they can result in over-segmentation and under-segmentation, especially in natural forests. In this paper, we propose an adaptive crown shaped algorithm for individual tree segmentation without consideration of the window size. It was implemented in four plots with different forest types and topographies (i.e., planted coniferous forest with flat terrain, coniferous forest with sloping terrain, mixed forest with flat terrain and broadleaf forest with flat terrain). First, the normalized point clouds were rotated and blocked at multiple angles to extract the surface points of the forest. Then, the crown boundaries were delineated by analyzing the crown profiles to extract the treetops as seed points. Finally, a region growing method based on seed points was applied for individual tree segmentation. Our results showed that the recall, precision and F1-score of seed point detection reached 91.6%, 95.9% and 0.94, respectively, and that the accuracy rates for individual tree segmentation for the four plots were 87.7%, 80.6%, 73.2% and 70.5%, respectively. Our proposed method can effectively detect seed points via the adaptive crown shaped algorithm and reduce the impacts of elongated branches by applying distance thresholds between trees, enhancing the accuracy of seed point detection and subsequently improving the precision of individual tree segmentation. In addition, the proposed algorithm demonstrated superior performance in comparison to LM and CHM-based methods for the calculation of seed points, as well as outperforming PCS in individual tree segmentation. The proposed method demonstrates effectiveness and feasibility in dense forests and natural forests, providing an important reference for future research on seed point detection and individual tree segmentation.

Seasonal dynamics of fallow and cropping lands in the broadacre cropping region of Australia

Fallowing is an important strategy for enhancing soil health, water harvesting and crop yields, thus improving sustainability and reducing production risks in dryland farming systems in Australia. However, accurate data regarding the location, frequency, extent, and duration of fallow land is not readily available at high spatio-temporal resolutions before and during a cropping season. As a result, continental maps depicting seasonal dynamics of fallow and cropping lands and their responses to climate change and human activities remain missing. This study set out to develop an automated approach to discriminate fallow areas from cropping areas within Australian broadacre cropping region. This was done by applying a mathematical algorithm of turning point detection technique to a curve fitted vegetation index time series from 2016 to 2022, derived from high spatial (10 m) and temporal (5-days) resolution Sentinel-2 data. Specifically, we aimed to derive: (i) 5-day revisit fallow/cropping map layers; (ii) key attributes of the fallow and cropping periods (e.g., start, end, duration); (iii) cropping intensity and area. The proposed approach yielded a high and significant overall accuracy, surpassing 92% with substantial balanced accuracy (>0.9) against >3000 fields for individual winter and summer seasons across Australia. In addition, this study's temporal and geographical outputs, encompassing seasonal attributes, cropping intensity and cropping areas, robustly enhanced the understanding of seasonal cropping dynamics and historical shifts in dryland farming practices. Findings derived from this analysis aligned well with extreme climatic events and changes in crop activities adopted in response to such events. Future research will aim to extract key seasonal dynamics attributes influenced by cropping practices, enhancing the conversion of high-resolution earth observation data into actionable industry knowledge.

Automating Ground Control Point Detection in Drone Imagery: From Computer Vision to Deep Learning

Drone-based photogrammetry typically requires the task of georeferencing aerial images by detecting the center of Ground Control Points (GCPs) placed in the field. Since this is a very labor-intensive task, it could benefit greatly from automation. In this study, we explore the extent to which traditional computer vision approaches can be generalized to deal with variability in real-world drone data sets and focus on training different residual neural networks (ResNet) to improve generalization. The models were trained to detect single keypoints of fixed-sized image tiles with a historic collection of drone-based Red–Green–Blue (RGB) images with black and white GCP markers in which the center was manually labeled by experienced photogrammetry operators. Different depths of ResNets and various hyperparameters (learning rate, batch size) were tested. The best results reached sub-pixel accuracy with a mean absolute error of 0.586. The paper demonstrates that this approach to drone-based mapping is a promising and effective way to reduce the human workload required for georeferencing aerial images.