Objective Estimation Research Articles

6-DoF Pose Estimation from Single RGB Image and CAD Model Retrieval Using Feature Similarity Measurement

This study presents six degrees of freedom (6-DoF) pose estimation of an object from a single RGB image and retrieval of the matching CAD model by measuring the similarity between RGB and CAD rendering images. The 6-DoF pose estimation of an RGB object is one of the important techniques in 3D computer vision. However, in addition to 6-DoF pose estimation, retrieval and alignment of the matching CAD model with the RGB object should be performed for various industrial applications such as eXtended Reality (XR), Augmented Reality (AR), robot’s pick and place, and so on. This paper addresses 6-DoF pose estimation and CAD model retrieval problems simultaneously and quantitatively analyzes how much the 6-DoF pose estimation affects the CAD model retrieval performance. This study consists of two main steps. The first step is 6-DoF pose estimation based on the PoseContrast network. We enhance the structure of PoseConstrast by adding variance uncertainty weight and feature attention modules. The second step is the retrieval of the matching CAD model by an image similarity measurement between the CAD rendering and the RGB object. In our experiments, we used 2000 RGB images collected from Google and Bing search engines and 100 CAD models from ShapeNetCore. The Pascal3D+ dataset is used to train the pose estimation network and DELF features are used for the similarity measurement. Comprehensive ablation studies about the proposed network show the quantitative performance analysis with respect to the baseline model. Experimental results show that the pose estimation performance has a positive correlation with the CAD retrieval performance.

TagRecon: Fine-Grained 3D Reconstruction of Multiple Tagged Packages via RFID Systems

To meet the new requirements of Industry 4.0, the logistics field has introduced 3D reconstruction technology. Computer vision-based solutions face challenges like bad lighting conditions and line-of-sight constraints. Meanwhile, the widespread adoption of RFID tags in supply chains offers an opportunity to enhance current reconstruction methods. In this paper, we propose TagRecon, a fine-grained multi-object 3D reconstruction scheme utilizing well-deployed RFIDs. Specifically, TagRecon transforms the task of reconstruction into a problem of estimating 3D bounding boxes for tagged packages. By placing dual anchor tags on each target package, TagRecon enables accurate inference of the package’s translation and rotation using RFID-based localization and orientation sensing. Our scheme introduces a novel method to estimate rotations and translations for tagged packages, utilizing the known geometric relationship of anchor tags. Besides, to achieve simultaneous reconstruction of multiple packages, we manage to match tags from various packages through the correlation between anchor tag pairs. As far as we know, this is the first RFID-based solution that can simultaneously realize 3D translation and rotation estimation of multiple objects to a fine granularity. Experiments validate TagRecon achieves a 28.0 cm translation error and 6.8°, 6.0°, and 7.5° rotation errors for roll, pitch, and yaw angles on average.

Motion and Inertia Estimation for Non-Cooperative Space Objects During Long-Term Occlusion Based on UKF-GP

This study addresses the motion and inertia parameter estimation problem of a torque-free, tumbling, non-cooperative space object (target) under long-term occlusions. To solve this problem, we employ a data-driven Gaussian process (GP) to simulate sensor measurements. In particular, we implement the multi-output GP to predict the projection measurements of a stereo-camera system onboard a chaser spacecraft. A product kernel, consisting of two periodic kernels, is used in the GP models to capture the periodic trends from non-periodic projection data. The initial guesses for the periodicity hyper-parameters of the GP models are intelligently derived from fast Fourier transform (FFT) analysis of the projection data. Additionally, we propose an unscented Kalman filter–Gaussian process (UKF-GP) fusion algorithm for target motion and inertia parameter estimation. The predicted projections from the GP models and their derivatives are used as the pseudo-measurements for UKF-GP during long-term occlusion. Results from Monte Carlo (MC) simulations demonstrate that, for varying tumbling frequencies, the UKF-GP can accurately estimate the target’s motion variables over hundreds of seconds, a capability the conventional UKF algorithm lacks.

Noise amplification and ill-convergence of Richardson-Lucy deconvolution

Richardson-Lucy (RL) deconvolution optimizes the likelihood of the object estimate for an incoherent imaging system. It can offer an increase in contrast, but converges poorly, and shows enhancement of noise as the iteration progresses. We have discovered the underlying reason for this problematic convergence behaviour using a Cramér Rao Lower Bound (CRLB) analysis. An analytical expression for the CRLB diverges for spatial frequency components that approach the diffraction limit from below. The resulting mean noise variance per pixel diverges for large images. These results imply that a regular optimum of the likelihood does not exist, and that RL deconvolution is necessarily ill-convergent.

JWST ERS Program Q3D: The pitfalls of virial black hole mass constraints shown for a z ∼ 3 quasar with an ultramassive host

We present observations with the Mid-InfraRed Instrument (MIRI) and Near-InfraRed Spectrograph (NIRSpec) on board the James Webb Space Telescope (JWST), targeting the extremely red quasar J165202.64+172852.3 at z = 2.948 (dubbed J1652). As one of the most luminous quasars known to date, it drives powerful outflows and hosts a clumpy starburst, in the midst of several interacting companions. We estimated the black hole (BH) mass of the system based on the broad Hα and Hβ lines, as well as the broad Paβ emission in the infrared and Mg II in the ultraviolet. We recovered a very broad range of mass estimates, with individual constraints ranging between log MBH ∼ 9 and 10.2, which is extended further if we impose a uniform broad line region geometry at all wavelengths. The large spread may be caused by several factors: uncertainties on measurements (insufficient sensitivity to detect the broadest component of the faint Paschen β line, spectral blending, ambiguities in the broad or narrow component distinction, etc.), lack of virial equilibrium, and uncertainties on the luminosity-inferred size of the broad line region (BLR). The exotic nature of our target (luminous, starburst, powerful outflows, high accretion rate, and dusty centre) is another likely contribution to the large uncertainties. We broadly constrained the stellar mass of J1652 by fitting the spectral energy distribution, which suggests that the host is extremely massive, at ∼1012.1 M⊙, with a 1.1 dex uncertainty at > 1 dex above the characteristic mass of the Schechter fit to the z = 3 stellar mass function. Notably, J1652’s central BH might be interpreted as being either over-massive or in line with the BH mass–stellar mass relation, depending on the choice of assumptions. The recovered Eddington ratio varies accordingly, but it exceeds 10% in any case. We set our results into context by providing an extensive overview and discussion of recent literature results and their associated assumptions. Our findings provide an important demonstration of the uncertainties inherent in the virial BH mass estimates of individual objects, which are of particular relevance in the JWST era, given the increasing number of studies on rapidly accreting quasars at high redshift.

Clinical Characteristics of Patients With Symptomatic Nasolacrimal Duct Stenosis.

To characterize symptoms and signs for patients with tearing eye(s) and ipsilateral nasolacrimal duct stenosis (NLDS), as defined by delayed fluorescein disappearance test and ocular reflux of saline during gentle irrigation of a patent drainage system. Retrospective case-note review of a consistent grading of 4 symptoms and 7 signs, together with estimates of the degree of fluid reflux and nasal fluid passage on gentle saline syringing. Characteristics, including gender differences, were compared for unilateral or bilateral symptoms. A side-to-side comparison was performed in unilateral cases, and assessed for concordance of signs and/or symptoms. The average age of presentation was 62.4 years in 386 patients (37% male), with a third having unilateral symptoms. Systemic atopy (22%) and chronic nasal disease (27%) were frequent. Patients with unilateral symptoms were significantly younger (males 9.5, females 5.5 years; p < 0.000001) and had shorter symptom duration (p = 0.0025). Three-quarters of asymptomatic sides had objective evidence of nasolacrimal duct stenosis, and there was significant side-to-side concordance for 7/9 clinical signs. Among 640 symptomatic systems, many of the presenting (subjective) symptoms and/or objective signs showed a significant direct or inverse correlation. The lack of laterality- or gender bias for symptoms and signs suggests that patients with nasolacrimal duct stenosis might seek treatment for the epiphora per se, rather than for issues with ocular dominance or visual requirements. The close correlation between subjective symptom-severity and objective estimates of signs suggests that thorough clinical assessment can be very reliable, and that several factors probably contribute to symptoms in these patients.

Shared visuo-tactile interactive perception for robust object pose estimation

Shared perception between robotic systems significantly enhances their ability to understand and interact with their environment, leading to improved performance and efficiency in various applications. In this work, we present a novel full-fledged framework for robotic systems to interactively share their visuo-tactile perception for the robust pose estimation of novel objects in dense clutter. This is demonstrated with a two-robot team sharing their visuo-tactile scene representation which then declutters the scene using interactive perception and precisely estimates the 6 Degrees-of-Freedom (DoF) pose and 3 DoF scale of a target unknown object. This is achieved with the Stochastic Translation-Invariant Quaternion Filter (S-TIQF), a novel Bayesian filtering method with robust stochastic optimization for estimating the globally optimal pose of a target object. S-TIQF is also deployed to perform in situ visuo-tactile hand-eye calibration, since shared perception requires accurate extrinsic calibration between the two different sensing modalities, tactile and visual. Finally, we develop a novel active shared visuo-tactile representation and object reconstruction method employing a joint information gain criterion to improve the sample efficiency of the robot actions. To validate the effectiveness of our approach, we perform extensive experiments across standard datasets for pose estimation, as well as real-robot experiments with opaque, transparent and specular objects in randomised clutter settings and comprehensive comparison with other state-of-the-art approaches. Our experiments indicate that our approach outperforms state-of-the-art methods in terms of pose estimation accuracy for dense visual and sparse tactile point clouds.

Objective Visual Acuity Estimates in Amblyopia Are More Accurate With Optotype-Based P300 Than With VEP Measurements.

Traditional visual acuity (VA) measurements depend on subjective responses, which can be unreliable, especially with uncooperative participants. Objective measurements with visual evoked potentials (VEP) address this issue but can overestimate VA in amblyopia. This study aims to establish the P300 component of the event-related potential as an objective VA test for amblyopia and compare its performance to subjective (psychophysical) and VEP-based VA estimates. Psychophysical, VEP-based, and P300-based VA estimates were obtained for amblyopic and fellow eyes of 18 participants (aged 19-65) in a bicentric study. VEP-based VA was determined from the spatial frequency threshold derived from occipital cortex pattern-pulse responses to check-sizes ranging from 0.048° to 8.95°. P300 responses were collected using visual oddball sequences with circular optotypes. The threshold was estimated from the sigmoid function of parietal P300 amplitude versus optotype gap size. Mean VA values for amblyopic eyes were compared across methods. VEP-based VA of the amblyopic eyes overestimated psychophysical VA by 0.18 ± 0.06 logMAR (P = 0.0016). In contrast, P300-based VA showed no significant difference from psychophysical VA (0.00 ± 0.04 logMAR, P > 0.05). In amblyopia, P300-based optotype VA aligns more closely with psychophysical VA than VEP-based VA, suggesting that P300-based VA is a valid objective alternative for estimating VA in amblyopic eyes. This study highlights the potential of P300-based VA testing as a reliable and objective method for assessing VA in amblyopic eyes, offering a promising tool for clinical and research applications where traditional methods fall short.

Cormorant predation in fyke net fishing: The direct effects of a protected bird on coastal commercial fishing

The population size of great cormorants, Phalacrocorax carbo sinensis, has risen steeply in the Baltic Sea over the past 40 years. The growing population has resulted in polarized conflicts between conservation and coastal fisheries due to the losses cormorants may inflict on fisheries. Mitigation of the conflicts requires objective estimates of true losses to fisheries, but quantitative research on losses has been scarce. We used continuous video-recordings to systematically quantify cormorant visits and their activity at 15 fyke nets during the 2022–2023 breeding and post breeding seasons. More than 2400 h of video footage were recorded, in which cormorants were found for 664 h. We also quantified the frequency of fish injured by birds in coastal fishing catches using data from the EU Fisheries Data Collection Program including data from fyke nets and gill nets. Our results show that cormorants frequently foraged in open, floating fyke nets but relatively rarely in submerged nets, leading to significantly higher losses in the former. Monitoring data from fyke and gill net catches covering the entire Finnish coast revealed that the proportion of bird-injured fish in catches is very modest (0.5 %) but can be considerable in individual catches. Finally, results indicate that cormorant visits and the proportion of injured fish in the catch tend to increase when distance to the nearest cormorant colony decreases. We conclude that the losses caused by birds are generally modest, except in open fyke nets where cormorants may conduct hundreds of dives and catch dozens of fish a day. Our study shows that cormorant depredation is highly variable in time and space, but also partly manageable by selecting gear that conforms to local cormorant pressures. We underline the importance of systematic scientific research when measuring damage caused by cormorants and ask for evidence-based political strategies to mitigate perceived cormorant problems.

Neural Basis of Perceptual Surface Qualities and Materials: Evidence from EEG Decoding

Abstract The human visual system can easily recognize object material categories and estimate surface properties such as glossiness and smoothness. Recent psychophysical and computational studies suggest that the material perception depends on global feature statistics. To elucidate dynamic neural representations underlying surface property and material perception in humans, we measured visual evoked potentials (VEPs) for 191 natural images consisting of 20 categories of materials and then classified material categories and surface properties from the VEPs. As a result, we found that material categories were correctly classified by the VEPs even at latencies of 150 msec or less. The apparent surface properties were also significantly classified within 175 msec (lightness, colorfulness, and smoothness) and after 200 msec (glossiness, hardness, and heaviness). The subsequent reverse-correlation analysis revealed that the VEPs at these latencies are highly correlated with low- and high-level global feature statistics of the surface images, indicating that neural activities about such global features are reflected in the VEPs. Moreover, by using deep generative models (multimodal variational autoencoder models) to reconstruct surface images from the VEPs via style information, we demonstrated that the reconstructed surface images are judged by observers to have very similar material categories and surface properties as the original natural surfaces. These results support the notion that neural representations of statistical features in the early cortical response play a crucial role in the perception and recognition of surface materials in humans.

Contour-based object forecasting for autonomous driving

A novel algorithm, called contour-based object forecasting (COF), to simultaneously perform contour-based segmentation and depth estimation of objects in future frames in autonomous driving systems is proposed in this paper. The proposed algorithm consists of encoding, future forecasting, decoding, and 3D rendering stages. First, we extract the features of observed frames, including past and current frames. Second, from these causal features, we predict the features of future frames using the future forecast module. Third, we decode the predicted features into contour and depth estimates. We obtain object depth maps aligned with segmentation masks via the depth completion using the predicted contours. Finally, from the prediction results, we render the forecasted objects in a 3D space. Experimental results demonstrate that the proposed algorithm reliably forecasts the contours and depths of objects in future frames and that the 3D rendering results intuitively visualize the future locations of the objects.

EBFA-6D: End-to-End Transparent Object 6D Pose Estimation Based on a Boundary Feature Augmented Mechanism.

Transparent objects, commonly encountered in everyday environments, present significant challenges for 6D pose estimation due to their unique optical properties. The lack of inherent texture and color complicates traditional vision methods, while the transparency prevents depth sensors from accurately capturing geometric details. We propose EBFA-6D, a novel end-to-end 6D pose estimation framework that directly predicts the 6D poses of transparent objects from a single RGB image. To overcome the challenges introduced by transparency, we leverage the high contrast at object boundaries inherent to transparent objects by proposing a boundary feature augmented mechanism. We further conduct a bottom-up feature fusion to enhance the location capability of EBFA-6D. EBFA-6D is evaluated on the ClearPose dataset, outperforming the existing methods in accuracy while achieving an inference speed near real-time. The results demonstrate that EBFA-6D provides an efficient and effective solution for accurate 6D pose estimation of transparent objects.

A comprehensive RGB-D dataset for 6D pose estimation for industrial robots pick and place: Creation and real-world validation

In the field of robotic grasping, 2D pose estimation algorithms are outdated and insufficient for modern requirements. Transitioning to 6D pose estimation of objects offers, particularly through deep learning methods, significantly improved performance. However, most high-performance 6D algorithms lack publicly disclosed methods for creating the necessary datasets, presenting challenges for researchers. This study introduces a methodology for creating a sample dataset for 6D pose estimation, addressing the challenges researchers face when applying these algorithms to specific projects. RGB and depth images are captured using Intel® RealSense™ Depth D435 camera, forming the foundation for accurately determining the pose of each object in the dataset. A CAD model along with accompanying metadata files, is generated to provide a complete dataset. The sample dataset was tested on two algorithms: EfficientPose and FFB6D, achieving accuracy rates of 97.05 % and 98.09 % respectively. These results indicate that the dataset is both effective and applicable to real-world robotic grasping tasks. Our research offers substantial practical value, enabling researchers and engineers to easily apply state-of-the-art 6D pose estimation algorithms to fields such as conveyor belt robotic picking, medical automation, and various other applications.

Words versus Strands: Reliability and Stability of Concordance Rates of Self-Reported and Hair-Analyzed Substance Use of Young Adults over Time

Introduction: Population-level substance use research primarily relies on self-reports, which often underestimate actual use. Hair analyses offer a more objective estimate; however, longitudinal studies examining concordance are lacking. Previous studies showed that specific psychological and behavioral characteristics are associated with a higher likelihood of underreporting substance use, but the longitudinal stability of these associations remains unclear. We compared the prevalence of illegal and non-medical prescription substance use assessed with self-reports and hair analyses and predicted underreporting across two time points. Methods: Data were drawn from a community cohort study. At the first time point, the sample with self-report and hair analysis comprised 1,002 participants (Mage = 20.6 [SD = 0.38] years, 50.2% female), of which 761 (Mage = 24.5 [SD = 0.38] years, 48.3% female) also provided hair at the second time point. We compared substance use 3-month prevalence rates assessed by self-reports and hair analyses for the most frequent substances cannabis/tetrahydrocannabinol (THC), amphetamines, Ecstasy/3,4-methylenedioxymethamphetamine (MDMA), cocaine, ketamine, codeine, and opioid painkillers. Binary logistic regressions were conducted to test behavioral and psychological predictors of underreporting. Results: Self-reported past-year prevalence rates of non-medical substance use were high, specifically for cannabis (56% prevalence rate at age 20/49% at age 24), Ecstasy (13%/14%), codeine (13%/11%), cocaine (12%/13%), and opioid painkillers (4%/11%). Comparing self-report and hair-analysis 3-month prevalence rates over time, consistent underreporting (similar underreporting rates between time points and investigation of false negatives) was observed for daily cannabis (22%/23%), Ecstasy/MDMA (41%/52%), cocaine (30%/60%), ketamine (61%/72%), and codeine use (48%/51%). Underreporting of Ecstasy/MDMA, cocaine, ketamine, and opioid painkillers significantly increased. Contrarily, weekly to daily cannabis (31%/18%), amphetamine (95%/11%), and opioid painkiller use (12%/66%) were overreported. Hair analysis-derived 3-month prevalence rates of cocaine (9%/23%) and ketamine (2%/6%) strongly increased over time, while decreasing for codeine (11%/8%). Balanced accuracies were higher for hair analysis compared to self-reports for daily cannabis, Ecstasy/MDMA, cocaine, ketamine, and codeine but lower for weekly to daily cannabis and amphetamines, while fairly similar for opioid painkillers. Accuracy metrics were largely stable for cannabis measures but partially varied over time for other substances, which was likely driven by the large changes in underreporting. False negative reports were associated across both time points, indicating an intra-individual consistency of underreporting. At both time points, delinquency and attention-deficit hyperactivity disorder symptoms were associated with an increased likelihood of accurately reporting cocaine use, while internalizing symptoms increased the likelihood of accurately reporting codeine use. Conclusion: Consistent and changeable underreporting emphasizes the importance of objective substance use assessments, specifically for studies investigating cocaine, Ecstasy/MDMA, ketamine, and codeine.

Enhancing manual inspection in semiconductor manufacturing with integrated augmented reality solutions

On-site routine inspection often remains a manual operation in the semiconductor manufacturing industry because implementing automated solutions can be costly and technically challenging in such a highly controlled and complex environment. The manual inspection is prone to errors due to the impact of demanding physical and mental workloads. This paper presents an integrated Augmented Reality (AR) solution developed to assist manual inspection tasks in the supporting areas of semiconductor manufacturing, referred to as the sub-fab. The solution is accessible to a human worker wearing an AR headset during the inspection process at the location. We propose a system framework to deploy computational intelligences of varying granularity provided by the solution across cloud, edge, and device levels, accommodating constraints within the sub-fab. A machine maintenance module helps estimate and monitor the health condition of running scrubbers. Incorrect intentions performed by the worker on the scrubber control panel are detected through hand gesture recognition. This instantly prompts warning messages in the AR headset to prevent subsequent wrong actions. The solution can also identify abnormal device states through 6D pose estimation of objects enabled by machine learning models. A test scenario demonstrates how these functional features enhance the inspection efficiency and quality by reducing human workloads. This work demonstrates that semiconductor manufacturing may require AR-assisted functions different from those needed or common in other industrial sectors. It also highlights the potential of AR technology for reducing operational human errors in manual tasks.

TDOcc: Exploit machine learning and big data in multi-view 3D occupancy prediction

With the advancement of machine learning and big data technologies, BEV (Bird’s Eye View)-based methodologies have recently achieved significant breakthroughs in multi-view 3D occupancy prediction tasks. However, BEV (Bird’s Eye View)-centric 3D occupancy prediction continues to grapple with feature representation and annotation costs when applied to complex open environments. In order to surmount these issues and further propel the evolution of 3D occupancy tasks, this study introduces a novel framework termed TDOcc. By leveraging multi-camera imagery, TDOcc executes 3D semantic occupancy prediction by directly learning from unprocessed 3D spaces, thereby maximizing information retention. TDOcc presents two notable advantages: firstly, it utilizes dense occupancy labels, which not only facilitate robust dense occupancy inference but also enable comprehensive object estimation within the scene. Secondly, the framework synthesizes historical feature information by adeptly aligning past and present features through temporal cues, thereby bolstering the efficacy of the feature fusion module. Additionally, with a view to address the ill-posed nature inherent in camera-based 3D occupancy prediction, we incorporate an enhancement module that operates within the 3D feature space. This module has been meticulously crafted for the training phase to amplify the model’s learning potential. Extensive experiments conducted on the widely recognized nuScenes dataset underscore the efficacy of our proposed approach. Compared to the most recent TPVFormer and OccFormer, our approach has achieved a significant improvement in mean Intersection over Union (mIoU) by 2.0 and 0.8 respectively, and has reached performance comparable to the state-of-the-art LiDAR-based methods.

A recurrent neural network-based approach for ballistic coefficient estimation of resident space objects in low earth orbit

Characterizing Resident Space Objects (RSOs) has become paramount for several Space Situational Awareness functions, such as accurate orbit prediction, collision avoidance and sensor tasking. Due to the huge and diverse amount of data to handle and fuse for this purpose, there is an increasing interest in Machine Learning (ML) approaches to retrieve physical parameters of RSOs in a cost-efficient manner. Among different ML architectures, Recurrent Neural Networks (RNNs) are particularly suitable to handle sequential or time-series data. In this context, this paper demonstrates the possibility to use Recurrent Neural Networks to estimate the ballistic coefficient of RSOs in Low Earth Orbit from time series of orbital elements. A particular RNN architecture has been adopted, i.e., the Gated Recurrent Unit, as it has been demonstrated to be cost efficient and to have good performance for the required application. The sensitivity of RNNs with respect to atmospheric model uncertainty has been analysed. The algorithm can handle unevenly spaced time-series data. The proposed neural network has been demonstrated to be robust with respect to orbital state errors. The applicability of the presented approach is tested and discussed using synthetic datasets generated with a high-accuracy numerical orbital propagator, reaching a mean percentage error of 10% in the estimation of the ballistic coefficient.

Identifying thresholds for meaningful improvements in NTDT-PRO scores to support conclusions about treatment benefit in clinical studies of patients with non-transfusion-dependent beta-thalassaemia: analysis of pooled data from a phase 2, double-blind, placebo-controlled, randomised trial

ObjectivesTo estimate thresholds for defining meaningful within-patient improvement from baseline to weeks 13–24 and interpreting meaningfulness of between-group difference for the non-transfusion-dependent beta-thalassaemia patient-reported outcome (NTDT-PRO) tiredness/weakness (T/W) and shortness...

IPTW and DR Estimators: Advancing towards the Adoption of Methodologies for Estimating Causal Treatment Effects in Observational Studies

The propensity score refers to the likelihood of a subject being selected for intervention, given their observed baseline covariates. By assigning different weights to academic disciplines based on the reciprocal probability of receiving treatment, there will be a synthetic sample where the assignment of treatment is not influenced by baseline factors that were measured. Utilizing inverse probability of treatment weighting (IPTW) through the propensity score enables people to assemble unbiased or objective estimates regarding average treatment effects. In order to estimate the causal relationship between an exposure and an outcome, the second notion of doubly robust estimation combines an outcome regression with a propensity score model. Only when the statistical model is appropriately stated can unbiased estimates be obtained using the propensity score approach and outcome regression separately. However, even if only one of the two models is correctly specified, an unbiased estimator for the effect can be obtained by employing the doubly robust estimator. This introduction to inverse probability of treatment weighting and doubly robust estimators includes conceptual overviews, an application to students’ performance in high school, as well as discussions based on the project.

Cylinder object 6-DOF pose estimation via single perspective circle on cylindrical surface

Abstract Pose estimation is an important research topic in computer vision. In this paper, a novel method for six-degree-of-freedom (6-DOF) pose estimation of cylindrical objects via a single perspective circle on cylindrical surface is proposed. Unlike traditional methods that rely on planar circular features, a circular feature target which is affixed to the side of cylindrical objects is utilized. The geometric properties of the spatial curve formed by its contour are leveraged for pose estimation. Specifically, the imaging model of the spatial curve is established to derive the general equation of its projection curve. The initial pose is determined based on the perspective principle, and the final optimized pose is obtained with the least squares method. To avoid local optima, a verification and correction method is proposed to enhance estimation accuracy. Synthetic and physical experiments demonstrate that the proposed method can achieve real-time, high-precision pose estimation for cylindrical objects, exhibiting robustness against occlusion and noise interference.&amp;#xD;