Visual Error Research Articles

The Effects of High-Altitude Mountaineering on Cognitive Function in Mountaineers: A Meta-Analysis

Nowadays, with the convenience of international traveling and driven by many individuals' fond dreams of challenging high-altitude exercises, high-altitude mountaineering is becoming increasingly popular worldwide. Therefore, we performed a meta-analysis to determine the effects of high-altitude mountaineering on cognitive functions in mountaineers before and after climbing. After a thorough electronic literature search and selection, eight studies were included in this meta-analysis, and the conducted test cycles ranged from 8 to 140 days. Eight variables were included in this meta-analysis: the Trail-Making Test (TMB), Digit Span-Forward (DSF), Digit Span-Backward (DSB), Finger Tapping Test-Right (FTR) Finger Tapping Test-Left (FTL), Wechsler Memory Scale Visual (WMSV), the Aphasia Screening Test (Verbal Items) (AST-Ver), and the Aphasia Screening Test (Visual Motor Errors) (AST-Vis). The effect sizes (ES) and forest plots of these eight variables were generated. Five variables (TMB, ES = 0.39; DSF, ES = 0.57; FTR, ES = 0.50; FTL, ES = 0.16; WMSV, ES = 0.63) out of eight were significantly improved after high-altitude mountaineering, whereas the ES values of DSB, AST-Ver, and AST-Vis did not show significant improvement after climbing. Despite two limitations, namely, methodological issues inherent in the meta-analysis and the inability to explain high heterogeneity between studies, this study is the first meta-analysis that has attempted to specify and compare the cognitive functions of mountaineers before and after high-altitude mountaineering. Furthermore, as a short-term plateau exercise, high-altitude mountaineering has no significant negative impacts on the cognitive functions of climbers. Future research is needed for a long period of high-altitude mountaineering.

Interactions and tensions between mathematical discourses and schoolwork discourses when solving dynamic geometry tasks: what is internally persuasive for students?

ABSTRACT I explore students’ discourses in small groups working on mathematical problems using GeoGebra, focusing on the Cartesian connection between algebra and geometry. Specifically, the interest lies in what is internally persuasive for students in upper-secondary school (11th grade) with histories of low attainment. Three problem-solving episodes are presented in detail to illuminate different intertwining and interacting discourses that students produce. In all cases, students engaged in visual explorations and expressed joy in the work. Students used discourses of visual appearance and technical symbolism to talk about screen objects and problem solutions. Two cases illustrate how a student makes a conjecture internally before verifying it for themselves and then convincing their peers of the validity of their solution. In a contrasting case, students used visual trial and error and asked an authority to confirm their solution. Discourses concerning the institutional demands of school interfered with students’ mathematical dialogue.

Determination of the Accuracy of the Straight Bevel Gear Profiles by a Novel Optical Coaxial Multi-Ring Measurement Method.

Straight bevel gears are widely used in mining equipment, ships, heavy industrial equipment, and other fields due to their high capacity and robust transmission. Accurate measurements are essential in order to determine the quality of bevel gears. We propose a method for measuring the accuracy of the top surface profile of the straight bevel gear teeth based on binocular visual technology, computer graphics, error theory, and statistical calculations. In our method, multiple measurement circles are established at equal intervals from the small end of the top surface of the gear tooth to the large end, and the coordinates of the intersection points of these circles with the tooth top edge lines of the gear teeth are extracted. The coordinates of these intersections are fitted to the top surface of the tooth based on NURBS surface theory. The surface profile error between the fitted top surface of the tooth and the designed surface is measured and determined based on the product use requirements, and if this is less than a given threshold, the product is acceptable. With a module of 5 and an eight-level precision, such as the straight bevel gear, the minimum surface profile error measured was -0.0026 mm. These results demonstrate that our method can be used to measure surface profile errors in the straight bevel gears, which will broaden the field of in-depth measurements for the straight bevel gears.

A randomized, sham-controlled trial of high-definition transcranial direct current stimulation on the right orbital frontal cortex in children and adolescents with attention-deficit hyperactivity disorder.

This study aimed to find out the clinical and cognitive effects of high-definition transcranial direct current stimulation (HD-tDCS) on the right orbital frontal cortex (OFC) in the treatment of attention deficit hyperactivity disorder (ADHD). A total of 56 patients with ADHD were recruited as subjects and completely and randomly divided into the HD-tDCS group and the Sham group. A 1.0 mA anode current was applied to the right OFC. The HD-tDCS group received real stimulation, while the Sham group received sham stimulation in 10 sessions of treatment. ADHD symptom assessment (the SNAP-IV Rating Scale and the Perceived Stress Questionnaire) was carried out before treatment, after the 5th and 10th stimuli, and at the 6th week after the end of all stimulations, while the cognitive effect was assessed by the Integrated Visual and Auditory Continuous Performance Test (IVA-CPT), the Stroop Color and Word Test (Stroop), and the Tower of Hanoi (TOH). Repeated-measure ANOVA was used to find out the results of both groups before and after treatment. A total of 47 patients completed all sessions and evaluations. Their SNAP-IV score, their PSQ score, the mean visual and auditory reaction times by IVA-CPT, the interference RT of Stroop Color and Word, and the number of completed steps of TOH did not change with intervention time before and after treatment (P > 0.0031). However, the integrated visual and audiovisual commission errors and the TOH completion time results of the HD-tDCS group were significantly decreased after the 5th intervention, the 10th intervention, and the 6th week of intervention follow-up compared to the Sham group (P < 0.0031). This study draws cautious conclusions that HD-tDCS does not significantly alleviate the overall symptoms of patients with ADHD but leads to significant improvements in the cognitive measures of attention maintenance. The study also attempted to fill in the gaps in research studies on HD-tDCS stimulation of the right OFC. ChiCTR2200062616.

Application of full waveform inversion algorithm in Laplace–Fourier domain for high-contrast ultrasonic bone quantitative imaging

Background and objectivesFull waveform inversion (FWI) has been widely applied for the reconstruction of underground medium parameters in seismic communities and has made a great success. It is also a promising way to image hard tissues such as bones by ultrasonic FWI algorithm. However, the ultrasonic FWI methods for bone parameters imaging reported in literature so far are limited to the time domain and/or Fourier domain, and can only achieve quantitative imaging with acoustic velocity of bone less than 3000 m/s. Because the acoustic velocity of actual cortical bones can be as high as 4200 m/s, it is still a challenge for FWI to achieve higher parameter contrast bone imaging. MethodsHere, we proposed an ultrasonic FWI algorithm in Laplace–Fourier domain (LFDFWI) for high-contrast bone quantitative imaging. Compared to Time domain and Fourier domain, the LFDFWI algorithm is more appropriate for dealing with the presence of high contrast between bone tissues, reducing the possibility of inversion falling into a local minimum, and obtaining better inversion results. We adapted the seismic FWI algorithm to make it suitable for high-frequency ultrasonic sources and small-sized bone parameter imaging. ResultsWe conducted a series of bone models to evaluate the effectiveness of the proposed algorithm, including four kinds of bone model derived from micro computed tomography (Micro-CT) image of rat. We evaluated the experimental results based on visual analysis, error analysis and structural similarity (SSIM). The numerical simulation results showed that, when acoustic approximation is used, the proposed method can obtain accurate high-contrast images of the velocity and density parameters of bone structure, the mean relative error (MRE) in the region of interest (ROI) were all less than 2%, and the SSIM is up to 98%; when the viscoelastic approximation is used, this method can also obtain the desired high-contrast bone parameter distribution, with MRE less than 4% and SSIM higher than 74%, both of which are better than FDFWI in Fourier domain (FDFWI). ConclusionThe results demonstrated that the proposed FWI algorithm can obtain high resolution bone parameter models close to the Micro-CT image, which proves its clinical application potential.

Identifying key mechanisms leading to visual recognition errors for missed colorectal polyps using eye-tracking technology.

Lack of visual recognition of colorectal polyps may lead to interval cancers. The mechanisms contributing to perceptual variation, particularly for subtle and advanced colorectal neoplasia, have scarcely been investigated. We aimed to evaluate visual recognition errors and provide novel mechanistic insights. Eleven participants (seven trainees and four medical students) evaluated images from the UCL polyp perception dataset, containing 25 polyps, using eye-tracking equipment. Gaze errors were defined as those where the lesion was not observed according to eye-tracking technology. Cognitive errors occurred when lesions were observed but not recognized as polyps by participants. A video study was also performed including 39 subtle polyps, where polyp recognition performance was compared with a convolutional neural network. Cognitive errors occurred more frequently than gaze errors overall (65.6%), with a significantly higher proportion in trainees (P=0.0264). In the video validation, the convolutional neural network detected significantly more polyps than trainees and medical students, with per-polyp sensitivities of 79.5%, 30.0%, and 15.4%, respectively. Cognitive errors were the most common reason for visual recognition errors. The impact of interventions such as artificial intelligence, particularly on different types of perceptual errors, needs further investigation including potential effects on learning curves. To facilitate future research, a publicly accessible visual perception colonoscopy polyp database was created.

A Homography-Based Visual Servo Control Approach for an Underactuated Unmanned Aerial Vehicle in GPS-Denied Environments

This paper proposes a homography-based visual servo control approach for the stabilization of underactuated unmanned aerial vehicles in GPS-denied environments. A virtual homography matrix is proposed, and a new visual error vector is defined to obtain the passivity-like visual error equation. In addition, a homography-based online translation velocity estimator and a nonlinear backstepping visual servo control approach are addressed to promote fast maneuvering without linear velocity feedback. Unlike conventional homography-based visual servo control solutions that only guarantee the local stability in the equilibrium, the proposed control scheme can get the global stability in large offset. Simulation and experimental tests with a realistic quadrotor subject to the measurement noise are carried out to verify the robustness and performance of the control approach. In addition, the autonomous tracking experiment when the target speed is unpredictable are also reported.

The dark side of being a pathologist: Unravelling the health hazards.

Pathologists are indispensable to the practice of medicine. Awareness of health hazards among pathologists is a crucial aspect of today's time. Numerous occupational health risks are prevalent which are mostly ignored; for example, the association of microscope use for prolonged durations leading to the development of chronic pain syndromes has been acknowledged for nearly three decades, yet most pathologists are unaware about this hazard until after it transforms into a chronic health issue. The purpose of this study is to learn its prevalence in working pathologists, make them aware of the risks, discuss and encourage them to proactively integrate strategies which are preventive in nature into their daily routine lives. The aim of the study was to analyze the level of risk, knowledge, awareness and biosafety measures taken by the pathologists in their routine daily work life. The study was conducted in a developing country, Northern India, using a standard online 50-item questionnaire enquiring about routine practices. 450 participants were enrolled consisting of 360 pathologists and 90 residents of pathology. Among the 450 enrolled study participants, 84.8% complained of musculoskeletal disorders (MSD), with the neck being the commonest location of pain. Furthermore, 74.8% reported visual refractive errors, among which myopia took the highest place. Work injuries were reported in 60% of participants. Intolerance reactions to chemicals especially formaldehyde was observed in 63.1%. Depression and burnout were reported in 42%. Although knowledge seems to be near adequate, there is a lack of implementation and a noticeable risk of health hazards namely musculoskeletal problems, injuries, visual disorders, and ergonomic issues in routine daily activities of pathologists.

Image-Based Visual Impedance Force Control for Contact Aerial Manipulation

In this paper, an image-based impedance control strategy for force tracking of an unmanned aerial manipulator (UAM) is presented. Firstly, image features with nice decoupling characteristics are designed and the relationship between the camera motion and the image features is derived. Then, a two-stage strategy is proposed to achieve force tracking of the UAM on a planar object in an arbitrary pose. The first stage drives the end-effector perpendicular to the object’s planer surface by pure visual servoing. To achieve force tracking under the visual guidance, an adaptive visual impedance control method which adjusts the target stiffness according to the force tracking error and the visual feature error is proposed in the second stage. The closed-loop system is proved asymptotically stable by means of Lyapunov analysis. Further, the stability in free flight phase of the stage two is also analyzed and ensured. Finally, experiments were carried out including a whiteboard cleaning task in different poses. The experimental results illustrate the validity and effectiveness of the proposed approach. Note to Practitioners—This work is motivated by the contact force tracking problem of an unmanned aerial manipulator (UAM) without the position measurement. In recent years, impedance control is widely used in force tracking problems. However, position measurement is needed both for the robot and the object in most studies. To generate desired force under visual guidance, image-based visual servoing is combined with a novel impedance controller with variable stiffness. The idea is intuitive. For a human in contact with a wall, the contact force is controlled by adjusting his arm stiffness, which means the stiffness is adapted to the difference between the desired and actual contact force. Furthermore, the stiffness is also adapted to the visual tracking error, removing the assumption that no tracking error is in the inner loop of the impedance controller in the previous works. The proposed strategy is a promising solution for real applications and is validated by a board cleaning experiment in this paper.

Qualitative Abnormalities of Peripheral Blood Smear Images Using Deep Learning Techniques

In recent years, Peripheral blood smear is a generic analysis to assess the person’s health status. Manual testing of Peripheral blood smear images are difficult, time-consuming and is subject to human intervention and visual error. This method encouraged for researchers to present algorithms and techniques to perform the peripheral blood smear analysis with the help of computer-assisted and decision-making techniques. Existing CAD based methods are lacks in attaining the accurate detection of abnormalities present in the images. In order to mitigate this issue Deep Convolution Neural Network (DCNN) based automatic classification technique is introduced with the classification of eight groups of peripheral blood cells such as basophil, eosinophil, lymphocyte, monocyte, neutrophil, erythroblast, platelet, myocyte, promyocyte and metamyocyte. The proposed DCNN model employs transfer learning approach and additionally it carries three stages such as pre-processing, feature extraction and classification. Initially the pre-processing steps are incorporated to eliminate noisy contents present in the image by using Histogram Equalization (HE). It is enclosed to improve an image contrast. In order to distinguish the dissimilar class and segmentation approach is carried out with the help of Fuzzy C-Means (FCM) model whereas its centroid point optimality method with Slap Swarm based optimization strategy. Moreover some specific set of Gray Level Co-occurrence Matrix (GLCM) features of the segmented images are extracted to augment the performance of proposed detection algorithm. Finally the extracted features are recorded by DCNN and the proposed classifier has the capability to extract their own features. Based on this the diverse set of classes are classified and distinguished from qualitative abnormalities found in the image.

Food volume estimation by multi-layer superpixel.

Estimating the volume of food plays an important role in diet monitoring. However, it is difficult to perform this estimation automatically and accurately. A new method based on the multi-layer superpixel technique is proposed in this paper to avoid tedious human-computer interaction and improve estimation accuracy. Our method includes the following steps: 1) obtain a pair of food images along with the depth information using a stereo camera; 2) reconstruct the plate plane from the disparity map; 3) warp the input image and the disparity map to form a new direction of view parallel to the plate plane; 4) cut the warped image into a series of slices according to the depth information and estimate the occluded part of the food; and 5) rescale superpixels for each slice and estimate the food volume by accumulating all available slices in the segmented food region. Through a combination of image data and disparity map, the influences of noise and visual error in existing interactive food volume estimation methods are reduced, and the estimation accuracy is improved. Our experiments show that our method is effective, accurate and convenient, providing a new tool for promoting a balanced diet and maintaining health.

ASSISTENTE VIRTUAL: FERRAMENTA PARA COPRODUÇÃO EM SAÚDE NO ENFRENTAMENTO À COVID-19

ABSTRACT Objective: to describe the development of a virtual assistant as a potential tool for health co-production in coping with COVID-19. Method: this is an applied technological production research study developed in March and April 2020 in five stages: 1) literature review, 2) content definition, 3) elaboration of the dialog, 4) test of the prototype, and 5) integration with the social media page. Results: the literature review gathered diverse scientific evidence about the disease based on the Brazilian Ministry of Health publications and by consulting scientific articles. The content was built from the questions most asked by the population, in March 2020, evidenced by Google Trends, in which the following topics emerged: concept of the disease, prevention means, transmission of the disease, main symptoms, treatment modalities, and doubts. Elaboration of the dialog was based on Natural Language Processing, intentions, entities and dialog structure. The prototype was tested in a laboratory with a small number of user computers on a local network to verify the functionality of the set of apps, technical and visual errors in the dialog, and whether the answers provided were in accordance with the user's question, answering the questions correctly and integrated into Facebook. Conclusion: the virtual assistant proved to be a health education tool with potential to combat “Fake News”. It also represents a patient-centered form of health communication that favors the strengthening of the bond and interaction between health professionals and patients, promoting co-production in health.

Assessing visual symptoms related to dry eye and refractive error in school students before and after online classes during COVID-19 pandemic

Background: During the COVID-19 pandemic, there was a major change in the mode of education from offline to online classes for the school students. Objectives: To determine if school students have developed symptoms related to dry eye. Methodology: Its descriptive cross-sectional study. This study was conducted in a reputed school in the city and 1000 students who had attended online classes during the covid-19 pandemic by the Department of Ophthalmology, Chettinad hospital and research institute, Kelambakkam, Tamil nadu, India Results: About 41% experienced redness of eye, 38% experienced blurring of vision, 36.6% had eye pain, 32% had burning sensation of eyes signs of dryness of eye. 50.2% had adequate distance between your gadget and eyes, 36.1 % had too close to eyes and 13.7 % had too far from eyes. Regarding the eye checkup, 43.7% never checked up their eyes, 11.6% does annual examination and 44.7% does rarely. Comparison between duration of Electronic Gadget usage per day during online class and offline class was significantly reduced after the offline class commencement. P value is 0.000001. Conclusion: There is significant Digital screen exposure time difference is observed during online and in offline classes. And its impact in visual refractive errors and computer vision syndrome

Highlights from the Detroit SID Vehicle Display Symposium and Exposition

Highlights from the Detroit SID Vehicle Display Symposium and Exposition

Occlusion Handler Density Networks for 3D Multimodal Joint Location of Hand Pose Hypothesis

Predicting the pose parameters during the hand pose estimation (HPE) process is an ill-posed challenge. This is due to severe self-occluded joints of the hand. The existing approaches for predicting pose parameters of the hand, utilize a single-value mapping of an input image to generate final pose output. This way makes it difficult to handle occlusion especially when it comes from the multimodal pose hypothesis. This paper introduces an effective method of handling multimodal joint occlusion using the negative log-likelihood of a multimodal mixture-of-Gaussians through a hybrid hierarchical mixture density network (HHMDN). The proposed approach generates multiple feasible hypotheses of 3D poses with visibility, unimodal and multimodal distribution units to locate joint visibility. The visible features are extracted and fed into the Convolutional Neural Networks (CNN) layer of the HHMDN for feature learning. Finally, the effectiveness of the proposed method is proved on ICVL, NYU, and BigHand public hand pose datasets. The imperative results show that the proposed method in this paper is effective as it achieves a visibility error of 30.3mm, which is less error compared to many state-of-the-art approaches that use different distributions of visible and occluded joints.

Direct and Indirect Effects Between First Literacy Errors, Visual Perception, and Phonological Awareness Variables

This research is a descriptive study in the survey model to determine the direct and indirect effects between visual perception, phonological awareness, and literacy errors. The design of the study is exploratory correlational design. 552 first-grade primary school students participated in the study. The data were collected using measurement tools named phonological awareness, visual perception, word-sentence writing/spelling, and reading errors. According to the findings, visual perception affects sentence writing/spelling both directly and through word-writing-reading errors. Visual perception affects reading errors both directly and through word-sentence writing errors. The results show that the development of prerequisite skills and reading are mediated by writing, writing/spelling are mediated by reading, and learning develops in a spiral manner. It can be said that children’s reading-writing/spelling errors increase because they have difficulty in converting from sound to the letter, from letter to sound, and in synthesizing and analyzing according to their initial level of phonological awareness and visual perception development.

Visual Error Augmentation During Bimanual Therapy in Individuals Post Stroke

<h3>Research Objectives</h3> To investigate the influence of visual error augmentation during bimanual upper extremity therapy in individuals' post-stroke. <h3>Design</h3> Two-arm randomized clinical trial with blinded rater. Individuals were randomized into the treatment or control group. Individuals received 9 treatments across 3 weeks, and completed upper extremity evaluations before treatment, 1 week after treatment, and 8 weeks after treatment. <h3>Setting</h3> Translational research hospital in which clinicians and researchers are integrated in the same space. <h3>Participants</h3> The target population for the study was chronic stroke participants (at least 8 months post-injury), 18 years or older, with a history of a single stroke event, with mild-moderate upper extremity impairment (Fugl-Meyer Score 15-50) and residual active elbow flexion/extension when supported against gravity. 69 participants were assessed for eligibility, 38 participants met inclusion criteria and were randomized into the study. 19 subjects were allocated in each group, but 3 in each group were lost due to participant withdrawal. One participant in the control group was lost to follow-up. 16 participants in the treatment group, and 15 participants in the control group were analyzed in the results. <h3>Interventions</h3> Both groups completed a bimanual reaching and balancing exercise in a virtual reality environment. The treatment group received visual error augmentation, which visually shifted the cursor in the direction of error to enhance neuroplasticity associated with motor recovery. <h3>Main Outcome Measures</h3> Upper Extremity Fugl-Meyer, and bimanual asymmetry. <h3>Results</h3> No clinically significant difference between treatment and control group for functional motor recovery (p=0.665) and no significant difference in the interaction between time and groups (p=0.069); however, both groups did improve over time (p=0.005). For asymmetry of trajectory between paretic and non-paretic hand in the superior-inferior direction there is a significant difference between time instants (p< 0.001), while no significant difference was found in groups (p=0.266) or in the interaction between time and groups (p=0.066). <h3>Conclusions</h3> This is an example of supplemental treatment using interactive visual feedback for post-stroke upper extremity rehabilitation. <h3>Author(s) Disclosures</h3> N/A.

Fusion of binocular vision, 2D lidar and IMU for outdoor localization and indoor planar mapping

Emergent fields such as Internet of Things applications, driverless cars, and indoor mobile robots have brought about an increasing demand for simultaneous localization and mapping (SLAM) technology. In this study, we design a SLAM scheme called BVLI-SLAM based on binocular vision, 2D lidar, and an inertial measurement unit (IMU) sensor. The pose estimation provided by vision and the IMU can provide better initial values for the 2D lidar mapping algorithm and improve the mapping effect. Lidar can also assist vision to provide better plane and yaw angle constraints in weak texture areas and obtain higher precision 6-degree of freedom pose. BVLI-SLAM uses graph optimization to fuse the data of the IMU, binocular camera, and laser. The IMU pre-integration combines the visual reprojection error and the laser matching error to form an error equation, which is processed by a sliding window-based bundle adjustment optimization to calculate the pose in real time. Outdoor experiments based on KITTI datasets and indoor experiments based on the trolley mobile measurement platform show that BVLI-SLAM has different degrees of improvement in mapping effect, positioning accuracy, and robustness compared with VINS-Fusion and Cartographer, and can solve the problem of positioning and plane mapping in indoor complex scenes.

Dual STDP processes at Purkinje cells contribute to distinct improvements in accuracy and speed of saccadic eye movements.

Saccadic eye-movements play a crucial role in visuo-motor control by allowing rapid foveation onto new targets. However, the neural processes governing saccades adaptation are not fully understood. Saccades, due to the short-time of execution (20-100 ms) and the absence of sensory information for online feedback control, must be controlled in a ballistic manner. Incomplete measurements of the movement trajectory, such as the visual endpoint error, are supposedly used to form internal predictions about the movement kinematics resulting in predictive control. In order to characterize the synaptic and neural circuit mechanisms underlying predictive saccadic control, we have reconstructed the saccadic system in a digital controller embedding a spiking neural network of the cerebellum with spike timing-dependent plasticity (STDP) rules driving parallel fiber-Purkinje cell long-term potentiation and depression (LTP and LTD). This model implements a control policy based on a dual plasticity mechanism, resulting in the identification of the roles of LTP and LTD in regulating the overall quality of saccade kinematics: it turns out that LTD increases the accuracy by decreasing visual error and LTP increases the peak speed. The control policy also required cerebellar PCs to be divided into two subpopulations, characterized by burst or pause responses. To our knowledge, this is the first model that explains in mechanistic terms the visual error and peak speed regulation of ballistic eye movements in forward mode exploiting spike-timing to regulate firing in different populations of the neuronal network. This elementary model of saccades could be extended and applied to other more complex cases in which single jerks are concatenated to compose articulated and coordinated movements.

PPR-Net++: Accurate 6-D Pose Estimation in Stacked Scenarios

Most supervised learning-based pose estimation methods for stacked scenes are trained on massive synthetic datasets. In most cases, the challenge is that the learned network on the training dataset is no longer optimal on the testing dataset. To address this problem, we propose a pose regression network PPR-Net++. It transforms each scene point into a point in the centroid space, followed by a clustering process and a voting process. In the training phase, a mapping function between the network’s critical parameter (i.e., the bandwidth of the clustering algorithm) and the compactness of the centroid distributions is obtained. This function is used to adapt the bandwidth between centroid distributions of two different domains. In addition, to further improve the pose estimation accuracy, the network also predicts the confidence of each point, based on its visibility and pose error. Only the points with high confidence have the right to vote for the final object pose. In experiments, our method is trained on the IPA synthetic dataset and compared with the state-of-the-art algorithm. When tested with the public synthetic Siléane dataset, our method is better in all eight objects, where five of them are improved by more than 5% in average precision (AP). On IPA real dataset, our method outperforms a large margin by 20%. This lays a solid foundation for robot grasping in industrial scenarios. Note to Practitioners—Our work is motivated by industrial product assembly based on robot grasping. The industrial parts are usually manufactured by numerical machines and piled in bins. Our method can estimate the poses of visible parts accurately. A pose of a part includes its centroid and spatial orientations. Combined with a depth camera, this algorithm allows an industrial robot to understand complex stacked scenes. We improve the pose estimation accuracy in order to assemble parts with robot grasping, without an additional pose adjuster. Our network can learn from a synthetic dataset and apply it to real-world data, without a significant accuracy drop. The synthetic dataset can be obtained easily by computer simulation programs, so the training data are sufficient. Experiments demonstrate that our method outperforms the state-of-the-art pose estimation approaches.