Partial Occlusion Research Articles

Underwater optical signal detection system using diffuser-based lensless imaging.

We propose a diffuser-based lensless underwater optical signal detection system. The system consists of a lensless one-dimensional (1D) camera array equipped with random phase modulators for signal acquisition and one-dimensional integral imaging convolutional neural network (1DInImCNN) for signal classification. During the acquisition process, the encoded signal transmitted by a light-emitting diode passes through a turbid medium as well as partial occlusion. The 1D diffuser-based lensless camera array is used to capture the transmitted information. The captured pseudorandom patterns are then classified through the 1DInImCNN to output the desired signal. We compared our proposed underwater lensless optical signal detection system with an equivalent lens-based underwater optical signal detection system in terms of detection performance and computational cost. The results show that the former outperforms the latter. Moreover, we use dimensionality reduction on the lensless pattern and study their theoretical computational costs and detection performance. The results show that the detection performance of lensless systems does not suffer appreciably. This makes lensless systems a great candidate for low-cost compressive underwater optical imaging and signal detection.

An Integrated Hand-Object Dense Pose Estimation Approach With Explicit Occlusion Awareness for Human-Robot Collaborative Disassembly

Human-robot collaborative disassembly (HRCD) has gained much interest in the disassembly tasks of end-of-life products, integrating both robot’s high efficiency in repetitive works and human’s flexibility with higher cognition. Explicit human-object perceptions are significant but remain little reported in the literature for adaptive robot decision-makings, especially in the close proximity co-work with partial occlusions. Aiming to bridge this gap, this study proposes a vision-based 3D dense hand-object pose estimation approach for HRCD. First, a mask-guided attentive module is proposed to better attend to hand and object areas, respectively. Meanwhile, explicit consideration of the occluded area in the input image is introduced to mitigate the performance degradation caused by visual occlusion, which is inevitable during HRCD hand-object interactions. In addition, a 3D hand-object pose dataset is collected for a lithium-ion battery disassembly scenario in the lab environment with comparative experiments carried out, to demonstrate the effectiveness of the proposed method. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —This work aims to overcome the challenge of joint hand-object pose estimation in a human-robot collaborative disassembly scenario, of which can also be applied to many other close-range human-robot/machine collaboration cases with practical values. The ability to accurately perceive the pose of the human hand and workpiece under partial occlusion is crucial for the collaborative robot to successfully carry out co-manipulation with human operators. This paper proposes an approach that can jointly estimate the 3D pose of the hand and object in an integrated model. An explicit prediction of the occlusion area is then introduced as a regularization term during model training. This can make the model more robust to partial occlusion between the hand and object. The comparative experiments suggest that the proposed approach outperforms many existing hand-object estimation ones. Nevertheless, the dependency on manually labeled training data can limit its application. In the future, we will consider semi-supervised or unsupervised training to address this issue and achieve faster adaptation to different industrial scenarios.

VT-3DCapsNet: Visual tempos 3D-Capsule network for video-based facial expression recognition.

Facial expression recognition(FER) is a hot topic in computer vision, especially as deep learning based methods are gaining traction in this field. However, traditional convolutional neural networks (CNN) ignore the relative position relationship of key facial features (mouth, eyebrows, eyes, etc.) due to changes of facial expressions in real-world environments such as rotation, displacement or partial occlusion. In addition, most of the works in the literature do not take visual tempos into account when recognizing facial expressions that possess higher similarities. To address these issues, we propose a visual tempos 3D-CapsNet framework(VT-3DCapsNet). First, we propose 3D-CapsNet model for emotion recognition, in which we introduced improved 3D-ResNet architecture that integrated with AU-perceived attention module to enhance the ability of feature representation of capsule network, through expressing deeper hierarchical spatiotemporal features and extracting latent information (position, size, orientation) in key facial areas. Furthermore, we propose the temporal pyramid network(TPN)-based expression recognition module(TPN-ERM), which can learn high-level facial motion features from video frames to model differences in visual tempos, further improving the recognition accuracy of 3D-CapsNet. Extensive experiments are conducted on extended Kohn-Kanada (CK+) database and Acted Facial Expression in Wild (AFEW) database. The results demonstrate competitive performance of our approach compared with other state-of-the-art methods.

Effect of Detector Orientation and Influence of Jaw Position in the Determination of Small-field Output Factor with Various Detectors for High-energy Photon Beams.

Accurate dose measurements are difficult in small fields due to charge particle disequilibrium, partial source occlusion, steep dose gradient, and the finite size of the detector. The study aims to determine the output factor using various detectors oriented in parallel and perpendicular orientations for three different tertiary collimating systems using 15 MV photon beams. In addition, this study analyzes how the output factor could be affected by different configurations of X and Y jaws above the tertiary collimators. Small field output factor measurements were carried out with three detectors for different tertiary collimating systems such as BrainLab stereotactic cones, BrainLab mMLC and Millennium MLC namely. To analyze the effect of jaw position on output factor, measurements have been carried out by positioning the jaws at the edge, 0.25, 0.5, and 1.0 cm away from the tertiary collimated field. The data acquired with 15 MV photon beams show significant differences in output factor obtained with different detectors for all collimating systems. For smaller fields when compared to microDiamond, the SRS diode underestimates the output by up to -1.7% ± 0.8% and -2.1% ± 0.3%, and the pinpoint ion chamber underestimates the output by up to -8.1% ± 1.4% and -11.9% ± 1.9% in their parallel and perpendicular orientation respectively. A large increase in output factor was observed in the small field when the jaw was moved 0.25 cm symmetrically away from the tertiary collimated field. The investigated data on the effect of jaw position inferred that the position of the X and Y jaw highly influences the output factors of the small field. It also confirms that the output factor highly depends on the configuration of X and Y jaw settings, the tertiary collimating system as well as the orientation of the detectors in small fields.

Efficacy of partial and complete resuscitative endovascular balloon occlusion of the aorta in the hemorrhagic shock model of liver injury.

Resuscitative endovascular balloon occlusion of the aorta (REBOA) can temporarily control traumatic bleeding. However, its prolonged use potentially leads to ischemia-reperfusion injury (IRI). Partial REBOA (pREBOA) can alleviate ischemic burden; however, its security and effectiveness prior to operative hemorrhage control remains unknown. Hence, we aimed to estimate the efficacy of pREBOA in a swine model of liver injury using an experimental sliding-chamber ballistic gun. Twenty Landrace pigs were randomized into control (no aortic occlusion) (n=5), intervention with complete REBOA (cREBOA) (n=5), continuous pREBOA (C-pREBOA) (n=5), and sequential pREBOA (S-pREBOA) (n=5) groups. In the cREBOA and C-pREBOA groups, the balloon was inflated for 60 min. The hemodynamic and laboratory values were compared at various observation time points. Tissue samples immediately after animal euthanasia from the myocardium, liver, kidneys, and duodenum were collected for histological assessment using hematoxylin and eosin staining. Compared with the control group, the survival rate of the REBOA groups was prominently improved (all P<0.05). The total volume of blood loss was markedly lower in the cREBOA group (493.14±127.31 mL) compared with other groups (P<0.01). The pH was significantly lower at 180 min in the cREBOA and S-pREBOA groups (P<0.05). At 120 min, the S-pREBOA group showed higher alanine aminotransferase (P<0.05) but lower blood urea nitrogen compared with the cREBOA group (P<0.05). In this trauma model with liver injury, a 60-minute pREBOA resulted in improved survival rate and was effective in maintaining reliable aortic pressure, despite persistent hemorrhage. Extended tolerance time for aortic occlusion in Zone I for non-compressible torso hemorrhage was feasible with both continuous partial and sequential partial measures, and the significant improvement in the severity of acidosis and distal organ injury was observed in the sequential pREBOA.

Effects of occlusion pressure on hemodynamic responses recorded by near-infrared spectroscopy across two visits.

Ischemic Preconditioning (IPC) has emerged as a promising approach to mitigate the impact of hypoxia on physiological functions. However, the heterogeneity of occlusion pressures for inducing arterial occlusion has led to inconsistent hemodynamic outcomes across studies. This study aims to evaluate the peripheral hemodynamic responses to partial and total blood-flow occlusions on the left arm at rest, using absolute or individualized pressures, on two occasions. Thirty-five young males volunteered to participate in this study. IPC procedure (3 × 7-min) was performed on the left upper arm with cuff pressures at 50mmHg (G1), 50mmHg over the systolic blood pressure (SBP + 50mmHg) (G2) or 250mmHg (G3). NIRS-derived parameters were assessed for each occlusion and reperfusion phase in the brachioradialis. Results showed a significantly lower magnitude of deoxygenation (TSIAUC) for G1 compared to G2 (-1959.2 ± 1417.4 vs. -10908.1 ± 1607.5, P < 0.001) and G3 -1959.2 ± 1417.4 vs. -11079.3 ± 1828.1, P < 0.001), without differences between G2 and G3. However, G3 showed a significantly faster reoxygenation only for tissue saturation index (TSIslope) compared to G2 (1.3 ± 0.1 vs. 1.0 ± 0.2, P = 0.010), but without differences in the speed of recovery of deoxyhemoglobin [(HHb) slope], or in the magnitude of post-occlusive hyperemia (PORH). Besides TSI reoxygenation speed, G2 and G3 elicit comparable resting hemodynamic responses measured by NIRS. Thus, this study highlights the practicality and effectiveness of using relative occlusion pressures based on systolic blood pressure (SBP) rather than relying on excessively high absolute pressures.

Exploring the Impact of Partial Occlusion on Emotion Classification From Facial Expressions: A Comparative Study of XR Headsets and Face Masks

Exploring the Impact of Partial Occlusion on Emotion Classification From Facial Expressions: A Comparative Study of XR Headsets and Face Masks

Navigating a Rare Presentation: Case Report of a Large Gartner’s Duct Cyst

Background: Mullerian ducts form the female genital tract and wolffian ducts form the male genital tract. In females, sometimes the wolffian duct persists and form the Gartner duct and its total or partial occlusion results in the formation of Gartner’s cyst. It is typically small and asymptomatic and occurs along the antero-lateral wall of vagina. Methods and Results: We report a case of 40-year-old woman who presented with a big mass coming out per vaginum. After examination, she was provisionally diagnosed as Gartner duct cyst, excision was done and confirmed as a case of Gartner’s duct cyst on histopathological examination. Conclusion: A good clinical examination along with radiological investigations aids in making a timely diagnosis and surgical management.

Part-based Tracking via Discriminative Correlation Filters

In order to better deal with the partial occlusion issue, part-based trackers are widely used in visual object tracking recently. However, it is still difficult to realize fast and robust tracking, due to complicated online training and updating process. Correlation filters have been used in visual object tracking tasks recently because of their high efficiency. However, the traditional correlation filter based tracking methods do not deal with occlusion well. In this paper, we propose a novel tracking method which tracks objects based on parts with multiple correlation filters. The Bayesian inference framework and a structural constraint mask are adopted to enable our tracker to be robust to various appearance changes. Additionally, a discriminative part selection scheme is adopted to further improve performance and accelerate our method. Experimental results demonstrate that our multiple part tracker can significantly improve tracking performance on benchmark datasets.

Flexible Iris Matching Based on Spatial Feature Reconstruction

In an iris recognition-at-a-distance (IAAD) system used in surveillance scenarios, the camera usually captures a large number of low-quality images. These images exhibit partial occlusions due to eyelids and eyelashes, specular reflections, and severe deformations caused by pupil dilations and contractions. Recognizing these low-quality images is a challenging yet dominant problem in IAAD. To mitigate this issue, current iris recognition systems mostly filter out low-quality images by using strict criteria based on image quality evaluation. This strategy, however, wastes device capabilities and produces low throughput of subjects. Other systems require highly cooperative users. In this work, we propose a novel occlusion-robust, deformation-robust, and alignment-free framework for low-quality iris matching, which integrates the merits of deep features and sparse representation in an end-to-end learning process known as iris spatial feature reconstruction (ISFR). Here each probe image can be sparsely reconstructed on the basis of appropriate feature maps from gallery high-quality images. ISFR uses the error from robust reconstruction over spatial pyramid features to measure similarities between two iris images, which naturally avoids the time-consuming alignment step. In summary, the distinctiveness of deep features, the robustness of sparse reconstruction, and the flexibility of multiscale matching strategy are unified in a general framework to attain more accurate and reasonable iris matching. Extensive experimental results on four public iris image databases demonstrate that the proposed method significantly outperforms both traditional and deep learning-based iris recognition methods.

Anterior Segment Optical Coherence Tomography for Cases of High Intraocular Pressure Following XEN Implant for Glaucoma.

This study showed that the XEN patency should be verified by OCT imaging in cases of encapsulated blebs. Although fibrosis plays the principal role, humor aqueous flow reduction could affect the "spacer" effect that inhibits the fibroblast attachments. To evaluate the application of the anterior segment optical coherence tomography (AS-OCT) imaging in studying the relationship between a low flow rate through the XEN63 and the development of a cystic bleb. Retrospective case series of 3 eyes presenting a cystic bleb after an XEN63 implantation for uncontrolled intraocular pressure (IOP). Demographic and clinical data were obtained from medical records. The imaging findings, complications, and managements following the surgery were evaluated. Three patients, with an average age of 67.3 years, initially showed a patent stent lumen and a functional bleb after surgery. The IOP of all eyes increased on average at 28.3 days from the surgery, with a mean value of 39.66mmHg. The slit lamp examination showed a cystic bleb. The AS-OCT imaging confirmed the previous finding and revealed either a partial or total occlusion of the stent internal ostium. A Nd:YAG laser, in proximity to the ostium, was performed to resolve the obstruction. Although the AS-OCT imaging showed the device patency and the IOP immediately decreased, the latter became elevated again. Consequently, in all the cases, a further needling procedure was needed to achieve an adequate IOP reduction. Six months after the two-step procedure, the IOP averaged 13.33mmHg, the XEN63 lumens appeared cleared, and the blebs showed a functional morphology. No adverse events were observed. The development of a cystic bleb may result from an altered balance between the flow rate through the XEN63 and the fibrosis development in the postoperative healing process. A proper follow-up based on slit lamp biomicroscopy, IOP measurement, and AS-OCT imaging is advisable to estimate and manage a cystic bleb following XEN63 implantation.

Comprehensive Analysis of Model Errors in Blueberry Detection and Maturity Classification: Identifying Limitations and Proposing Future Improvements in Agricultural Monitoring

In blueberry farming, accurately assessing maturity is critical to efficient harvesting. Deep Learning solutions, which are increasingly popular in this area, often undergo evaluation through metrics like mean average precision (mAP). However, these metrics may only partially capture the actual performance of the models, especially in settings with limited resources like those in agricultural drones or robots. To address this, our study evaluates Deep Learning models, such as YOLOv7, RT-DETR, and Mask-RCNN, for detecting and classifying blueberries. We perform these evaluations on both powerful computers and embedded systems. Using Type-Influence Detector Error (TIDE) analysis, we closely examine the accuracy of these models. Our research reveals that partial occlusions commonly cause errors, and optimizing these models for embedded devices can increase their speed without losing precision. This work improves the understanding of object detection models for blueberry detection and maturity estimation.

Selected routine laboratory tests in the clinical assessment of patients with obstructive sleep apnea.

Obstructive sleep apnea (OSA) is a chronic disease characterized by repetitive complete or partial occlusion of the upper airways during sleep with respiratory muscle effort, which leads to consecutive apneas and hypopneas. Obstruction of the upper airways during sleep leads to repetitive episodes of disrupted airflow and consequent changes in blood oxygenation, resulting in hypoxaemia and hypercapnia. Intermittent hypoxaemia induces the production of pro-inflammatory factors and promotes metabolic dysregulation and platelet aggregation. The main aim of this study was to determine differences, if any, in selected standard parameters in routine laboratory tests often used in GP practice between patients with obstructive sleep apnea, without comorbidities, and a well-defined control group with the absence of this syndrome proven in polygraphic examination. Of the 192 clinically assessed persons with suspected OSA and admitted to the Internal Medicine Department in Lublin, 85 were qualified for the study after application of exclusion criteria. Demographic and health behaviour-related data, medical history regarding sleep habits and cardiovascular disease, were collected from each patient. Apart from significantly higher MCV and MCH among the cpontrol group, no significant differences were found between patients with obstructive sleep apnea and the control group. The results can be useful for the holistic assessment of the health status of patients with newly-diagnosed OSA.

Depth-aware pose estimation using deep learning for exoskeleton gait analysis

In rehabilitation medicine, real-time analysis of the gait for human wearing lower-limb exoskeleton rehabilitation robot during walking can effectively prevent patients from experiencing excessive and asymmetric gait during rehabilitation training, thereby avoiding falls or even secondary injuries. To address the above situation, we propose a gait detection method based on computer vision for the real-time monitoring of gait during human–machine integrated walking. Specifically, we design a neural network model called GaitPoseNet, which is used for posture recognition in human–machine integrated walking. Using RGB images as input and depth features as output, regression of joint coordinates through depth estimation of implicit supervised networks. In addition, joint guidance strategy (JGS) is designed in the network framework. The degree of correlation between the various joints of the human body is used as a detection target to effectively overcome prediction difficulties due to partial joint occlusion during walking. Finally, a post processing algorithm is designed to describe patients’ walking motion by combining the pixel coordinates of each joint point and leg length. Our advantage is that we provide a non-contact measurement method with strong universality, and use depth estimation and JGS to improve measurement accuracy. Conducting experiments on the Walking Pose with Exoskeleton (WPE) Dataset shows that our method can reach 95.77% PCKs@0.1, 93.14% PCKs@0.08 and 3.55 ms runtime. Therefore our method achieves advanced performance considering both speed and accuracy.

Endoscope Automation Framework with Hierarchical Control and Interactive Perception for Multi-Tool Tracking in Minimally Invasive Surgery.

In the context of Minimally Invasive Surgery, surgeons mainly rely on visual feedback during medical operations. In common procedures such as tissue resection, the automation of endoscopic control is crucial yet challenging, particularly due to the interactive dynamics of multi-agent operations and the necessity for real-time adaptation. This paper introduces a novel framework that unites a Hierarchical Quadratic Programming controller with an advanced interactive perception module. This integration addresses the need for adaptive visual field control and robust tool tracking in the operating scene, ensuring that surgeons and assistants have optimal viewpoint throughout the surgical task. The proposed framework handles multiple objectives within predefined thresholds, ensuring efficient tracking even amidst changes in operating backgrounds, varying lighting conditions, and partial occlusions. Empirical validations in scenarios involving single, double, and quadruple tool tracking during tissue resection tasks have underscored the system's robustness and adaptability. The positive feedback from user studies, coupled with the low cognitive and physical strain reported by surgeons and assistants, highlight the system's potential for real-world application.

Metameric Inpainting for Image Warping.

Image-warping, a per-pixel deformation of one image into another, is an essential component in immersive visual experiences such as virtual reality or augmented reality. The primary issue with image warping is disocclusions, where occluded (and hence unknown) parts of the input image would be required to compose the output image. We introduce a new image warping method, Metameric image inpainting - an approach for hole-filling in real-time with foundations in human visual perception. Our method estimates image feature statistics of disoccluded regions from their neighbours. These statistics are inpainted and used to synthesise visuals in real-time that are less noticeable to study participants, particularly in peripheral vision. Our method offers speed improvements over the standard structured image inpainting methods while improving realism over colour-based inpainting such as push-pull. Hence, our work paves the way towards future applications such as depth image-based rendering, 6-DoF 360 rendering, and remote render-streaming.

Efficient Visual Tracking Based on Fuzzy Inference for Intelligent Transportation Systems

Remote monitoring is an important application of intelligent transportation systems (ITSs). The combination of monitoring equipment and tracking algorithms can be used to automatically track moving targets. The tracking algorithm based on the Siamese network is both accurate and efficient, and its development potential is better than that of other algorithms. Its output is a detection map that reflects the probability that any position in the search area is the center of the target’s bounding box, and the maximum value of the detection map is the center of the target’s bounding box predicted by the algorithm. Owing to partial occlusion, target deformation, out-of-view, and background clutter, local maxima in the detection map may also be the center of the target’s bounding box. A tracker’s ability to make accurate judgments is currently limited. Furthermore, previous trackers extracted only the target features in the initial frame as the matching template. Although this matching template is highly reliable, it cannot effectively combine the target features available in the subsequent frames. Therefore, in this study, fuzzy inference is introduced into the tracking process to analyze the reliability of the detection map. When this map is reliable, the target feature of the search area is transformed into a substitute template; otherwise, multiple substitute templates are selected from the template pool for parallel matching as per the set rules. The optimal result is selected from multiple detection results, based on the priority of the detection results when the initial frame is used as the matching template. Experimental results on multiple datasets show that the proposed algorithm is superior to other similar algorithms in terms of multiple assessment metrics and can improve the robustness of remote monitoring tasks in ITSs.

CreatureShop: Interactive 3D Character Modeling and Texturing From a Single Color Drawing.

Creating 3D shapes from 2D drawings is an important problem with applications in content creation for computer animation and virtual reality. We introduce a new sketch-based system, CreatureShop, that enables amateurs to create high-quality textured 3D character models from 2D drawings with ease and efficiency. CreatureShop takes an input bitmap drawing of a character (such as an animal or other creature), depicted from an arbitrary descriptive pose and viewpoint, and creates a 3D shape with plausible geometric details and textures from a small number of user annotations on the 2D drawing. Our key contributions are a novel oblique view modeling method, a set of systematic approaches for producing plausible textures on the invisible or occluded parts of the 3D character (as viewed from the direction of the input drawing), and a user-friendly interactive system. We validate our system and methods by creating numerous 3D characters from various drawings, and compare our results with related works to show the advantages of our method. We perform a user study to evaluate the usability of our system, which demonstrates that our system is a practical and efficient approach to create fully-textured 3D character models for novice users.

Multiscale Dynamic Graph Representation for Biometric Recognition with Occlusions.

Occlusion is a common problem with biometric recognition in the wild. The generalization ability of CNNs greatly decreases due to the adverse effects of various occlusions. To this end, we propose a novel unified framework integrating the merits of both CNNs and graph models to overcome occlusion problems in biometric recognition, called multiscale dynamic graph representation (MS-DGR). More specifically, a group of deep features reflected on certain subregions is recrafted into a feature graph (FG). Each node inside the FG is deemed to characterize a specific local region of the input sample, and the edges imply the co-occurrence of non-occluded regions. By analyzing the similarities of the node representations and measuring the topological structures stored in the adjacent matrix, the proposed framework leverages dynamic graph matching to judiciously discard the nodes corresponding to the occluded parts. The multiscale strategy is further incorporated to attain more diverse nodes representing regions of various sizes. Furthermore, the proposed framework exhibits a more illustrative and reasonable inference by showing the paired nodes. Extensive experiments demonstrate the superiority of the proposed framework, which boosts the accuracy in both natural and occlusion-simulated cases by a large margin compared with that of baseline methods. The source code is available here, or you can visit this website: https://github.com/RenMin1991/Dyamic-Graph-Representation.

High-Speed Videogrammetry with Mutually Guided Target Tracking under Occlusion for Masonry Building Structure Displacement on a Shaking Table

High-speed videogrammetric measurements are widely used on shaking tables. However, during progressive collapse experiments, the protective string used to ensure the safety of personnel and the shaking table, mandated by safety considerations, can partially occlude the structural model. To address the problem of inaccurate tracking of the ellipse targets in image sequences due to the partial occlusion, this paper proposes a novel mutually guided tracking method for the partial occlusion situations. Firstly, the strategy of loopback detection is proposed to eliminate the cumulative errors with the initial tracking model and to replace the initial results of the tracking with those from the loopback detection. Secondly, tiny offset compensation is used to solve the problem of deviations. The experimental results demonstrate that the proposed method can achieve single-point localization at the sub-millimeter level and interlayer localization at the millimeter level within partially occluded environments. It is important that the proposed method meets the requirements of experimental accuracy on shaking tables and ensures the safety of personnel and facilities.