Visual Metrics Research Articles

Exploring Built Environment Visual Interactions: A SoftBIM Data-Driven Approach for a Database About the Outdoor View

Windows and glazed facades provide outdoor views, serving as vital sources of visual information that aid navigation and interaction within buildings. These views can trigger psychological and physiological responses, affecting individual well-being. However, optimizing outdoor view quality is challenging due to the complex interplay of factors influencing the building’s experience of vision. Managing the complexity of optimizing outdoor view quality within current digital frameworks for building design presents significant challenges. A key issue lies in the ambiguity of certain visual metrics, which are often difficult to translate into explicit descriptors of spatial configurations. Even when such metrics are available, their practical use as guiding tools in the design process is frequently obstructed by complex data interoperability procedures. These procedures are necessary to enable seamless data transfer across the multiple software environments involved in the design process. This study advocates for the softBIM paradigm, which optimizes workflows by embedding visual analysis results into target geometries. Supported by this process, the calculation of a metric to measure the impact of existing and planned visual obstructions on the vision of the targeted landmarks is proposed and analysed. This metric is specifically applied to assess the visual information incoming to the vertical facades of building envelopes, a context of application that denotes criteria of assessment different from the ones usually applied in the most established frameworks for visual analysis (e.g., isovist analysis). SoftBIM enables effective automation strategies to aid the metric computation and the processing of the results to implement seamless export and data implementation. The visual metric is built upon implementing the Ladybug suite and addresses the different limitations in the target-based visibility calculation supported by the tool.

A Situated Inspection of Autonomous Vehicle Acceptance – A Population Study in Virtual Reality

The successful integration of Autonomous Vehicles (AVs) into daily life is influenced by various individual and contextual factors. This study examines key factors affecting acceptance and trust in AVs by assessing how interactive experiences influence user perceptions and adoption. Utilizing a Virtual Reality (VR) environment to simulate real-world driving conditions, the research investigates the impact of different levels of vehicle interaction—manual control, semi-autonomous, fully autonomous, and taxi-riding modes—on user and passenger trust, anxiety, perceived ease of use, and overall acceptance. A dual-method approach was employed, combining objective data collection through eye-tracking, which measures engagement and vigilance, with subjective user feedback gathered via the Autonomous Vehicle Acceptance Model (AVAM) questionnaire. The findings reveal a complex relationship between user control and trust in AV systems. While semi-autonomous conditions that incorporate user participation in decision-making enhance trust and intention to use, fully autonomous conditions influence trust but not intention to use significantly. However, semi- autonomous conditions also elicited higher anxiety levels compared to fully autonomous modes, suggesting a trade-off between interaction and comfort. Engagement levels, as indicated by visual metrics such as gaze patterns, were found to be critical for understanding user acceptance. These results highlight the importance of considering both subjective perceptions and objective behaviors in developing AV interfaces. The study contributes significant insights into the cognitive underpinnings of AV acceptance and underscores the need for strategies that both enhance user trust and minimize anxiety by finding an optimal balance between automation and user control. Further research into this balance is recommended to better accommodate the evolving nature of user trust and the cognitive complexities associated with semi-autonomous systems.

Transformer based Douglas-Rachford unrolling network for compressed sensing

Compressed sensing (CS) with the binary sampling matrix is hardware-friendly and memory-saving in the signal processing field. Existing Convolutional Neural Network (CNN)-based CS methods show potential restrictions in exploiting non-local similarity and lack interpretability. In parallel, the emerging Transformer architecture performs well in modelling long-range correlations. To further improve the CS reconstruction quality from highly under-sampled CS measurements, a Transformer based deep unrolling reconstruction network abbreviated as DR-TransNet is proposed, whose design is inspired by the traditional iterative Douglas-Rachford algorithm. It combines the merits of structure insights of optimization-based methods and the speed of the network-based ones. Therein, a U-type Transformer based proximal sub-network is elaborated to reconstruct images in the wavelet domain and the spatial domain as an auxiliary mode, which aims to explore local informative details and global long-term interaction of the images. Specially, a flexible single model is trained to address the CS reconstruction with different binary CS sampling ratios. Compared with the state-of-the-art CS reconstruction methods with the binary sampling matrix, the proposed method can achieve appealing improvements in terms of Peak Signal to Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM) and visual metrics. Codes are available at https://github.com/svyueming/DR-TransNet.

Enhanced bone assessment of the shoulder using zero-echo time MRI with deep-learning image reconstruction

ObjectivesTo assess a deep learning-based reconstruction algorithm (DLRecon) in zero echo-time (ZTE) MRI of the shoulder at 1.5 Tesla for improved delineation of osseous findings.MethodsIn this retrospective study, 63 consecutive exams of 52 patients (28 female) undergoing shoulder MRI at 1.5 Tesla in clinical routine were included. Coronal 3D isotropic radial ZTE pulse sequences were acquired in the standard MR shoulder protocol. In addition to standard-of-care (SOC) image reconstruction, the same raw data was reconstructed with a vendor-supplied prototype DLRecon algorithm. Exams were classified into three subgroups: no pathological findings, degenerative changes, and posttraumatic changes, respectively. Two blinded readers performed bone assessment on a 4-point scale (0-poor, 3-perfect) by qualitatively grading image quality features and delineation of osseous pathologies including diagnostic confidence in the respective subgroups. Quantitatively, signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of bone were measured. Qualitative variables were compared using the Wilcoxon signed‐rank test for ordinal data and the McNemar test for dichotomous variables; quantitative measures were compared with Student’s t-testing.ResultsDLRecon scored significantly higher than SOC in all visual metrics of image quality (all, p < 0.03), except in the artifact category (p = 0.37). DLRecon also received superior qualitative scores for delineation of osseous pathologies and diagnostic confidence (p ≤ 0.03). Quantitatively, DLRecon achieved superior CNR (95 CI [1.4–3.1]) and SNR (95 CI [15.3–21.5]) of bone than SOC (p < 0.001).ConclusionDLRecon enhanced image quality in ZTE MRI and improved delineation of osseous pathologies, allowing for increased diagnostic confidence in bone assessment.

Unidentified fish sounds as indicators of coral reef health and comparison to other acoustic methods

The global decline of coral reefs is a major contributor to the global biodiversity crisis and requires improved monitoring at these critically important habitats. Non-invasive passive acoustic assessments may address this need, leveraging the rich variety and spatiotemporal variability of biological sounds present in coral reef environments and offering near-continuous temporal coverage. Despite this, acoustic metrics that reliably represent coral reef health are still debated, and ground-truthing of methods is limited. Here we investigated how the prevalence of low frequency biotic sounds (without species information) relates to coral reef health, providing a foundation from which one can compare assessment methods. We first quantified call rates of these low frequency sounds for three reefs exhibiting different community assemblages around St. John, U.S. Virgin Islands, by manually annotating presumed fish noises for 1 min every 30 min across 8 days for each site. Annotated days were selected at key points across lunar cycles. These call rates were then compared with traditional visual surveys, and several acoustic methods and indices commonly used in underwater soundscape research. We found that, overall, manually detected fish call rates successfully differentiated between the three reefs, capturing variation in crepuscular activity levels–a pattern consistent with previous work that highlights the importance of diel choruses. Moreover, fish vocal rates were predictors of hard coral cover, fish abundance, and fish species richness, while most acoustic indices failed to parse out fine distinctions among the three sites. Some, such as the Acoustic Complexity Index, failed to reveal any expected differences between sites or times of day, while the Bioacoustic Index could only identify the most acoustically active reef, otherwise having weak correlations to visual metrics. Of the indices tested, root-mean-squared sound pressure level and Acoustic Entropy, both calculated in the low frequency fish band (50–1,200 Hz), showed the strongest association with visual health measures. These findings present an important step toward using soundscape cues for reef health assessments. The limited generalizability of acoustic indices across different locations emphasizes the need for caution in their application. Therefore, it is crucial to improve methods utilizing fish sounds, such as automatic fish call detectors that are able to generalize well to new soundscapes.

1151 Promoting Timely Treatment of Severe Hypertension with Live Visual Metric on Labor and Delivery

1151 Promoting Timely Treatment of Severe Hypertension with Live Visual Metric on Labor and Delivery

The role of pictorial cues and contrast for camouflage

Shadows that are produced across the surface of an object (self-shadows) are potentially an important source of information for visual systems. Animal patterns may exploit this principle for camouflage, using pictorial cues to produce false depth information that manipulates the viewer’s detection/recognition processes. However, pictorial cues could also facilitate camouflage by matching the contrast (e.g. due to shadows) of 3D backgrounds. Aside from studies of countershading (patterning that may conceal depth information), the role of self-shadows in camouflage patterns remains unclear. Here we investigated whether pictorial cues (self-shadows) increase the survival probability of moth-like prey presented to free-living wild bird predators relative to targets without these cues. We manipulated the presence of self-shadows by adjusting the illumination conditions to produce patterned targets under directional lighting (lit from above or from below; self-shadows present) or diffuse lighting (no self-shadows). We used non-patterned targets (uniform colour) as controls. We manipulated the direction of illumination because it has been linked with depth perception in birds; objects lit from above may appear convex while those lit from below can appear concave. As shadows influence contrast, which also determines detectability, we photographed the targets in situ over the observation period, allowing us to evaluate the effect of visual metrics on survival. We found some evidence that patterned targets without self-shadows had a lower probability of survival than patterned targets with self-shadows and targets with uniform colour. Surprisingly, none of the visual metrics explained variation in survival probability. However, predators increased their foraging efficiency over time, suggesting that predator learning may have overridden the benefits afforded by camouflaging coloration.

Urban Environmental Imaginaries and Aesthetic Sensibilities in Mumbai, India

Urban environmental aesthetics form a cornerstone in neoliberal development discourse in Mumbai, India. Formulated primarily on visual metrics, such as those of green lawns and modern architecture, these aesthetic sensibilities set up the horizon of what is seeable and sayable, serving to legitimize planning schemes while obscuring their social and environmental harms. This is evident in the city’s elite Hiranandani Gardens township, a project heavily contested on legal, humanistic, and environmental grounds. Beginning from “waste,” or spaces and perspectives that lack value in dominant discourses, I analyze how the production of developmentalist “value” relies on environmental aesthetics as well as the limits of such formulations. By way of three frames—empty buildings, an abandoned quarry, and remembered wilderness—I illustrate power structures that facilitate the conversion of waste into value, the contradictions and limits in dominant sustainability discourses, and the messy terrain of contestations that they face. The article contributes to critical development scholarship by emphasizing the significance of aesthetics in unveiling power relations entrained in the making of urban landscapes. I also extend creative engagements in geography by incorporating sensory engagements beyond the visual to interrupt dominant aesthetic sensibilities and open critical and creative ways of knowing urban nature.

The Hausdorff dimension of the harmonic measure for relatively hyperbolic groups

The paper studies the Hausdorff dimension of harmonic measures on various boundaries of a relatively hyperbolic group which are associated with random walks driven by a probability measure with finite first moment. With respect to the Floyd metric and the shortcut metric, we prove that the Hausdorff dimension of the harmonic measure equals the ratio of the entropy and the drift of the random walk.If the group is infinitely-ended, the same dimension formula is obtained for the end boundary endowed with a visual metric. In addition, the Hausdorff dimension of the visual metric is identified with the growth rate of the word metric. These results are complemented by a characterization of doubling visual metrics for accessible infinitely-ended groups: the visual metrics on the end boundary is doubling if and only if the group is virtually free. Consequently, there are at least two different bi-Hölder classes (and thus quasi-symmetric classes) of visual metrics on the end boundary.

Bayesian self-supervised learning allying with Transformer powered compressed sensing imaging

Deep learning based compressed sensing imaging algorithms usually adopt supervised learning mechanism, which generally require massive high-quality images paired with the measured data in the training process. However, clear images are difficult to obtain in some specific application scenarios. In view of this, we propose a self-attention powered multi-scale compressed sensing imaging network named BNN-SANet with the Bayesian self-supervised learning manner in this paper. BNN-SANet can automatically learn effective feature representation from the measured data and reconstruct high-quality images without large-scale training samples. In particular, the self-attention based Transformer employed in BNN-SANet is effective to exploit global and long-range dependencies. Multi-scale dual path design in BNN-SANet performs well in extracting the semantic information at different scales to further improve the CS reconstruction quality. Experimental results illustrate that the proposed approach is substantially superior to previous compressed sensing imaging methods in terms of Peak Signal to Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM) and visual metrics.

Eye-related quality of life and activities of daily living in pediatric retinoblastoma patients: A single-center, non-controlled, cross-sectional analysis.

Childhood retinoblastoma (RB) survivors are known to experience long-term morbidity; however, eye-related quality of life (QoL), which may significantly impact activities of daily living (ADL), has not been extensively studied in this population. The purpose of this cross-sectional study was to assess QoL and ADL morbidity among school-age RB survivors. The Pediatric Eye Questionnaire (PedEyeQ) and Roll Evaluation Activities of Life (REAL) were administered to childhood RB survivors between ages 5 and 17 followed at St. Louis Children's Hospital. Visual outcomes and demographic predictors of ADL and QoL were examined. Total 23 patients (mean age 9.6years) consented for participation in this study. All children experienced at least one domain on the PedEyeQ≤80%. Subjects and parents marked functional vision to be the most impacted domain with a median score of 82.5 and 83.4, respectively. Only 10.5% of participants scored above 75% on the ADL percentile rank. On multivariable analysis, decreased visual acuity (VA) was associated with worse "Child Functional" (odds ratio [OR] -59.2, p=.004) and "Parent Worry Function" (OR -66.5, p=.03) metrics. Decreased contrast sensitivity was associated with worse "Parent Impact" (OR 21.0, p = .02) and "Parent Worry Function" (OR 3.70, p=.04) metrics. Longer saccade horizontal latency was associated with a worse "Parent Worry Function" metric (OR 43.0, p=.009). On multivariable analysis, no variable was significantly associated with ADL. RB survivors have impaired QoL and ADL. Screening for such difficulties should strongly be considered for all RB patients. Additional studies may help predict morbidity based on visual metrics and demographic data.

Developing surgical skill level classification model using visual metrics and a gradient boosting algorithm.

Assessment of surgical skills is crucial for improving training standards and ensuring the quality of primary care. This study aimed to develop a gradient boosting classification model (GBM) to classify surgical expertise into inexperienced, competent, and experienced levels in robot-assisted surgery (RAS) using visual metrics. Eye gaze data were recorded from 11 participants performing four subtasks; blunt dissection, retraction, cold dissection, and hot dissection using live pigs and the da Vinci robot. Eye gaze data were used to extract the visual metrics. One expert RAS surgeon evaluated each participant's performance and expertise level using the modified Global Evaluative Assessment of Robotic Skills (GEARS) assessment tool. The extracted visual metrics were used to classify surgical skill levels and to evaluate individual GEARS metrics. Analysis of Variance (ANOVA) was used to test the differences for each feature across skill levels. Classification accuracies for blunt dissection, retraction, cold dissection, and burn dissection were 95%, 96%, 96%, and 96%, respectively. The time to complete only the retraction was significantly different among the 3 skill levels (p-value = 0.04). Performance was significantly different for 3 categories of surgical skill level for all subtasks (p-values<0.01). The extracted visual metrics were strongly associated with GEARS metrics (R2>0.7 for GEARS metrics evaluation models). Machine learning (ML) algorithms trained by visual metrics of RAS surgeons can classify surgical skill levels and evaluate GEARS measures. The time to complete a surgical subtask may not be considered a stand-alone factor for skill level assessment.

Comprehensive Evaluation and Optimization of the Data-Dependent LC-MS/MS Workflow for Deep Proteome Profiling.

Data-dependent liquid chromatography-tandem mass spectrometry (LC-MS/MS) is widely used in proteomic analyses. A well-performed LC-MS/MS workflow, which involves multiple procedures and interdependent metrics, is a prerequisite for deep proteome profiling. Researchers have previously evaluated LC-MS/MS performance mainly based on the number of identified peptides and proteins. However, this is not a comprehensive approach. This motivates us to develop MSRefine, which aims to evaluate and optimize the performance of the LC-MS/MS workflow for data-dependent acquisition (DDA) proteomics. It extracts 47 kinds of metrics, scores the metrics, and reports visual results, assisting users in evaluating the workflow, locating problems, and providing optimizing strategies. In this study, we compared and analyzed multiple pairs of datasets spanning different samples, methods, and instruments and demonstrated that the comprehensive visual metrics and scores in MSRefine enable us to evaluate the performance of the various experiments and provide optimal strategies for the identification of more peptides and proteins.

MP26-09 EYE MOVEMENT BEHAVIOR ASSOCIATES WITH EXPERTISE LEVEL IN ROBOT-ASSISTED SURGERY

You have accessJournal of UrologyCME1 Apr 2023MP26-09 EYE MOVEMENT BEHAVIOR ASSOCIATES WITH EXPERTISE LEVEL IN ROBOT-ASSISTED SURGERY Mehdi Seilanian Toussi, Saeed Shadpour, Kristopher Attwood, Qian Liu, Camille Gutierrez, james L. Mohler, and Somayeh B. Shafiei Mehdi Seilanian ToussiMehdi Seilanian Toussi More articles by this author , Saeed ShadpourSaeed Shadpour More articles by this author , Kristopher AttwoodKristopher Attwood More articles by this author , Qian LiuQian Liu More articles by this author , Camille GutierrezCamille Gutierrez More articles by this author , james L. Mohlerjames L. Mohler More articles by this author , and Somayeh B. ShafieiSomayeh B. Shafiei More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000003254.09AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: An objective method for assessing robot-assisted surgery (RAS) skills that can be used in clinical settings has not been established. This study aimed to compare visual metrics at three different skill levels—inexperienced, competent, or experienced— to determine whether eye gaze data differed among RAS surgeons. METHODS: Eleven right-handed participants who performed coagulation subtasks (monopolar or bipolar cautery) during hysterectomy, cystectomy, or nephrectomy on live pigs with the Da Vinci robot had their eye gaze data captured using TobiiPro2 eyeglasses. Visual metrics were extracted using eye gaze data (Table 1). An expert RAS surgeon evaluated each participant's performance and level of expertise after watching operation videos using the modified Global Evaluative Assessment of Robotic Skills (GEARS) assessment tool. Each metric was compared across the three skill levels—novice, competent, or experienced—using ANOVA. RESULTS: When participants performed coagulation using the dominant hand, the entropy of the right eye’s pupil diameter differed among skill levels (p-value = 0.01). When this subtask was completed with the non-dominant hand, the rates of change of the gaze directions of the left eye in the horizontal and vertical dimensions and the right eye in the vertical dimension differed (p-values = 2x10-6, 6x10-6, and 6x10-4, respectively) across skill levels. Table 2 shows the significance level for the difference in visual metrics between skill level pairs. CONCLUSIONS: Visual metrics differed significantly across RAS skill levels. The ease and efficacy of recording and evaluating visual data without interfering with the surgeon's work suggest a new objective surgical skill evaluation method that could be applied to clinical settings. Source of Funding: National Institute of Biomedical Imaging and Bioengineering of the National Institutes of Health under award number R01EB029398, the Alliance Foundation of Roswell Park Comprehensive Cancer Center, and the National Cancer Institute (NCI) grant P30CA016056 involving the use of Roswell Park Comprehensive Cancer Center’s Laboratory Animal Shared Resource and Applied Technology Laboratory for Advanced Surgery © 2023 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 209Issue Supplement 4April 2023Page: e355 Advertisement Copyright & Permissions© 2023 by American Urological Association Education and Research, Inc.MetricsAuthor Information Mehdi Seilanian Toussi More articles by this author Saeed Shadpour More articles by this author Kristopher Attwood More articles by this author Qian Liu More articles by this author Camille Gutierrez More articles by this author james L. Mohler More articles by this author Somayeh B. Shafiei More articles by this author Expand All Advertisement PDF downloadLoading ...

Current status and frontier tracking of the China HACCP system.

In today's booming society and in the age of science and technology, the diversification of food processing methods, the continuous extension of the food trade chain, and the potential hazard factors in the food production process all make people pay more and more attention to the establishment, development, and improvement of the hazard analysis and critical control points (HACCP) system. Only terminal control and post-processing supervision of food can guarantee the absolute safety of food. In the process of processing, it is particularly important to strictly identify and evaluate the food safety hazards. To better assist food production enterprises in establishing and implementing HACCP systems, to implement the primary responsibility of food safety, and to improve the theoretical level and practical application of HACCP system in China, an investigation of the current situation and development frontier of HACCP system in China was conducted. Based on the core journal database of China Knowledge Network, the Chinese Social Science Citation Index database, and the Chinese Science Citation Database as the literature search database platform, the study used the CiteSpace visual metrics software system to analyze 1,084 pieces of literature in the field of HACCP research, in order to track the dynamics and impact of research in this field by Chinese research institutions and major authors, and analyze the research hotspots in the field. It is important for further research on HACCP. The results of the study showed that (1) the number of publications in the field of HACCP in China increased steadily from 1992 to 2004 and then began to decrease; (2) the indexes of journals with more publications were more concentrated, and the journal Food Science published the most; (3) the indexes of major research institutions showed that the cultivation bases of the State Key Laboratory of Chinese Medicinal Materials in the Center of Chinese Medicine Resources of the Chinese Academy of Traditional Medicine, the Guangdong Institute of Occupational Diseases, the Nanchang University of Life Sciences, and the Guangdong Institute of Occupational Diseases were more concentrated. Prevention and Treatment Institute, School of Life Sciences of Nanchang University, China Aquatic Products Quality Certification Center, School of Food Science and Nutrition Engineering of China Agricultural University, and other research structures have the most publications and strong scientific research strength; (4) from the main author indicators, the research in the field of HACCP has formed a total of four more active research teams, involving Chinese herbal medicine, ecological planting, ecological agriculture, occupational disease prevention and treatment, light industry handicrafts, computer software and computer application, agricultural economy, and other research directions. The cooperation between the authors of each team is closer. It is suggested that in terms of food safety requirements, China should not only integrate the traditional supervision measures for food terminals and after the event but also reflect the role of food hazard analysis and assessment in the production process and comprehensively integrate the pre-production, production, and post-production management of food so that food can really be safe.

Exposing Deep Representations to a Recurrent Expansion with Multiple Repeats for Fuel Cells Time Series Prognosis.

The green conversion of proton exchange membrane fuel cells (PEMFCs) has received particular attention in both stationary and transportation applications. However, the poor durability of PEMFC represents a major problem that hampers its commercial application since dynamic operating conditions, including physical deterioration, have a serious impact on the cell performance. Under these circumstances, prognosis and health management (PHM) plays an important role in prolonging durability and preventing damage propagation via the accurate planning of a condition-based maintenance (CBM) schedule. In this specific topic, health deterioration modeling with deep learning (DL) is the widely studied representation learning tool due to its adaptation ability to rapid changes in data complexity and drift. In this context, the present paper proposes an investigation of further deeper representations by exposing DL models themselves to recurrent expansion with multiple repeats. Such a recurrent expansion of DL (REDL) allows new, more meaningful representations to be explored by repeatedly using generated feature maps and responses to create new robust models. The proposed REDL, which is designed to be an adaptive learning algorithm, is tested on a PEMFC deterioration dataset and compared to its deep learning baseline version under time series analysis. Using multiple numeric and visual metrics, the results support the REDL learning scheme by showing promising performances.

The Effect of Smart Colored Windows on Visual Performance of Buildings

The photochromic coating is a promising smart technology that provides different optical properties in response to daylight variations. The application of photochromic coatings with various colors/shades on window glass is one of the current research approaches for finding better energy saving techniques. The aim of this study was to develop a series of photochromic coatings for window glass and measure the impact of such smart technologies on occupants’ visual comfort. This paper examines the visual performance of building facades that utilize windows with different photochromic-coated glass. The visual performance data of three window types coated with nine different photochromic color shades were considered and compared to determine the best photochromic shades and window types that provide optimum visual metrics for the inside of the building. The results show that compared to no-coating glass, both the Daylight Glare Probability and the Useful Daylight Illuminance could be improved by using multi-color coatings that contain equal or different color proportions for photochromic window glass. From an energy-saving point of view, the results indicate that the windows coated with photochromic materials provide a better alternative to the no-coating window products.

Feasibility of smart glasses in supporting spinal surgical procedures in low- and middle-income countries: experiences from East Africa.

Telemedicine technology has been developed to allow surgeons in countries with limited resources to access expert technical guidance during surgical procedures. The authors report their initial experience using state-of-the-art wearable smart glasses with wireless capability to transmit intraoperative video content during spine surgery from sub-Saharan Africa to experts in the US. A novel smart glasses system with integrated camera and microphone was worn by a spine surgeon in Dar es Salaam, Tanzania, during 3 scoliosis correction surgeries. The images were transmitted wirelessly through a compatible software system to a computer viewed by a group of fellowship-trained spine surgeons in New York City. Visual clarity was determined using a modified Snellen chart, and a percentage score was determined on the smallest line that could be read from the 8-line chart on white and black backgrounds. A 1- to 5-point scale (from 1 = unrecognizable to 5 = optimal clarity) was used to score other visual metrics assessed using a color test card including hue, contrast, and brightness. The same scoring system was used by the group to reach a consensus on visual quality of 3 intraoperative points including instruments, radiographs (ability to see pedicle screws relative to bony anatomy), and intraoperative surgical field (ability to identify bony landmarks such as transverse processes, pedicle screw starting point, laminar edge). All surgeries accomplished the defined goals safely with no intraoperative complications. The average download and upload connection speeds achieved in Dar es Salaam were 45.21 and 58.89 Mbps, respectively. Visual clarity with the modified white and black Snellen chart was 70.8% and 62.5%, respectively. The average scores for hue, contrast, and brightness were 2.67, 3.33, and 2.67, respectively. Visualization quality of instruments, radiographs, and intraoperative surgical field were 3.67, 1, and 1, respectively. Application of smart glasses for telemedicine offers a promising tool for surgical education and remote training, especially in low- and middle-income countries. However, this study highlights some limitations of this technology, including optical resolution, intraoperative lighting, and internet connection challenges. With continued collaboration between clinicians and industry, future iterations of smart glasses technology will need to address these issues to stimulate robust clinical utilization.

Assessing and Quantifying the Surface Texture of Milk Powder Using Image Processing.

Milk powders produced from similar spray dryers have different visual appearances, while the surface appearance of the powder is a key quality attribute because the smoothness of the milk powder also affects flowability and handling properties. Traditionally quantifying this nuanced visual metric was undertaken using sensory panelists, which is both subjective and time consuming. Therefore, it is advantageous to develop an on-line quick and robust appearance assessment tool. The aim of this work is to develop a classification model which can classify the milk powder samples into different surface smoothness groups. This work proposes a strategy for quantifying the relative roughness of commercial milk powder from 3D images. Photogrammetry equipment together with the software RealityCapture were used to build 3D models of milk powder samples, and a surface normal analysis which compares the area of the triangle formed by the 3 adjacent surface normals or compares the angle between the adjacent surface normals was used to quantify the surface smoothness of the milk powder samples. It was found that the area of the triangle of the smooth-surface milk powder cone is smaller than the area of the triangle of the rough-surface milk powder cone, and the angle between the adjacent surface normals of the rough-surface milk powder cone is larger than the angle between the adjacent surface normals of the smooth-surface milk powder cone, which proved that the proposed area metrics and angle metrics can be used as tools to quantify the smoothness of milk powder samples. Finally, the result of the support vector machine (SVM) classifier proved that image processing can be used as a preliminary tool for classifying milk powder into different surface texture groups.

Training and Predicting Visual Error for Real-Time Applications

Visual error metrics play a fundamental role in the quantification of perceived image similarity. Most recently, use cases for them in real-time applications have emerged, such as content-adaptive shading and shading reuse to increase performance and improve efficiency. A wide range of different metrics has been established, with the most sophisticated being capable of capturing the perceptual characteristics of the human visual system. However, their complexity, computational expense, and reliance on reference images to compare against prevent their generalized use in real-time, restricting such applications to using only the simplest available metrics. In this work, we explore the abilities of convolutional neural networks to predict a variety of visual metrics without requiring either reference or rendered images. Specifically, we train and deploy a neural network to estimate the visual error resulting from reusing shading or using reduced shading rates. The resulting models account for 70%-90% of the variance while achieving up to an order of magnitude faster computation times. Our solution combines image-space information that is readily available in most state-of-the-art deferred shading pipelines with reprojection from previous frames to enable an adequate estimate of visual errors, even in previously unseen regions. We describe a suitable convolutional network architecture and considerations for data preparation for training. We demonstrate the capability of our network to predict complex error metrics at interactive rates in a real-time application that implements content-adaptive shading in a deferred pipeline. Depending on the portion of unseen image regions, our approach can achieve up to 2x performance compared to state-of-the-art methods.