Real-time Capture Research Articles

CURRENT STATE OF THE ART HISTORIC BUILDING INFORMATION MODELLING

Abstract. In an extensive review of existing literature a number of observations were made in relation to the current approaches for recording and modelling existing buildings and environments: Data collection and pre-processing techniques are becoming increasingly automated to allow for near real-time data capture and fast processing of this data for later modelling applications. Current BIM software is almost completely focused on new buildings and has very limited tools and pre-defined libraries for modelling existing and historic buildings. The development of reusable parametric library objects for existing and historic buildings supports modelling with high levels of detail while decreasing the modelling time. Mapping these parametric objects to survey data, however, is still a time-consuming task that requires further research. Promising developments have been made towards automatic object recognition and feature extraction from point clouds for as-built BIM. However, results are currently limited to simple and planar features. Further work is required for automatic accurate and reliable reconstruction of complex geometries from point cloud data. Procedural modelling can provide an automated solution for generating 3D geometries but lacks the detail and accuracy required for most as-built applications in AEC and heritage fields.

Real-time 3D motion capture by monocular vision and virtual rendering

Networked 3D virtual environments allow multiple users to interact over the Internet by means of avatars and to get some feeling of a virtual telepresence. However, avatar control may be tedious. 3D sensors for motion capture systems based on 3D sensors have reached the consumer market, but webcams remain more widespread and cheaper. This work aims at animating a user’s avatar by real-time motion capture using a personal computer and a plain webcam. In a classical model-based approach, we register a 3D articulated upper-body model onto video sequences and propose a number of heuristics to accelerate particle filtering while robustly tracking user motion. Describing the body pose using wrists 3D positions rather than joint angles allows efficient handling of depth ambiguities for probabilistic tracking. We demonstrate experimentally the robustness of our 3D body tracking by real-time monocular vision, even in the case of partial occlusions and motion in the depth direction.

Investigation of Two Prototypes of Novel Noncontact Technologies for Automated Real-Time Capture of Incremental Drug Administration Data From Syringes.

An ideal electronic anesthesia recording system would be capable of not only recording physiological data but also injectable drug doses given, including those given incrementally from one syringe, without recourse to manual data entry. We compared 2 prototype devices which wirelessly recognized individual syringes and measured changes in their plunger positions via 2 different optical noncontact means, allowing calculation of incremental drug doses given. Both devices incorporated a radio-frequency identification reader, which wirelessly read a unique code from a radio-frequency identification tag within syringe drug labels. A custom-designed cradle oriented any inserted 1-mL to 20-mL syringe in a repeatable position. The "laser" device had a moving laser beam broken by the end of the syringe plunger. The infrared (IR) device measured time of travel of IR light from a sender to a syringe plunger and back to a receiver. Both devices could therefore determine the drug and volume administered since the previous occasion when any syringe had been used. For each syringe size of 1, 2, 5, 10, and 20 mL, 121 plunger-length measurements were made over their full range, with each machine against a reference method of water filling and weighing using a randomized de Bruijn sequence. For every syringe size, the laser device showed greater accuracy and precision, lower bias, and narrower limits of agreement (95% confidence intervals = bias ± 1.96 SD) than the IR device when compared to the reference method. For all syringe sizes, the range of bias was -0.05 to 0.32 mL for the laser and -2.42 to 1.38 mL for the IR. Lin concordance correlation coefficient values for the IR versus reference methods ranged from 0.6259 to 0.9255, with the lowest coefficients seen in syringes with the shortest distance of plunger travel (2 and 5 mL), while in laser versus reference comparisons, these coefficients were similar (0.9641-0.9981) over all syringe lengths. Both devices measured syringe volume changes, demonstrating potential for measuring incremental drug doses, recording these, and also the time of each measurement. The IR device had no moving parts, which would be advantageous in a clinical situation. However, the current embodiment was not deemed accurate enough for clinical use, potentially remediable through improvements in hardware and software design. The laser device showed high accuracy and precision over all syringe sizes and contained volumes, and was considered potentially accurate enough for clinical use with suitable development.

Real-time data capture with electronic cigarettes for smoking cessation programme: a cloud platform for behavioural research

Tobacco smoking is a major risk factor for many chronic diseases, which led to the popularity of electronic cigarette (e-cigarette) and showed to be an effective tool for tobacco smoking...

Active brainwave pattern generation for brain-to-machine communication.

Over the years of research, Electroencephalogram (EEG) signal study has grown to give promising outcomes. A lot of research has been done on implementing brain-computer-interfaces, and the brain-computer interface (BCI) algorithm as well as the study of the effects of different stimuli on brain signals. This paper intends to make progress toward that goal by developing a responsive real-time EEG-based brain-to-machine communication system by generating distinct EEG signals at will and identification of the explicit pattern that they reflect for the presented self-induced internal visual and auditory stimuli. The brain-to-machine communication system delivers the real-time capture, analysis, and visualization of the brain signal patterns that can be used for smart medical applications such as rehabilitation robotic control, smart wheelchair, etc.

Realtime Capture of High-Speed Traffic on Multi-Core Platform

Realtime Capture of High-Speed Traffic on Multi-Core Platform

Wearable low-cost inertial sensor-based electrogoniometer for measuring joint range of motion

El análisis del movimiento humano ha llegado a ser fundamental para una amplia gama de aplicaciones, tales como terapias físicas, neuro-rehabilitación, medicina deportiva, la evaluación de la funcionalidad del sistema motor y la medicina del trabajo. Este artículo se centra en el diseño, implementación y validación de un electrogoniómetro portátil basado en sensores inerciales y magnéticos para la adquisición del rango articular de movimiento. El sistema se compone de dos unidades de medición inercial y un microcontrolador que permite la captura de movimiento humano en tiempo real. El electrogoniómetro se validó tanto en condiciones estáticas como dinámicas, en comparación con un electrogoniómetro estándar comercial para movimientos de la articulación del codo. Para validación estática, el coeficiente de correlación de concordancia (ρC) obtenido fue 0.9605. El ρC obtenido para los movimientos cíclicos de baja velocidad fue 0.9830 y el ρC obtenido para los movimientos cíclicos de velocidad moderada fue 0.9619.

Understanding Environmental and Contextual Influences of Physical Activity During First-Year University: The Feasibility of Using Ecological Momentary Assessment in the MovingU Study.

BackgroundIt is well established that drastic declines in physical activity (PA) occur during young adults’ transition into university; however, our understanding of contextual and environmental factors as it relates to young adults’ PA is limited.ObjectiveThe purpose of our study was to examine the feasibility of using wrist-worn accelerometers and the use of ecological momentary assessment (EMA) to assess the context and momentary correlates of PA on multiple occasions each day during first-year university.MethodsFirst-year university students were asked to participate in the study. The participants completed a brief questionnaire and were subsequently asked to wear an ActiGraph GT9X-Link accelerometer and respond to a series of EMA prompts (7/day) via their phones for 5 consecutive days.ResultsA total of 96 first-year university students with smartphones agreed to participate in the study (mean age 18.3 [SD 0.51]; n=45 females). Overall, there was good compliance for wearing the accelerometers, with 91% (78/86) of the participants having ≥2 days of ≥10 hours of wear time (mean=3.53 valid days). Students were generally active, averaging 10,895 steps/day (SD 3413) or 1123.23 activity counts/min (SD 356.10). Compliance to EMA prompts was less desirable, with 64% (55/86) of the participants having usable EMA data (responding to a minimum of ≥3 days of 3 prompts/day or ≥4 days of 2 prompts/day), and only 47% (26/55) of these participants were considered to have excellent EMA compliance (responding to ≥5 days of 4 prompts/day or ≥ 4 days of 5 prompts/day).ConclusionsThis study represents one of the first studies to use an intensive real-time data capture strategy to examine time-varying correlates of PA among first-year university students. These data will aim to describe the physical and social contexts in which PA occurs and examine the relationships between momentary correlates of PA among the first-year university students. Overall, current results suggest that wrist-worn accelerometers and EMA are feasible methods for data collection among the young adult population; however, more work is needed to understand how to improve upon compliance to a real-time data capture method such as EMA.

Cow behavior recognition based on image analysis and activities

Abstract: For the rapid and accurate identification of cow reproduction and healthy behavior from mass surveillance video, in this study, 400 head of young cows and lactating cows were taken as the research object and analyzed cow behavior from the dairy activity area and milk hall ramp. The method of object recognition based on image entropy was proposed, aiming at the identification of motional cow object behavior against a complex background. Calculating a minimum bounding box and contour mapping were used for the real-time capture of rutting span behavior and hoof or back characteristics. Then, by combining the continuous image characteristics and movement of cows for 7 d, the method could quickly distinguish abnormal behavior of dairy cows from healthy reproduction, improving the accuracy of the identification of characteristics of dairy cows. Cow behavior recognition based on image analysis and activities was proposed to capture abnormal behavior that has harmful effects on healthy reproduction and to improve the accuracy of cow behavior identification. The experimental results showed that, through target detection, classification and recognition, the recognition rates of hoof disease and heat in the reproduction and health of dairy cows were greater than 80%, and the false negative rates of oestrus and hoof disease were 3.28% and 5.32%, respectively. This method can enhance the real-time monitoring of cows, save time and improve the management efficiency of large-scale farming. Keywords: cow behavior, target segmentation, image entropy, image moment, activities, intelligent analysis DOI: 10.3965/j.ijabe.20171003.3080 Citation: Gu J Q, Wang Z H, Gao R H, Wu H R. Cow behavior recognition based on image analysis and activities. Int J Agric & Biol Eng, 2017; 10(3): 165–174.

Real-Time Multi-View Facial Capture with Synthetic Training

We present a real-time multi-view facial capture system facilitated by synthetic training imagery. Our method is able to achieve high-quality markerless facial performance capture in real-time from multi-view helmet camera data, employing an actor specific regressor. The regressor training is tailored to specified actor appearance and we further condition it for the expected illumination conditions and the physical capture rig by generating the training data synthetically. In order to leverage the information present in live imagery, which is typically provided by multiple cameras, we propose a novel multi-view regression algorithm that uses multi-dimensional random ferns. We show that higher quality can be achieved by regressing on multiple video streams than previous approaches that were designed to operate on only a single view. Furthermore, we evaluate possible camera placements and propose a novel camera configuration that allows to mount cameras outside the field of view of the actor, which is very beneficial as the cameras are then less of a distraction for the actor and allow for an unobstructed line of sight to the director and other actors. Our new real-time facial capture approach has immediate application in on-set virtual production, in particular with the ever-growing demand for motion-captured facial animation in visual effects and video games.

Real-Time Multi-View Facial Capture with Synthetic Training

We present a real-time multi-view facial capture system facilitated by synthetic training imagery. Our method is able to achieve high-quality markerless facial performance capture in real-time from...

Development of a Self-Calibrated Motion Capture System by Nonlinear Trilateration of Multiple Kinects v2

In this paper, a Kinect-based distributed and real-time motion capture system is developed. A trigonometric method is applied to calculate the relative position of Kinect v2 sensors with a calibration wand and register the sensors' positions automatically. By combining results from multiple sensors with a nonlinear least square method, the accuracy of the motion capture is optimized. Moreover, to exclude inaccurate results from sensors, a computational geometry is applied in the occlusion approach, which discovers occluded joint data. The synchronization approach is based on an NTP protocol that synchronizes the time between the clocks of a server and clients dynamically, ensuring that the proposed system is a real-time system. Experiments for validating the proposed system are conducted from the perspective of calibration, occlusion, accuracy, and efficiency. Furthermore, to demonstrate the practical performance of our system, a comparison of previously developed motion capture systems (the linear trilateration approach and the geometric trilateration approach) with the benchmark OptiTrack system is conducted, therein showing that the accuracy of our proposed system is $38.3\%$ and 24.1% better than the two aforementioned trilateration systems, respectively.

Development of an African Esophageal Cancer Consortium

Abstract 44 Background: Esophageal cancer is the sixth leading cause of cancer death worldwide. It kills 400,000 people every year, most of whom live in two distinct geographic bands across central Asia and along the eastern Africa corridor that extends from Ethiopia to South Africa. In these high-risk areas, nearly all cases are esophageal squamous cell carcinoma (ESCC). Our group and others have performed many etiologic, genetic, and early detection and treatment studies of ESCC in central Asia, but this disease remains essentially unstudied in eastern Africa. Over the past few years, several groups have begun quality studies of ESCC in Africa, including case-control studies in Dar es Salaam, Tanzania (University of California, San Francisco, and Muhimbili University of Health and Allied Sciences); Eldoret, Kenya (International Agency for Research on Cancer and Moi University); Moshi, Tanzania (International Agency for Research on Cancer and Kilimanjaro Clinical Research Institute); Bomet, Kenya (National Cancer Institute and Tenwek Hospital); and Lilongwe, Malawi (National Cancer Institute and the UNC-Malawi Project). In November 2015, these groups met and decided to create the African Esophageal Cancer Consortium. The goals of the consortium are to raise awareness of the importance of ESCC in Africa, to coordinate etiologic and molecular studies of ESCC in high-risk populations, and to facilitate provision of therapeutic training and equipment aimed to improve survival and quality of life. Methods: The first coordinated activity was to standardize questionnaires so that data can later be compared and combined. The consortium has embraced mobile health technologies through development of an mHealth app for real-time data capture on a phone or tablet and to collect harmonized data from the outset, increase efficiency, eliminate transcription mistakes, and allow real-time quality control and supervision of field activities from any location. Results: The consortium held its second annual meeting in September 2016. At this meeting, the five member sites affirmed their commitment to the consortium and the first study coordinator was named. Conclusion: Case-control studies in Moshi, Bomet, and Lilongwe are using the mobile app. A case-control study in Dar es Salaam is complete, with results pending. Coordinated genome-wide association and genomic studies are planned, with collection of biospecimens from multiple sites. The consortium is actively working with partners in China to provide affordable stents in Africa for palliative ESCC treatment as well as to secure training to safely and effectively place stents. Annual meetings will continue to follow-up on progress and develop new initiatives. AUTHORS' DISCLOSURES OF POTENTIAL CONFLICTS OF INTEREST No COIs from the authors.

Autostereoscopic augmented reality visualization for depth perception in endoscopic surgery

Augmented reality (AR) has received increasing attention in minimally invasive surgery (MIS) applications. The goal of applying AR techniques to MIS is to enhance a surgeon's perception of the spatial relationship by overlaying invisible structures (e.g. tumor or vessels) onto the in vivo endoscopic video acquired during the surgery. One of primary issues of AR visualization is to provide correct depth perception for visible and invisible structures. In this paper, we present a video-based AR system consisting of functional modules for real-time 3D surface capture, reconstruction, and registration with pre-operative segmented CT model. The real-time 3D registration allows precise overlay of invisible structures onto 2D video for AR visualization. The AR overlay result is displayed on a multi-view autostereoscopic lenticular LCD. To study and compare the efficacy of AR visualization techniques, we investigated five different AR visualization modes. Both simulated and in vivo experiments were carried out and autostereoscopic AR visualization results were given. Evaluation and comparison for depth perception between five AR visualization modes are presented. Finally, we conclude the characteristics of these visualization modes. The novelty of our work lies in successful implementation of an end-to-end 3D autostereoscopic AR system from real-time reconstruction and registration with our multi-channel 3D endoscope, and systematic evaluation and comparison of five different visualization modes for depth perception.

Closing the Science-Practice Gap With Technology: From Evidence-Based Practice to Practice-Based Evidence.

Closing the Science-Practice Gap With Technology: From Evidence-Based Practice to Practice-Based Evidence.

Immersive Distributed Design Through Real-Time Capture, Translation, and Rendering of Three-Dimensional Mesh Data1

With design teams becoming more distributed, the sharing and interpreting of complex data about design concepts/prototypes and environments have become increasingly challenging. The size and quality of data that can be captured and shared directly affects the ability of receivers of that data to collaborate and provide meaningful feedback. To mitigate these challenges, the authors of this work propose the real-time translation of physical objects into an immersive virtual reality environment using readily available red, green, blue, and depth (RGB-D) sensing systems and standard networking connections. The emergence of commercial, off-the-shelf RGB-D sensing systems, such as the Microsoft Kinect, has enabled the rapid three-dimensional (3D) reconstruction of physical environments. The authors present a method that employs 3D mesh reconstruction algorithms and real-time rendering techniques to capture physical objects in the real world and represent their 3D reconstruction in an immersive virtual reality environment with which the user can then interact. Providing these features allows distributed design teams to share and interpret complex 3D data in a natural manner. The method reduces the processing requirements of the data capture system while enabling it to be portable. The method also provides an immersive environment in which designers can view and interpret the data remotely. A case study involving a commodity RGB-D sensor and multiple computers connected through standard TCP internet connections is presented to demonstrate the viability of the proposed method.

A Virtual Out-of-Body Experience Reduces Fear of Death.

Immersive virtual reality can be used to visually substitute a person’s real body by a life-sized virtual body (VB) that is seen from first person perspective. Using real-time motion capture the VB can be programmed to move synchronously with the real body (visuomotor synchrony), and also virtual objects seen to strike the VB can be felt through corresponding vibrotactile stimulation on the actual body (visuotactile synchrony). This setup typically gives rise to a strong perceptual illusion of ownership over the VB. When the viewpoint is lifted up and out of the VB so that it is seen below this may result in an out-of-body experience (OBE). In a two-factor between-groups experiment with 16 female participants per group we tested how fear of death might be influenced by two different methods for producing an OBE. In an initial embodiment phase where both groups experienced the same multisensory stimuli there was a strong feeling of body ownership. Then the viewpoint was lifted up and behind the VB. In the experimental group once the viewpoint was out of the VB there was no further connection with it (no visuomotor or visuotactile synchrony). In a control condition, although the viewpoint was in the identical place as in the experimental group, visuomotor and visuotactile synchrony continued. While both groups reported high scores on a question about their OBE illusion, the experimental group had a greater feeling of disownership towards the VB below compared to the control group, in line with previous findings. Fear of death in the experimental group was found to be lower than in the control group. This is in line with previous reports that naturally occurring OBEs are often associated with enhanced belief in life after death.

Big Data, Predictive Analytics, and Quality Improvement in Kidney Transplantation: A Proof of Concept.

We sought proof of concept of a Big Data Solution incorporating longitudinal structured and unstructured patient-level data from electronic health records (EHR) to predict graft loss (GL) and mortality. For a quality improvement initiative, GL and mortality prediction models were constructed using baseline and follow-up data (0-90 days posttransplant; structured and unstructured for 1-year models; data up to 1 year for 3-year models) on adult solitary kidney transplant recipients transplanted during 2007-2015 as follows: Model 1: United Network for Organ Sharing (UNOS) data; Model 2: UNOS & Transplant Database (Tx Database) data; Model 3: UNOS, Tx Database & EHR comorbidity data; and Model 4: UNOS, Tx Database, EHR data, Posttransplant trajectory data, and unstructured data. A 10% 3-year GL rate was observed among 891 patients (2007-2015). Layering of data sources improved model performance; Model 1: area under the curve (AUC), 0.66; (95% confidence interval [CI]: 0.60, 0.72); Model 2: AUC, 0.68; (95% CI: 0.61-0.74); Model 3: AUC, 0.72; (95% CI: 0.66-077); Model 4: AUC, 0.84, (95 % CI: 0.79-0.89). One-year GL (AUC, 0.87; Model 4) and 3-year mortality (AUC, 0.84; Model 4) models performed similarly. A Big Data approach significantly adds efficacy to GL and mortality prediction models and is EHR deployable to optimize outcomes.

Avenues for Future Minority Stress and Substance Use Research among Sexual and Gender Minority Populations

ABSTRACTSexual and gender minority individuals (lesbian, gay, bisexual, transgender, queer [LGBTQ]) experience elevated rates of minority stress and associated substance use relative to their heterosexual and cisgender counterparts. Although the minority stress–substance use relationship is well documented, less is currently known regarding day-to-day minority stress and substance use risk processes. Rather than criticize existing literature, this review highlights future directions and advocates for the use of experience sampling methodology as a valuable research tool regarding real-time data capture. Greater utilization of this methodology is encouraged and expected to improve understanding of daily minority stress processes, and provide insight into real-time risk monitoring and intervention strategies.

VP113 Reframing “Disinvestment”: Appropriateness And Real-Time Data Capture

INTRODUCTION:Disinvestment – stopping the use of health technologies with little or no clinical benefits – can reduce health system costs and change practice towards effective innovations. In England, efforts to support disinvestment have included the National Institute of Health and Care Excellence (NICE's) list of 900+ “Do Not Do (DND) technologies”. However, recent studies show ongoing, varying rates of DND technology, suggesting limited influence. In response, we propose a shift in perspective and reframing of the concept of ‘disinvestment’ to focus on ‘appropriateness’.METHODS:We have developed a two-pronged approach to ‘appropriateness’. The first develops local clinician agreements on specific, appropriate indications for a technology. The "RAND/UCLA Appropriateness Method” is being extended in this stage. This knowledge management process enables incorporation of local knowledge and practice via consensus development amongst local experts alongside scientific evidence. The second, and more novel, element is to specify and routinely collect data on technology use associated with these agreed indications. Shifting from cross-sectional clinical audits to real-time monitoring will highlight variation from the agreed indications, which can inform reimbursement policy and decisions. Evaluating the feasibility and sustainability of this approach will provide important lessons for scaling up.RESULTS:For clinicians, the reframing from disinvestment to appropriateness has important implications. The approach recognizes that there are very few technologies with absolutely no benefit. Framing the management of technology diffusion in terms of appropriateness emphasises benefits and maximises value for public health. Furthermore, combining local agreements on indications with real-time data capture facilitates intelligent, flexible commissioning and informs real-life evaluation.CONCLUSIONS:Shifting the perspective from disinvestment to appropriateness overcomes negative associations of stopping healthcare technologies. Linking clinically driven decisions on technology indications with routine data capture on use can transform clinical audit and healthcare commissioning. The combination of these approaches is, we believe, a novel approach on which more reflection and research will be valuable.