Live Video Streaming Research Articles

The SEE-IT Trial: emergency medical services Streaming Enabled Evaluation In Trauma: a feasibility randomised controlled trial

BackgroundUse of bystander video livestreaming from scene to Emergency Medical Services (EMS) is becoming increasingly common to aid decision making about the resources required. Possible benefits include earlier, more appropriate dispatch and clinical and financial gains, but evidence is sparse.MethodsA feasibility randomised controlled trial with an embedded process evaluation and exploratory economic evaluation where working shifts during six trial weeks were randomised 1:1 to use video livestreaming during eligible trauma incidents (using GoodSAM Instant-On-Scene) or standard care only. Pre-defined progression criteria were: (1) ≥ 70% callers (bystanders) with smartphones agreeing and able to activate live stream; (2) ≥ 50% requests to activate resulting in footage being viewed; (3) Helicopter Emergency Medical Services (HEMS) stand-down rate reducing by ≥ 10% as a result of live footage; (4) no evidence of psychological harm in callers or staff/dispatchers. Observational sub-studies included (i) an inner-city EMS who routinely use video livestreaming to explore acceptability in a diverse population; and (ii) staff wellbeing in an EMS not using video livestreaming for comparison to the trial site.ResultsSixty-two shifts were randomised, including 240 incidents (132 control; 108 intervention). Livestreaming was successful in 53 incidents in the intervention arm. Patient recruitment (to determine appropriateness of dispatch), and caller recruitment (to measure potential harm) were low (58/269, 22% of patients; 4/244, 2% of callers). Two progression criteria were met: (1) 86% of callers with smartphones agreed and were able to activate livestreaming; (2) 85% of requests to activate livestreaming resulted in footage being obtained; and two were indeterminate due to insufficient data: (3) 2/6 (33%) HEMS stand down due to livestreaming; (4) no evidence of psychological harm from survey, observations or interviews, but insufficient survey data from callers or comparison EMS site to be confident. Language barriers and older age were reported in interviews as potential challenges to video livestreaming by dispatchers in the inner-city EMS.ConclusionsProgression to a definitive RCT is supported by these findings. Bystander video livestreaming from scene is feasible to implement, acceptable to both 999 callers and dispatchers, and may aid dispatch decision-making. Further assessment of unintended consequences, benefits and harm is required.Trial registration. ISRCTN 11449333 (22 March 2022). https://www.isrctn.com/ISRCTN11449333

Ray tracing-based construction of 3D background model for real-time stereoscopic rendering of live immersive video

Immersive video stored in multiview video-plus-depth format can provide viewers with vivid immersive experiences. However, rendering such video in real time in immersive environments remains a challenging task due to the high resolution and refresh rate demanded by recent extended reality displays. An essential issue in this immersive rendering is the disocclusion problem that inevitably occurs when virtual views are synthesized via the de facto standard 3D warping technique. In this paper, we present a novel virtual view synthesis framework that, from a live immersive video stream, renders stereoscopic images in real time for a freely moving virtual viewer. The main difference from previous approaches is that the surrounding background environment of the immersive video’s virtual scene is progressively reproduced on the fly directly in the 3D space while the input stream is being rendered. To allow this, we propose a new 3D background modeling scheme that, based on GPU-accelerated real-time ray tracing, efficiently and incrementally builds the background model in compact 3D triangular mesh. Then, we demonstrate that the 3D background environment can effectively alleviate the critical disocclusion problem in the immersive rendering, eventually reducing spatial and temporal aliasing artifacts. It is also suggested that the 3D representation of background environment enables extension of the virtual environment of immersive video by interactively adding 3D visual effects during rendering.

Validity of remote live stream video evaluation of the North Star Ambulatory Assessment in patients with Duchenne muscular dystrophy.

Conducting functional assessments remotely can help alleviate the burden of in-person assessment on patients with Duchenne muscular dystrophy and their caregivers. The objective of this study was to evaluate whether scores from remote functional assessment of patients with Duchenne muscular dystrophy correspond to in-person scores on the same functional assessments. Remote live stream versus in-person scores on the North Star Ambulatory Assessment (including time [seconds] to complete the 10-meter walk/run and time to rise from the floor [supine to stand]) were assessed using statistical analyses, including intraclass correlation coefficient, and Pearson, Spearman, and Bland-Altman analyses. The remote and in-clinic assessments had to occur within 2 weeks of one another to be considered for this analysis. This analysis included patients with Duchenne muscular dystrophy, aged 4 to 7 years. Participants in this analysis received delandistrogene moxeparvovec (as part of SRP-9001-101 [Study 101; NCT03375164] or SRP-9001-102 [Study 102; NCT03769116]) or were randomized to receive placebo (in Part 1 of Study 102). This study evaluates score reproducibility between live stream remote scoring versus in-person functional assessments as determined by intraclass correlation coefficient, and Pearson, Spearman, and Bland-Altman analyses. The results showed that scores from remote functional assessment of patients with Duchenne muscular dystrophy strongly correlated with those obtained in person. These findings demonstrate congruence between live stream remote and in-person functional assessment and suggest that remote assessment has the potential to reduce the burden on a family by supplementing in-clinic visits.

Intelligent Face Recognition Based Students’ Attendance System

This paper aims at developing an intelligent face recognition students’ attendance system to enhance school attendance tracking. The system is made up of four phases- database of students’ details, face detection, face recognition and attendance report. The database stores all the students’ details and images of the students’ face captured while face detection and recognition is carried out with convolutional neural network algorithms from the face recognition and opencv library. As faces are detected and recognized from live streaming video of the classroom, attendance are recorded into an excel file and then sent to a real time database. The system also contains a mobile interface through which the course instructors can access information at all time. The methodology adopted for this work is object-oriented analysis and design methodology (OOADM) while programming language used is Python. This work has helped immensely to eliminate the issue of proxy attendance as well as reduce the time wasted in manual attendance system. It is very beneficial to schools and other institutions where attendance is required.

Audience participation fighting game: Exploring social facilitation for an enhanced APG experience

This paper discusses the popularity of live streaming video games and its potential to address psychological challenges, especially during the COVID-19 pandemic. An audience participation game (APG) that involve massive audiences in gameplay, blurring the lines between viewers and players, is introduced. The game highlights the dynamic adjustment of AI character strengths based on audience inputs, specifically cheering and jeering. The study examines factors that influence user experience (UX) and activeness in APG. System evaluation includes comprehensive AI testing, consisting of 500,000 one-minute game rounds, and a user experiment involving 82 participants. UX assessment is conducted using a pairwise preference, four-alternative forced choice (4-AFC), version of the Game User Experience Satisfaction Scale (GUESS). Finally, the paper concludes by offering guidelines and hypotheses for future research in the field of APGs.

Gesture-Based Control of Multimedia Player Using Python and OpenCV

The increasing significance of computers in our daily lives, coupled with the rise of ubiquitous computing, has necessitated effective human-computer interaction. Hand gesture recognition systems have emerged as a real-time video-based solution for detecting and interpreting hand gestures, offering intelligent and natural human-computer interaction (HCI) methods. This project focuses on leveraging human hands as input devices for computer operation. Developed using Python and the OpenCV library, the program utilizes a computer webcam to capture and analyze hand shapes and patterns. The program provides real-time feedback by displaying recognized hand gestures on the live video stream. The ultimate outcome of this project is an application that enhances user experiences in contactless systems. The project recognizes and detects human hand motions using the Python computer language through a process flow that includes background subtraction, hand ROI segmentation, contour detection, and finger recognition. Techniques for processing images are used, including hand gesture detection, pattern recognition, thresholding, and contour detection. The processing of incoming photos and the creation of related keystrokes are made possible by OpenCV, a rich set of image processing tools

Facial Landmark Detection Using Machine Learning

Facial landmark detection is a pivotal task in the field of computer vision, holding significant implications across various applications, including facial analysis, augmented reality, facial recognition, and emotion detection. In visual communication, the face serves as a primary means of conveying information, and humans possess an innate ability to discern a wealth of information about another person's intentions, identity, and emotions merely by observing their facial expressions. The process of facial landmark detection using machine learning involves training a model on a dataset comprising real-time facial images, where each image is meticulously annotated with the coordinates of crucial facial landmarks. These landmarks typically include points representing the eyes, nose, mouth, and other facial features. Once trained, the model becomes proficient in recognizing and predicting the precise locations of these landmarks in new, unseen images and videos. The primary objective of this work is to predict facial landmarks in real-time using a live webcam input. This task is achieved through a two-step process. First, a Convolutional Neural Network (CNN) is trained on a comprehensive dataset, such as the 300W-LP dataset available on platforms like Kaggle. This dataset consists of facial images meticulously annotated with 68 distinct facial landmarks. The CNN learns to extract intricate facial features and landmark relationships from this training data, enabling it to recognize these landmarks with high accuracy. With the trained CNN in place, the next step is to extend its capabilities to perform facial landmark detection on live video streams. This involves integrating face detection techniques to identify and isolate faces within the live video feed. Once a face is detected, the CNN can then be applied to predict the locations of the 68 facial landmarks in real-time, enhancing our ability to understand and interpret facial expressions and movements in dynamic scenarios. In summary, this work underscores the significance of facial landmark detection in various computer vision applications. By training a CNN on a dataset of annotated facial images and integrating it with live video feeds, we aim to empower machines with the ability to understand and interpret human facial expressions and gestures in real-time, opening up new possibilities for applications in fields like human-computer interaction, emotion analysis, and beyond.

Perception and attitude toward the regulation of online video streaming (in South Korea)

Abstract As the production and consumption of live video streaming have increased, a general concern is that live video streaming might yield social problems. This paper investigated how people perceived the current status of live video streaming through a nationwide survey. The survey was conducted with 825 users and 335 non-users in South Korea. The results demonstrate that people perceived live video streaming has more impact on adolescents than themselves, which confirms that the previous study of third-person perception. Respondents also evaluated that the current self-regulatory system is not functioning properly and regulation of live video streaming is required. Especially non-users are more supportive of regulation than users. The perception bias, the difference between the perceived influence on self and adolescents, is the strongest predictor of the need for regulation. Because of the difference between users and non-users regarding the perception of live video streaming, this study recommends that the policymakers should consider the actual status of live video streaming and not perception-based biases in orienting regulation.

Simulation of a Tele-Surgery process through a Live Video Streaming service, using Simu5G and Wowza

Telematic services that require low latency for real-time applications and that make use of wireless mobile networks are increasingly popular. In the case of Tele-Surgery services that employ Live Video Streaming (LVS), latency times of the order of 1ms are needed. Given the difficulty of implementing real 5G test scenarios that enable this type of service to be characterized, this paper presents an emulation scenario that uses Simu5G to simulate the network, Wowza as a real video server, OBS Studio for transmission and VLC media player for content playback. This emulation scenario makes it possible to modify such parameters as bitrate, bandwidth, frequency and numerology index in order to evaluate different network configurations. By varying these parameters in a controlled way, packet losses are obtained for different bitrate values. The best quality video was obtained with a bitrate of 3000 Kbps.

IBLUECULTURE: A NOVEL SYSTEM OF REAL-TIME UNDERWATER IMAGE TRANSMISSION IN A VIRTUAL REALITY ENVIRONMENT, AS A NEW MANAGERIAL APPROACH FOR UNDERWATER CULTURAL HERITAGE

Abstract. The Mediterranean is rich in ancient and modern shipwrecks and submerged sites of great archaeological, historical, and cultural value. Most of those sites tend to be relatively unknown, even to people living in the area, mostly due to the inherent limitation in physical approach. As a result, these sites are left unknown and unprotected. The aim of the iblueCulture project was to create a system that can make Underwater Cultural Heritage sites broadly accessible and raise public awareness on their location, content, and value. This approach is also meant to provide an effective management strategy for the constant, real-time monitoring and, therefore, protection of such sites, while in accordance with the sustainable tourism development goals for islands and coastal areas. This project, as implemented, can offer an immersive dry dive experience to the public, while providing management bodies and stakeholders with the capability of remotely monitoring the UCH sites in real-time, through live-streaming video. This ability can be vital in some cases, especially when involving sites in greater depths or in remote areas with little maritime traffic. The system is also expected to assist in underwater research, especially in deep water sites, and other educational activities or possible scientific research.

The Influence Of Tiktok Live Video Streaming, Price Discounts, And Free Shipping On Purchase Decisions

This research is motivated by the trend of Tiktok during the COVID-19 pandemic. This trend can be used to overcome economic problems due to declining public purchasing power. The purpose of this study was to determine the effect of live video streaming on Tiktok, discounted prices, and free shipping on online purchasing decisions. The population of this study is Skintific product users in DKI Jakarta who buy products on the Tiktok live platform. The sampling method used was purposive sampling. The samples obtained were 114 respondents. Based on the results of this study it was found that Tiktok live video streaming and free shipping have a positive and significant effect on purchasing decisions. Meanwhile, price discounts have no effect on purchasing decisions. The results of this study can be used by related sellers as a consideration for increasing sales through increasing consumer purchasing decisions.

DAMPAK PENGARUH PENGGUNAAN APLIKASI VIDEO LIVE STREAMING DI SMARTPHONE PADA KALANGAN PELAJAR

This study aims to determine the effect of using live streaming video applications that are currently popularly used by students. Live streaming video application itself is a video sharing application that is broadcast live and real time so that users can broadcast what activities are done and can be watched by everyone who has the same application and account. For interaction users can make two-way video calls with other users or interactions through the chat service provided. These applications are in the market such as Bigolive, Live.me, Ome.tv, Instagram live and others. This research was conducted using regression analysis. The analysis results obtained from this study that the use of live streaming video applications among students does have an impact on students such as students rarely attend religious activities, often make noise in class, often toy smartphones during lessons and even 51.58% talk dirty.

Advanced motion tracking for interactive mass spectrometry imaging (IMSI)

Mass spectrometry imaging (MSI) is a powerful analytical technique for the two-dimensional (2D) localization of chemicals on surfaces. Conventional MSI experiments require to predefine the surface of interest based on photographic or microscopic images. Typically, these boundaries can no longer be changed or adjusted once the experiment has been started. In terms of a more interactive approach we recently developed a pen-like ionization interface which is directly connected to the mass spectrometer. The device allows the user to ionize chemicals by desorption electrospray ionization (DESI) and to freely move the interface over a surface of interest. A mini camera, which is mounted on the tip of the pen, magnifies the desorption area and enables a simple positioning of the pen. The combination of optical data from the camera module and chemical data obtained by mass analysis facilitates a novel type of imaging experiment: interactive mass spectrometry imaging (IMSI). For this application, we present a novel approach for a robust, optical flow-based motion detection. While the live video stream from the camera is used to track the pen's motion across the surface a post-acquisition algorithm correlates the coordinates of the pen trajectory with respective mass spectra obtained from a simultaneous mass spectrometric data acquisition. This algorithm is no longer dependent on a single, manually applied optical marker on the sample surface, which has to be visible on all video frames throughout the analysis. The advanced DESI-IMSI method was successfully tested on inkjet-printed letters as well as mouse brain tissue samples. Validation of the results was done by comparing DESI-IMSI with standard DESI-MSI data.

Predicting potential real-time donations in YouTube live streaming services via continuous-time dynamic graphs

Online live streaming platforms, such as YouTube Live and Twitch, have seen a surge in popularity in recent years. These platforms allow viewers to send real-time gifts to streamers, which can bring significant profits and fame. However, there has been little research on the donation system used on live streaming platforms. This paper aims to fill this gap by building a continuous-time dynamic graph to model the interactions among viewers based on real-time chat messages and predict the real-time donations on live streaming platforms. To achieve this, we propose a novel model called the Temporal Difference Graph Neural Network (TDGNN) that incorporates imbalanced learning strategies to identify potential donors during live streaming. Our model can predict the exact time when donations will appear. We conduct extensive experiments on three live streaming video datasets and demonstrate that our proposed model is more effective and robust than other baseline methods from other fields.

Cost-effective live video streaming for internet of connected vehicles using heterogeneous networks

Smart vehicles of Internet of Connected Vehicles (IoCV) create Ad-Hoc networks and are persistently connected to the Internet through different network access technologies like Wifi, cellular, and dedicated short range communication (DSRC). A vehicle may prefer one network access technology over another based on availability, coverage area, and network access cost. The choice also depends on application requirements, like delay-tolerant or delay-sensitive, and application objectives, like maximizing data rate, maximizing cellular traffic offloading, etc. Cellular traffic offloading using Wifi access points and vehicle-to-vehicle (V2V) collaborations are very challenging due to the intermittent short coverage areas of Wifi access points and highly dynamic connectivity of V2V Ad-Hoc network. Most existing works on traffic offloading have considered delay-tolerant or on-demand services, whereas delay-constrained live video streaming services are mostly ignored. This work is focused on live video streaming services over IoCVs, where the non-triviality of the network selection task is demonstrated by formulating the task as an integer linear programming problem (ILPP). Accordingly, a distributed algorithm is proposed, which greedily maximizes cellular traffic offloading while significantly reducing the control packet overheads. Compared to existing works, the proposed work provides the best service effectiveness with a balanced performance on traffic offloading, service efficiency, and user satisfaction.

The impact of streamer emotions on viewer gifting behavior: evidence from entertainment live streaming

PurposeThe boom in live streaming has intensified competition among streamers for viewers' gifts, which makes it meaningful to study the factors that affect the viewers’ gifting behavior. Given the emotional attachment between streamers and viewers, the authors set out to elucidate a new driver on viewer gifting: expressions of the streamer. This research aims to explore the impact of streamer emotions on the viewer gifting behaviors, including free and paid gifting. The loyalty level of the viewers is also introduced as a moderating factor to investigate the heterogeneous effect of streamer emotions on gifting behavior.Design/methodology/approachThe dataset the authors collected consists of two parts, including 1809.69 h of live streaming videos and 358,002 gift giving records. Combined with deep learning methods and regression analysis, the authors performed empirical tests on the 81,110 valid samples. Several robustness checks were also conducted to ensure the reliability of main results.FindingsThe empirical results show that streamer emotions do have effects on viewers' free and paid gifting behavior. The authors’ findings show that positive streamer expressions, such as happiness and surprise, have a positive influence on viewer gifting behavior. However, some negative expressions, like sadness, can also have a positive impact. Moreover, the authors discovered that higher viewer loyalty amplifies the positive effect of streamer emotions and reduces the negative effect.Originality/valueThis research contributes to the study about streamer emotions and viewers' consumption behavior, which extends the application of emotion as social information model (EASI model) in the live streaming setting. The authors carefully divide the gifting behavior into two types: free and paid, and study how these two types are affected by streamer emotions. Besides, these effects are analyzed within viewers of different loyalty levels. This study offers practical emotion management strategies for streamers and live streaming platforms to gain more economic profits.

Digital Transformation of Agricultural Products Purchasing: From the Perspective of Short Videos Live-Streaming

In the current competitive market situation, live streaming has become an essential part of the digital transformation of agriculture. In this study, we empirically examine the influence of short video live streaming on the purchase of agricultural products. A regression model was developed using SPSS 23 software. The final results of this study show that short video live streaming has a significant effect on the sales of agricultural products. Consumer cognition and emotion show mediation in the impact between the Key Opinion Leaders (KOL) of charisma, content richness, and interactive evaluation on the purchase of agricultural products. This study explores the path of the impact of short video live streaming on the purchasing of agricultural products. It is beneficial to help agriculture-related practitioners develop new marketing paths, reduce the waste of agricultural products, and improve the economic income of related practitioners.

TIKTOK SHOP: CONSUMER CULTURE TRANSFORMATION IN THE ERA OF SOCIAL MEDIA

Background. The presence of social media has transformed human communication and interaction patterns. Communication typically occurred through face-to-face interactions. However, in the modern era, thanks to technological advancements, communication can take place without the need for physical meetings. Research Purpose. This research aims to analyze changes in consumer culture in the context of TikTok Shop, a social media-based video platform connecting users to virtual stores, particularly among millennial female students in the Blitar Raya area. Research Method. This study employs a qualitative descriptive method. Data collection is carried out through unstructured interviews using purposive sampling. This research was conducted on students in the Blitar Raya area using sample selection criteria. The data analysis in this research is conducted using scaling measurement. Findings. Consumption patterns on the TikTok Shop social media platform include the intensity of watching live streaming and short videos containing product reviews from buyers. Millennial students in Blitar tend to consider online shopping as an effective and efficient method. They trust the authenticity of products more because promotions on the TikTok Shop social media platform create the impression that they can see the products as if in a physical store. Conclusion. Through this research, it is hoped that society can become more aware of the influence of social media on consumer behavior, avoiding falling into false consciousness and resisting the allure of advertising. Furthermore, the role of capitalism in fostering consumer behavior by blurring the line between wants and needs should also be given attention.

Intelligent solution for automatic online exam monitoring

<p><span lang="EN-US">E-learning has shown significant growth in recent years due to its unavoidable benefits in unexpected situations such as the coronavirus disease 2019 (COVID-19) pandemic. Indeed, online exam is a very important component of an online learning program. It allows higher education institutions to assess student learning outcomes. However, cheating in exams is a widespread phenomenon worldwide, which creates several challenges in terms of integrity, reliability and security of online examinations. In this study, we propose a continuous authentication system for online exam. Our intelligent inference system based on machine learning algorithms and rules, detects continuously any inappropriate behavior in order to limit and prevent fraud. The proposed model includes several modules to enhance security, namely the registration module, the continuous students’ identity verification and control module, the live video stream and the end-to-end sessions recording.</span></p>

Role of live streaming surgical video in CVTS residency program in India: a strategy to improve learning curve of surgical residents.

Recording surgical video is not new in medicine. But not many surgical residency programs in India have this facility. The coronavirus disease (COVID) pandemic made us search for new ways to progress ahead in our surgical careers. We present a way to record surgical videos and live stream them to a select audience comprising surgical residents and faculty, wherever they may be. This may become a standard of teaching once adopted by all top surgical residency programs across the country.