Real-time Video Streaming Research Articles

The Design of Teaching System for College Piano Online Course Considering Network Delay and Bandwidth Optimization

The rapid growth of online piano education emphasizes the need for efficient teaching content transmission, yet challenges such as network latency and bandwidth constraints remain prevalent. This study explores solutions including content delivery networks (CDNs) and adaptive streaming technologies. CDNs minimize delays by distributing servers globally, while adaptive streaming dynamically adjusts video quality based on network conditions. However, issues such as bandwidth variability across regions and congestion during peak hours persist. To address these challenges, we propose a machine learning-based dynamic bandwidth control model. This model predicts network traffic fluctuations to optimize bandwidth allocation and improve transmission efficiency. Additionally, we evaluate the application of a novel algorithm for managing live video streams within the WebRTC framework. By employing proximal policy optimization (PPO), the proposed approach demonstrates superior performance compared to rule-based and traditional learning algorithms. Through experiments, PPO is shown to enhance video smoothness, clarity, and bandwidth prediction accuracy across diverse network conditions. The study also highlights PPO’s robustness and training efficiency, offering valuable insights for optimizing real-time video streaming and improving the delivery of online piano education.

Pothole Detection Using Yolo and Computer Vision

Road infrastructure is the infrastructural core and has an important function in transportation and economic growth activities. Nevertheless, potholes have a profound effect on the safety of driving, as they lead to vehicle repairs and operating costs, and on the effectiveness of road systems. State-of-the- art pothole detection methods involve either manual inspection of the road or sensor- based methods, which are inefficient, labor-intensive and expensive. Because of this, there is an increasing demand for automatic intelligent systems to identify potholes automatically and effectively in order to improve road maintenance and roadside safety. This paper introduces an intelligent pothole detection system, using combination of deep learning and real-time video processing for effective pothole detection. The system is based on a state-of-the-art object detection algorithm (YOLO (You Only Look Once) model) to identify potholes in real-time video streams. The YOLO model facilitates real-time high-accuracy pothole detection and localization, which can support automated log and analysis of freeway conditions. The suggested system is an automated, time- saving, economical tool that helps local governments to detect and repair road defects. Keywords—Keywords: computer vision, YOLO, machine learning, CNN, real-time detection, geolocation- based detection, video analysis.

ENHANCED CROWD EMOTION DETECTION IN OCCLUDED ENVIRONMENTS USING YOLOV5 AND CONVOLUTIONAL NEURAL NETWORKS

A deep learning methodology examines facial emotional identification when faces exist in partially obstructed conditions of crowds. YOLOv5-tiny functions for face detection while RepVGG handles emotion classification within this method. Training of the emotion recognition model employed FER-2013 dataset but detection enhancements came from processing WIDER FACE dataset. Experimental testing shows that YOLOv5 reaches a 91% detection success rate while RepVGG delivers an 87.5% accuracy level in emotion classification above standard CNN architectures such as ResNet and Efficient Net. The system detects emotions directly in real-time streaming video data which qualifies it for application in crowd monitoring and surveillance and behavioral analysis solutions. Future research initiatives aim to develop better methods for handling obscuration along with methods to optimize speed when applying the system to large-scale deployments.

PENERAPAN POLA FIBONACCI UNTUK PENGATURAN QOS (QUALITY OF SERVICE) JARINGAN

In managing network quality of service (QoS), this research uses the Fibonacci pattern to optimize delay control and bandwidth allocation. QoS is very important in contemporary network management, especially considering the increasing demand for stable and effective data services. This study prioritizes data based on traffic levels using a Fibonacci algorithm simulation. Each priority is assigned a value corresponding to the Fibonacci sequence, which allows for resource allocation that is more in line with network load.The simulation was conducted under normal and overload conditions. The research results show that conventional methods, such as round-robin and weighted fair queuing, can improve QoS efficiency with the Fibonacci pattern by up to 15%. This improvement primarily focuses on managing important data packets such as real-time communication and video streaming, and reducing latency. Additionally, this technique is better at adapting to traffic changes.The research results show that the Fibonacci pattern can be an innovative method for managing network QoS, especially for complex priority needs. By using the Fibonacci pattern as a data priority management technique, this research helps improve network quality of service (QoS). This method is capable of improving bandwidth allocation efficiency and reducing latency by up to 15% compared to conventional approaches such as Round-Robin and Weighted Fair Queuing. The main contribution of this research is to offer a new approach based on Fibonacci patterns that can be adapted to the dynamics of network traffic.

Концептуальная структура системы поддержки принятия решений ситуационной видеоаналитики для многообъектного распознавания

Information is provided on the growing interest in situational video analytics (SVA) technologies in various fields of activity. The paper describes a trend towards the implementation of SVA systems based on cognitive artificial intelligence technologies, which make it possible to detect an object and its location in a video stream in real time with a high degree of accuracy. The architecture of a decision support system (DSS) with the possibility of multi-object recognition is proposed. The key logical components of the DSS in the field of SVA are highlighted, as well as the functions and purpose of each component are described. The role of the decision maker for implementing multi-object recognition when searching for an object in a video stream is particularly emphasized. The classification of neural networks by types and fields of application is given, and it is revealed that convolutional neural networks are used to solve video analytics problems. Examples of using the YOLOv5 convolutional model in the DSS model database management system in IAS tasks for detecting the presence of objects on video data are considered. A block diagram of the SVA object recognition algorithm has been developed. A series of experiments has been conducted to train a convolutional neural network model on a unique dataset, on an expanded dataset, and with a new additional object. This organization of experiments is aimed at improving the quality and accuracy of object recognition and exploring the possibility of multi-object recognition. As a result of the experiment, the final trained neural network model was tested and its potential capabilities were analyzed for use in the SVA DSS, taking into account the accuracy of the model. The accuracy was 91.6% for the validation set containing 2 objects. The results obtained using a trained neural network of the YOLOv5 architecture confirms the importance of convolutional neural networks as a key component of the database of SVA DSS models.

Quality of Video Streaming: Taxonomy

Real-time and live video streaming are very important topics in networks nowadays, either wired or wireless, and so it is significant to address and study the behavior, advantages, and disadvantages of different techniques and algorithms. This article presents a comprehensive overview for researchers who are willing to conduct research in video compression standards, error correction algorithms for improving the quality of video streaming, forward error correction codes with feedback and forward error correction algorithms with unequal loss (or error) protection techniques for enhancing video streaming quality, description about the layered video streaming, single and multi-paths video streaming, good description about video streaming over wireless networks, the problem of erasure packets and packet erasure networks/packet erasure Channels, layered coding compression techniques, error detecting and correcting algorithms, Unequal Error Protection (UEP) techniques and schemes, multipath video streaming, and recent researches that based on hybrid solutions over 3G, 4G, 5G, WiMAX, and Wi-Fi wireless networks.

Extremely Low-resolution RFID Vision for Real-time and Visually-anonymized Action Recognition

Despite the potential of vision-based personal monitoring (e.g., healthcare), private data leakage concerns hinder its wide deployment in personal spaces (e.g., bedrooms). A body of data anonymization designs was proposed throughout image processing and federated learning. They commonly store high-quality images and videos locally, which are anonymized via post-processing before cloud upload. However, the recent IoT camera hacking and local data leakage call for anonymized data at the sensing stage. Also, continuous and pervasive monitoring without blind spots in complicated indoor spaces requires a scalable and economic system. This paper presents Mosaic , a vision-based end-to-end action recognition framework that (i) intrinsically achieves data anonymity from the sensing stage and (ii) battery-free operation for blind spot-free continuous monitoring. Mosaic leverages an extremely low resolution (eLR) Near-Infrared (NIR) image sensor with 6 × 10 pixels for video anonymity and an RFID-compliant fully-passive tag with four solar cells for real-time eLR video streaming under as low as 30 lux (e.g., deep in the shelf without direct light). This is accompanied by a lightweight action recognition neural network for real-time inference (18.4 ms on Intel(R) Core i7-8700). Mosaic achieves an average of 98% accuracy on 10 action classes, hitting the balance between data anonymity and high-precision action recognition. Taking advantage of the NIR (non-visible) frequency, Mosaic also works in the dark without disturbing sleep. Lastly, wildfire detection reaching 20 m was demonstrated, showcasing the potential for outdoor monitoring.

Enhancing real-time mobile health video streams: A cross-layer Region-of-Interest based approach

Enhancing real-time mobile health video streams: A cross-layer Region-of-Interest based approach

Enhancing Real-Time Video Streaming Quality via MPT-GRE Multipath Network

The demand for real-time 4K video streaming has introduced technical challenges due to the high bandwidth, low latency, and minimal jitter required for high-quality user experience. Traditional single-path networks often fail to meet these requirements, especially under network congestion and packet loss conditions, which degrade video quality and disrupt streaming stability. This study evaluates Multipath tunnel- Generic Routing Encapsulation (MPT-GRE), a technology designed to address these challenges by enabling simultaneous data transmission across multiple network paths. By aggregating bandwidth and adapting dynamically to network conditions, MPT-GRE enhances resilience, maintains quality during network disruptions, and offers throughput nearly equal to the sum of its physical paths’ throughput. This feature ensures that even if one path fails, the technology seamlessly continues streaming through the remaining path, significantly reducing interruptions. We measured key video quality metrics to assess MPT-GRE’s performance: Structural Similarity Index Measure (SSIM), Mean Squared Error (MSE), and Peak Signal-to-Noise Ratio (PSNR). Our results confirm that the MPT-GRE tunnel effectively improves SSIM, PSNR, and reduces MSE compared to single-path streaming, offering a more stable, high-quality viewing experience. Our results indicate that analyzing the SSIM, MSE, and PSNR values for 4K video streaming using the MPT tunnel demonstrates a significant performance improvement compared to a single path. The improvement percentages of the SSIM and PSNR values for the MPT tunnel are (29.05% and 29.04%) higher than that of the single path, while MSE is reduced by 81.17% compared to the single path.

Remotely Operated Video Enhanced Receiver

The "Remotely Operated Video Enhanced Receiver (ROVER) is a versatile system designed for remote environmental monitoring and data acquisition, tailored for challenging terrains, including extraterrestrial surfaces such as the Moon. The project integrates multiple sensors and a real-time video system to provide precise and actionable insights. A soil moisture sensor detects the presence of water or moisture in the substrate, triggering an LED to blink as an indicator. Additionally, a smoke and gas detector identifies harmful gases or smoke in the air, with an LED notification to alert the user to environmental hazards. These features make the system highly effective for monitoring and exploration in remote or hazardous environments. The system also employs an LDR (Light Dependent Resistor) to automatically activate the solar panel, optimizing energy usage by harnessing sunlight when available. A camera module provides real-time video streaming and recording capabilities, enabling visual observation of the surroundings. Designed for remote operation, ROVER offers a practical solution for applications such as planetary exploration, environmental hazard monitoring, and autonomous research operations. The integration of sensors with automated alerts and video recording enhances its usability and reliability for various scientific and industrial purposes.

ПОВЫШЕНИЕ ПРОПУСКНОЙ СПОСОБНОСТИ РЕГУЛИРУЕМЫХ ПЕРЕКРЕСТКОВ НА ОСНОВЕ СИНЕРГИИ КОМПЬЮТЕРНОГО ЗРЕНИЯ И АДАПТИВНОГО РЕГУЛИРОВАНИЯ СКОРОСТИ

The paper discusses new approaches to the arrangement of non-stop traffic flows at signaled crossings using coordinated traffic management. The study objective is to develop a mathematical model for determining the recommended traffic speed on the stretches of the urban road network using computer vision to ensure the non-stop traffic of a group of vehicles when crossing a signaled intersection. The model is unique because it takes into account the queue parameters of out-of-group vehicles, as well as the condition of the road surface. The study presents a method for calculating the time of non-stop passage of cars over crossings of the road network using AIMS-Eco monitoring system. The system uses real-time video stream analysis technology based on YOLOv4 neural network to obtain data on traffic parameters. The coefficients of influence of the traffic flow structure and the condition of the road surface on the time of queuing outside the group vehicles are characterized, which makes it possible to more accurately assess the impact of these factors on traffic dynamics. The dependences studied include those of the recommended speed of the leading car and the capacity of the road network section on the number of extra-group vehicles, taking into account the travel time of the queue of extra-group vehicles. The developed mathematical model makes it possible to increase the average flow velocity in the section of the stop line by 10-15% due to the arrangement of non-stop passage of signaled intersections by group vehicles. The results achieved are of practical importance for increasing the traffic capacity of the road network, improving road and environmental safety of automobile traffic.

Semantic-Driven Ghosting-Free Image Fusion Using Dual Gain Video Stream With FPGA

Conventional methods that merge multiple images with different exposure levels often suffer from blur and ghosting due to object movement. Existing ghosting removal algorithms are usually complex and slow, making them unsuitable for real-time video applications. To address this challenge, this study proposes a novel ghosting-free image fusion method using a dual gain video stream setup on an FPGA. IMX662 image sensor is employed, which simultaneously captures both HCG and LCG images with the same exposure time, enabling efficient HDR image synthesis. The proposed method directly addresses the source of the problem, eliminating the need for post-processing steps, thereby preserving algorithmic simplicity. Experimental results reveal that the proposed method not only removes ghosting by 100% but also processes data on an FPGA 98.79% faster than traditional software-based HDR fusion techniques, enabling real-time video stream processing. This dual gain, ghosting-free fusion algorithm demonstrates promising potential for use in high-speed photography and surveillance.

The Construction of a Stream Service Application with DeepStream and Simple Realtime Server Using Containerization for Edge Computing

This paper addresses the increasing demand for efficient and scalable streaming service applications within the context of edge computing, utilizing NVIDIA Jetson Xavier NX hardware and Docker. The study evaluates the performance of DeepStream and Simple Realtime Server, demonstrating that containerized applications can achieve performance levels comparable to traditional physical machines. The results indicate that WebRTC provides superior low-latency capabilities, achieving delays of around 5 s, while HLS typically experiences delays exceeding 10 s. Performance tests reveal that CPU usage for WebRTC can exceed 40%, which is higher than that of HLS and RTMP, while memory usage remains relatively stable across different streaming protocols. Additionally, load testing shows that the system can support multiple simultaneous connections, but performance degrades significantly with more than three devices, highlighting the limitations of the current hardware setup. Overall, the findings contribute valuable insights into building efficient edge computing architectures that support real-time video processing and streaming.

Enhancing Surveillance with Machine and Deep Learning-Based Facial Recognition Model: A Proposed Approach for Identification

There is limited understanding and utilization of facial recognition models in surveillance. This work addresses the underutilization of facial recognition Models in surveillance contexts. A Model that leverages its proposed facial recognition technology to monitor and locate individuals in real-time video streams and dataset images. The model begins with an initial dataset containing images of specific individuals, such as university professors, missing persons, or criminals. These images extract essential facial attributes for training models capable of identifying individuals in live video recordings. Upon a successful match, the model identifies individuals and tracks their movements using surveillance cameras. A primary objective of this work is to integrate the proposed model seamlessly with the current surveillance infrastructure, minimizing operational costs and disruptions. The work employs two main artificial intelligence approaches: Support Vector Machine achieved an accuracy of 85.33%, demonstrating effective facial recognition compared to the Multilayer Perceptron with 89.0% accuracy. Additionally, Linear Discriminant Analysis achieved the highest classification accuracy at 87.66%. Furthermore, our custom deep learning model demonstrated exceptional accuracy, ranging between 99.5% and 99.8%, showcasing significant advancements over existing methodologies.

Closed-loop Clustering-based Global Bandwidth Prediction in Real-Time Video Streaming

Closed-loop Clustering-based Global Bandwidth Prediction in Real-Time Video Streaming

Development of a Real-Time Traffic Density Detection Website Using YOLOv8-Based Digital Image Processing with OpenCV

This study introduces a real-time traffic density monitoring system utilizing YOLOv8-based digital image processing to improve traffic management efficiency. By leveraging YOLOv8’s enhanced speed and precision, the system detects and classifies five types of vehicles and displays traffic data through a web interface developed with OpenCV and Flask. Key implementation features include real-time video streaming and accurate detection metrics, with the system achieving 96% Precision, 84% Recall, and an F1 Score of 90% during field testing in Bogor. This indicates the system’s potential for minimizing manual traffic monitoring and aiding traffic authorities in making data-driven decisions. The research also discusses the system’s integration into urban traffic management and its scalability for diverse environments.

Improvement of mathematical methods for ensuring security based on real-time video sequence analysis

Purpose of research. Currently, mathematical methods of video sequence analysis represent a structured set of approaches to image recognition based on the difference in the glow of different image areas. Many of these values are described using mathematical dependencies, however, existing approaches work only for standard images obtained during video data processing. The purpose of this study is to develop a new approach to analyzing images obtained, including those using terahertz radiation, which has specific characteristics, both physical and mathematical.Methods. The following theoretical and empirical scientific methods were used in this study. Analysis (the analysis of the currently known mathematical methods of image processing in order to recognize images is carried out). Synthesis (a fundamentally new approach to security systems is proposed, which is a single system consisting of separate interconnected subsystems). Modeling (an information model of a security system based on ACS has been developed using a system for analyzing and recognizing potentially dangerous objects based on a real-time video stream).Mathematization (the image analysis system is described in the language of mathematical laws and formulas).Results. As a result of the research based on the analysis of modern materials, the concept of a security system based on real-time video sequence analysis with the use of advanced object scanning technologies is proposed in the future. As the main innovation, an improved Viola-Jones image analysis method is proposed using an additional set characterizing the feature space of objects in the terahertz radiation range.Conclusion. The use of high-frequency scanning technologies with intelligent object image recognition systems in real time will significantly reduce the risks of intruders entering protected facilities, as well as increase the safety of citizens with relatively low costs for the development and implementation of upgraded security systems.

Facial Feature Localization and Analysis Using Machine Learning

The facial feature localization system with machine learning (ML) is an innovative solution designed to accurately detect and locate key facial landmarks. By integrating advanced ML algorithms, the system processes images or video streams in real time to identify the positions of facial features such as the eyes, nose, mouth, and jawline. The ML component analyses the data to precisely locate these features, enabling applications in areas like facial expression analysis and biometric verification. This approach enhances accuracy by adapting to various lighting conditions, face orientations, and individual facial variations. The system’s scalability and flexibility further extend its utility, supporting diverse applications across industries like healthcare, security, and human-computer interaction. Overall, this project represents a significant advancement in facial feature localization, using IoT and ML to enable more effective and accurate facial analysis. By adapting to various lighting conditions, face orientations, and individual facial variations" to "by adapting to diverse lighting conditions, different face orientations, and individual facial variations, ensuring reliable performance in various environments.

Water Trash Detection System: An Innovative Approach to Monitoring Aquatic Pollution

Abstract: Water pollution, particularly from non-biodegradable waste such as plastics, is one of the most pressing environmental issues facing aquatic ecosystems today. This paper presents an innovative solution for detecting and classifying waste in water bodies using machine learning techniques, specifically You Only Look Once (YOLO) and Convolutional Neural Networks (CNNs). The Water Trash Detection System (WTDS) can process both static images and real-time video streams to efficiently detect various types of aquatic trash, including plastic bottles, bags, and fishing debris. The system generates detailed reports on detected waste, providing environmental organizations and researchers with actionable data for monitoring and cleaning polluted water bodies. The combination of YOLO for real-time object detection and CNNs for waste classification allows the WTDS to deliver high accuracy and real-time processing, which is essential for effective environmental management.

Facial Recognition Using Video Streaming

Facial recognition has become an essential technology in numerous applications, including security, surveillance, and human-computer interaction. With the advent of real-time video streaming, facial recognition systems are now tasked with handling the continuous flow of visual data. This paper explores the integration of facial recognition algorithms into video streaming systems, investigating the challenges, methodologies, and applications of real-time face detection and identification. We present a framework for implementing facial recognition in live video streams, assess the performance of different algorithms, and highlight areas for future improvement, including handling large datasets, optimizing computation, and ensuring privacy.