Video Flows Research Articles

Edge Cloud and Mobile Auxiliary Equipment of Fine Art Painting Course Teaching Auxiliary System Design

Due to the development of information technology, the new type of smart campus integrates teaching, scientific research, office services, and many other applications, and online education information resources show a blowout growth. Art and painting teaching courses in the cloud era also face a series of digital challenges. In view of the development of digital teaching mode, art and painting course is different from other courses and has higher requirements for the transmission of audio and video. How to transmit the audio and video generated during interactive teaching efficiently and with low latency is a challenge. In order to realize the needs of art painting course teaching, based on the characteristics of edge cloud and mobile auxiliary equipment, build the “double cloud” mode of art painting teaching auxiliary system, through the cloud edge deployed different layers and design adaptive code switching mechanism, realize the art painting teaching and remote teaching video flow, help to realize the teaching interaction between teachers and students and instant feedback, and help to improve the art painting course teaching effect.

Effects of Short Video Addiction on the Motivation and Well-Being of Chinese Vocational College Students.

While media use can be beneficial in some ways, excessive use of media has led to growing concerns about its potential negative consequences. With the popularity of Chinese video applications (apps) such as DouYin, TikTok, Kwai, and other short video apps sweeping through schools around the world. Due to the diversity and immersion principle of short videos, their popularity continues to grow, and the phenomenon of students being addicted to short videos also brings many hidden dangers to the learning effect. Among other things, the problem of excessive use of the Internet among Chinese youth has led the government to propose a series of control policies to strengthen the monitoring of harmful habits of youth in the use of online applications. In addition, the problem of youth addiction to short videos has become a major concern for education experts and the general public, thus demonstrating that short video addiction is indeed an ongoing research issue. Therefore, this study aimed to understand the causes of short-form video addiction and its impact on the psychology of learning, and to investigate the relationship between short-form video flow experience, short-form video addiction, intrinsic and extrinsic learning motivation, and learning well-being from the perspectives of flow experience theory and micro ecological systems. The questionnaire was sent via instant messaging software such as QQ and WeChat, and university students from vocational colleges in China were invited to complete the questionnaire. A total of 517 valid data were collected, including 222 (42.9%) were male students and 295 (57.1%) were female students. The collected questionnaires were analyzed for reliability and validity after removing incomplete data, followed by structural equation modeling for model verification. The findings showed that: (1) short video flow experience had a positive effect on short video addiction; (2) short video addiction had a negative effect on intrinsic and extrinsic learning motivation; (3) intrinsic and extrinsic learning motivation had a positive effect on learning well-being; (4) short video flow experience had an indirect negative effect on intrinsic and extrinsic learning motivation; (5) short video flow and short video addiction had indirect negative effects on learning well-being. According to the results, it is clear that addiction to short videos has a negative impact on learners' learning motivation and positive psychology of learning, so parents and teachers should effectively guide students to use short video apps in a self-controlled way.

QoS-Aware Scheduling Algorithm Enabling Video Services in LTE Networks

The Long-Term Evolution (LTE) system was a result of the 3rd-Generation Partnership Project (3GPP) to assure Quality-of-Service (QoS) performance pertaining to non-real-time and real-time services. An effective design with regards to resource allocation scheduling involves core challenges to realising a satisfactory service in an LTE system, particularly with the growing demand for network applications. The continuous rise in terms of the number of network users has resulted in impacts on the performance of networks, which also creates resource allocation issues when performing downlink scheduling in an LTE network. This research paper puts forward a review of optimisation pertaining packet scheduling performance through the LTE downlink system by introducing a new downlink-scheduling algorithm for serving video application through LTE culler networks, and also accounts for QoS needs and channel conditions. A comparison of the recommended algorithms’ performances was made with regards to delay, throughput, PLR, and fairness by utilising the LTE-SIM simulator for video flow. On the basis of the outcomes obtained, the algorithms recommended in this research work considerably enhance the efficacy of video streaming compared against familiar LTE algorithms.

Low Latency UHD Adaptive Video Bitrate Streaming Based on HEVC Encoder Configurations and Http2 Protocol

Applying 4K, (Ultra HD) Real-time video streaming via the internet network, with low bitrate and low latency, is the challenge this paper addresses. Compression technology and transfer links are the important elements that influence video quality. So, to deliver video over the internet or another fixed capacity medium, it is essential to compress the video to more controllable bitrates (customarily in the 1-20 Mbps range). In this study, the video quality is examined using the H.265/HEVC compression standard, and the relationship between quality of video and bitrate flow is investigated using various constant rate factors, GOP patterns, quantization parameters, RC-lookahead, and other types of video motion sequences. The ultra-high-definition video source is used, down sampled and encoded at multiple resolutions of (3480x2160), (1920x1080), (1280x720), (704x576), (352x288), and (176x144). To determine the best H265 feature configuration for each resolution experiments were conducted that resulted in a PSNR of 36 dB at the specified bitrate. The resolution is selected by delivery (encoder resource) based on the end-user application. While video streaming adapted to the available bandwidth is achieved via embedding a controller with MPEG DASH protocol at the client-side. Video streaming Adaptation methods allow the delivery of content that is encoded at different representations of video quality and bitrate and then dividing each representation into chunks of time. Through this paper, we propose to utilize HTTP/2 as a protocol to achieve low latency video streaming focusing on live streaming video avoiding the problem of HTTP/1.

Intersubject synchrony of viewers during naturalistic observational self-learning of a complex bimanual task

Watching an instructional video has become a common way to learn a new task. However, we have but a sparse understanding of the neural processes involved during observational learning in naturalistic settings. Recently developed data driven methods for analyzing brain activity provide an opportunity for further investigation. Here, we evaluate intersubject synchrony during fMRI to understand common brain processes during naturalistic observational learning. Participants solitarily watched an instructional video and learned how to fold a paper figure. Three learning runs were sufficient to successfully solve the task. To assess interbrain synchrony, we extended previous principal component (PCA)-based methods to an intersubject principal component analysis (PCA), which offers multiple measures for additional insights into the nature of the synchrony. Using the different metrics of this method, we show a robust synchronous involvement of the action observation execution network (AOEN) in observational learning, between subjects as well as within subjects, regardless of the task or video content. Importantly, additional areas such as the cerebellum, primary motor cortex, control, and sensory integration areas also showed robust synchrony in observational learning. Complimentary to this robust general synchrony, individual regions of the AOEN exhibited task-related differences. Synchrony decreased during the learning process, likely reflecting task state and individual learning strategies. To test the stimulus as a possible source of synchrony, we quantified the temporal structure as the optic flow of the instructional video. Optic flow was strongly related to common activation of the somatomotor areas of the AOEN well beyond visual areas, but could not completely explain synchrony. Thus, although visual motion provides a proxy for meaningful hand actions, our results suggest that intersubject synchrony reflects common cognitive processing during observational learning beyond sensory input.

A deep learning framework for real-time 3D model registration in robot-assisted laparoscopic surgery.

IntroductionThe current study presents a deep learning framework to determine, in real‐time, position and rotation of a target organ from an endoscopic video. These inferred data are used to overlay the 3D model of patient's organ over its real counterpart. The resulting augmented video flow is streamed back to the surgeon as a support during laparoscopic robot‐assisted procedures.MethodsThis framework exploits semantic segmentation and, thereafter, two techniques, based on Convolutional Neural Networks and motion analysis, were used to infer the rotation.ResultsThe segmentation shows optimal accuracies, with a mean IoU score greater than 80% in all tests. Different performance levels are obtained for rotation, depending on the surgical procedure.DiscussionEven if the presented methodology has various degrees of precision depending on the testing scenario, this work sets the first step for the adoption of deep learning and augmented reality to generalise the automatic registration process.

Experimental heat transfer results and flow visualization of vertical upflow boiling in Earth gravity with subcooled inlet conditions – In preparation for experiments onboard the International Space Station

Since 2012, researchers at the Purdue University Boiling and Two-Phase Flow Laboratory (PU-BTPFL) and NASA Glenn Research Center have been collaborating on a long-term effort to study flow boiling and condensation in microgravity. The ultimate goal has been to develop the Flow Boiling and Condensation Experiment (FBCE) for the International Space Station (ISS). Based on the findings from prior flow boiling experiments both at different orientations in Earth gravity and onboard parabolic flights simulating short durations of microgravity, a final refined experiment design, construction, and operating procedure have been arrived at for long-duration microgravity flow boiling experiments onboard the ISS. This study investigates flow boiling of n-Perfluorohexane with subcooled inlet in a rectangular channel of dimensions 114.6 mm heated length, 2.5 mm width, and 5 mm height. These pre-launch experiments (Mission Sequence Testing) were conducted in vertical upflow orientation in Earth gravity using the same experimental rig that was launched to the ISS in August 2021. The various operating parameters varied are heating configuration (single- and double-sided), mass velocity (180 – 3200 kg/m2s), inlet subcooling (+0 – 32 °C, encompassing both highly subcooled and near-saturated inlet conditions), and inlet pressure (119 – 191 kPa). High-speed video flow visualization images are presented to explain the two-phase interfacial physics within the channel's heated section. Heat transfer results in terms of flow boiling curves, streamwise profiles of wall temperature and heat transfer coefficient, and averaged heat transfer coefficients are analyzed and parametric effects elucidated. Severe temporal thermodynamic equilibrium is observed for near-saturated inlet at very low velocities. Nucleate boiling degradation starts at larger heat fluxes for single-sided heating than double- sided at low mass velocities with highly subcooled inlet, and conversely at high mass velocities with near-saturated inlet. Nucleate boiling degradation can be delayed to higher heat fluxes by highly subcooling the inlet and increasing mass velocity. The entire local heat transfer coefficient profiles are degraded at higher heat fluxes for near-saturated inlet, but only the downstream part for highly subcooled inlet. This study also confirmed reliability of the upcoming ISS experimental data for subcooled inlet conditions and the collected Earth-gravity data will be used for comparison against the ISS data.

Research on Real-time Monitoring of Video Images of Traffic Vehicles and Pedestrian Flow using Intelligent Algorithms

The development of urbanization has brought many traffic problems, among which the delayed feedback of traffic flow and people flow has led to traffic congestion. In order to effectively analyze the traffic flow and people flow on the traffic road, this research proposes a traffic surveillance video image object detection model based on the improved Vibe algorithm, and uses the moving historical image to track the traffic flow and people flow. Finally, the performance analysis of the algorithm shows that the loss rate of the improved Vibe algorithm proposed in the study is only 0.25%, and its detection accuracy reaches 91.25%. The above results show that the use of Vibe intelligent algorithm can significantly improve the detection effect of traffic flow and pedestrian flow in traffic monitoring video, help to improve urban traffic management ability and promote the development of urban modernization.

Swarm-Based and Energy-Aware Unmanned Aerial Vehicle System for Video Delivery of Mobile Objects

Floods are the most common disaster in the world and cause deaths, damages to houses, buildings, and possessions, as well as disruption to communications. In such dynamic scenarios, it is needed to search and track mobile objects transported by the water flows, such as humans, animals, vehicles, and debris. The use of Unmanned Aerial Vehicles (UAVs) is essential in disaster scenarios to help first responders determine correct procedures in terms of searching, tracking, and rescuing the victims, as well as in defining the actions to minimize the risks in a sustainable and timely manner. However, the tracking of mobile objects and the delivery of real-time video sequences from UAVs with energy constraints toward first responders is still a hard task. Therefore, it is necessary to orchestrate a swarm of UAVs for searching and tracking objects while reacting fast to frequent changes in the topology and trajectory, as well as distributing real-time video flows with quality level support to the ground team. This article proposes an energy-aware swarm-based and mobility prediction scheme for UAVs, called SUAV. SUAV provides a unique UAV-based system for rescue scenarios with mobile objects and with support for route and path planning, searching and tracking procedures, mobility prediction and multi-hop communication management, video delivery with Quality of Service (QoS)/Quality of Experience (QoE) support, and energy-efficiency. Simulation results show the efficiency of SUAV in transmitting real-time video flows with QoS/QoE support while minimizing the energy consumption in flooding scenarios with mobile targets.

Investigation of the Flow-Based Fast Reroute Model with Implementation of a Multimedia Quality Protection Scheme

Abstract In this paper, a tensor flow-based fast reroute model with multimedia quality protection is proposed. In the model, the conditions for implementing a multipath routing strategy and flow conservation are introduced taking into account possible packet loss at the network nodes and preventing overloading communication links both when using the primary and backup routes. At the same time, the novelty of the proposed solution is the formalization of the conditions of protection of the Quality of Experience level in terms of multimedia quality along the primary and backup routes. These conditions have been obtained during the tensor formalization of the network, which made it possible to calculate the quality of service indicators: packet loss probabilities, as well as the average end-to-end delay for audio and video flows transmitted in the multimedia session using the primary and backup routes, respectively. As a criterion for the optimality of the obtained solutions, a condition has been selected related to maximizing the overall performance of the infocommunication network. The results of the research of the proposed model confirm the adequacy of the numerical research results obtained for solving the problem of fast rerouting with link/node protection.

Online Video Popularity Regression Prediction Model with Multichannel Dynamic Scheduling Based on User Behavior

Popularity prediction of online video is widely used in many different scenarios. It can not only help video service providers to schedule video web sites, but also bring considerable profits on investment for both providers and advertisers if popularity of online video is predicted accurately. However, online video popularity prediction still cannot have a satisfactory result, due to the complexity of many crucial factors especially of video distribution network. In this article, we extract seven factors from huge amounts of data about user behavior, establishing a new multiple linear regression model to initially predict online video popularity. After that, a multichannel video popularity dynamic scheduling model is proposed to schedule videos on which channel and what time to be broadcast, according to its popularity predicted by multiple linear regression model, ensuring that maximum the sum value of online video popularity of each channel. Experimental results on dataset obtained from Sohu Video, a video service provider in China, and real-world video flow in Sohu Video demonstrate that the proposed model is robust and has promising performance in predicting online video popularity, which is helpful for video service providers to schedule videos on web sites effectively in the future.

On Improving the Robustness of MEC with Big Data Analysis for Mobile Video Communication

Mobile video communication and Internet of Things are playing a more and more important role in our daily life. Mobile Edge Computing (MEC), as the essential network architecture for the Internet, can significantly improve the quality of video streaming applications. The mobile devices transferring video flow are often exposed to hostile environment, where they would be damaged by different attackers. Accordingly, Mobile Edge Computing Network is often vulnerable under disruptions, against either natural disasters or human intentional attacks. Therefore, research on secure hub location in MEC, which could obviously enhance the robustness of the network, is highly invaluable. At present, most of the attacks encountered by edge nodes in MEC in the IoT are random attacks or random failures. According to network science, scale-free networks are more robust than the other types of network under the random failures. In this paper, an optimization algorithm is proposed to reorganize the structure of the network according to the amount of information transmitted between edge nodes. BA networks are more robust under random attacks, while WS networks behave better under human intentional attacks. Therefore, we change the structure of the network accordingly, when the attack type is different. Besides, in the MEC networks for mobile video communication, the capacity of each device and the size of the video data influence the structure significantly. The algorithm sufficiently takes the capability of edge nodes and the amount of the information between them into consideration. In robustness test, we set the number of network nodes to be 200 and 500 and increase the attack scale from 0% to 100% to observe the behaviours of the size of the giant component and the robustness calculated for each attack method. Evaluation results show that the proposed algorithm can significantly improve the robustness of the MEC networks and has good potential to be applied in real-world MEC systems.

Unveiling the End-User Viewport Resolution From Encrypted Video Traces

Video streaming is without doubt the most requested Internet service, and main source of pressure on the Internet infrastructure. At the same time, users are no longer satisfied by the Internet’s best effort service, instead, they expect a seamless service of high quality from the side of the network. As result, Internet Service Providers (ISP) engineer their traffic so as to improve their end-users’ experience and avoid economic losses. Content providers from their side, and to enforce customers privacy, have shifted towards end-to-end encryption (e.g., TLS/SSL). Video streaming relies on the dynamic adaptive streaming over HTTP protocol (DASH) which takes into consideration the underlying network conditions (e.g., delay, loss rate, and throughput) and the viewport capacity (e.g., screen resolution) to improve the experience of the end user in the limit of the available network resources. In this work, we propose an experimental framework able to infer fine-grained video flow information such as chunk sizes from encrypted YouTube video traces. We also present a novel technique to separate video and audio chunks from encrypted traces based on Gaussian Mixture Models (GMM). Then, we leverage our dataset to train models able to predict the class of viewport (either <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SD</i> or <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">HD</i> ) per video session with an average 92% accuracy and 85% F1-score. The prediction of the exact viewport resolution is also possible but shows a lower accuracy than the viewport class.

Experimental investigation of gas-liquid flow in a vertical venturi installed downstream of a horizontal blind tee flow conditioner and the flow regime transition

A venturi device is commonly used as an integral part of a multiphase flowmeter (MPFM) in real-time oil-gas production monitoring. Partial flow mixing is required by installing the venturi device vertically downstream of a blind tee pipework that conditions the incoming horizontal gas-liquid flow (for an accurate determination of individual phase fraction and flow rate). To study the flow-mixing effect of the blind tee, high-speed video flow visualization of gas-liquid flows has been performed at blind tee and venturi sections by using a purpose-built transparent test rig over a wide range of superficial liquid velocities (0.3–2.4 m/s) and gas volume fractions (10–95%). There is little ‘homogenization’ effect of the blind tee on the incoming intermittent horizontal flow regimes across the tested flow conditions, with the flow remaining intermittent but becoming more axis-symmetric and predictable in the venturi measurement section. A horizontal (blind tee) to vertical (venturi) flow-pattern transition map is proposed based on gas and liquid mass fluxes (weighted by the Baker parameters). Flow patterns can be identified from the mean and variance of a fast electrical capacitance holdup measured at the venturi throat.

Scheduling Inter-Datacenter Video Flows for Cost Efficiency

As video streaming applications are deployed on the cloud, cloud providers are charged by ISPs for inter-datacenter transfers under the dominant percentile-based charging models. In order to minimize the payment costs, existing works aim to keep the traffic on each link under the charging volume. However, these methods cannot fully utilize each link's available bandwidth capacity. As a solution, we propose an economical and deadline-driven video flow scheduling system, called EcoFlow. Considering that different video flows have different transmission deadlines, EcoFlow transmits videos in the order of their deadline tightness and postpones the deliveries of later-deadline videos to later time slots. The flows that are expected to miss their deadlines are divided into subflows to be rerouted to other under-utilized links. We also propose setting each link's initial charging volume to reduce the scheduling latency at the beginning of the charging period and discuss how to deal with issues such as the prediction errors of link available bandwidth and the lack of charging volume's prior knowledge. Furthermore, we designed implementation strategies for using EcoFlow in both centralized and distributed situations. Experimental results demonstrate that EcoFlow achieves lower bandwidth costs and higher video flow transmission rates when compared to existing methods.

EVeREst: Bitrate Adaptation for Cloud VR

Cloud Virtual Reality (VR) technology is expected to promote VR by providing a higher Quality of Experience (QoE) and energy efficiency at lower prices for the consumer. In cloud VR, the virtual environment is rendered on the remote server and transmitted to the headset as a video stream. To guarantee real-time experience, networks need to transfer huge amounts of data with much stricter delays than imposed by the state-of-the-art live video streaming applications. To reduce the burden imposed on the networks, cloud VR applications shall adequately react to the changing network conditions, including the wireless channel fluctuations and highly variable user activity. For that, they need to adjust the quality of the video stream adaptively. This paper studies video quality adaptation for cloud VR and improves the QoE for cloud VR users. It develops a distributed, i.e., with no assistance from the network, bitrate adaptation algorithm for cloud VR, called the Enhanced VR bitrate Estimator (EVeREst). The algorithm aims to optimize the average bitrate of cloud VR video flows subject to video frame delay and loss constraints. For that, the algorithm estimates both the current network load and the delay experienced by separate frames. It anticipates the changes in the users’ activity and limits the bitrate accordingly, which helps prevent excess interruptions of the playback. With simulations, the paper shows that the developed algorithm significantly improves the QoE for the end-users compared to the state-of-the-art adaptation algorithms developed for MPEG DASH live streaming, e.g., BOLA. Unlike these algorithms, the developed algorithm satisfies the frame loss requirements of multiple VR sessions and increases the network goodput by up to 10 times.

Quality of Service- and Fairness-Aware Resource Allocation Techniques for IEEE802.11ac WLAN

Increased demand for high-quality multimedia applications over IEEE802.11 networks has further motivated service providers to improve the QoS (quality of service) for all types of network services. IEEE802.11ac is one of the advanced WLAN standards that provides wideband transmission channels and higher data rates, which are vital to support very high-throughput services. However, due to the use of the CSMA/CA-based random access packet transmission technique, the QoS and service fairness criteria cannot always be maintained, particularly for variable bit rate services. This paper proposes new packet scheduling algorithms to support consistently high QoS and intra-service fairness for high data rate video streams. We name the proposed algorithms FRA - TXOP (Flow Rate Adaptive Transmission Opportunity) and EAS (Enhanced Access Scheduler). These algorithms offer appropriate QoS and fairness to video services in a CSMA/CA network. The FRA - TXOP algorithm allocates the transmission resources according to the channel congestion levels experienced by video flows to improve and maintain consistent QoS values. At the same time, the EAS algorithm offers service fairness among the video streams by appropriately scheduling them on the downlink channel. The EAS algorithm is implemented on top of the FRA - TXOP algorithm to achieve high QoS and service fairness among video streams. An NS-3 simulation model is developed to evaluate the performance of the proposed algorithms. The performance analysis shows that the proposed algorithms enhance the video flow QoS in terms of throughput and packet delay as well as improve the fairness among the video flows compared to other TXOP algorithms.

Electric Shovel Teeth Missing Detection Method Based on Deep Learning.

Electric shovels are widely used in the mining industry to dig ore, and the teeth in shovels' bucket can be lost due to the tremendous pressure exerted by ore materials during operation. When the teeth fall off and enter the crusher with other ore materials, serious damages to crusher gears and other equipment happen, which causes millions of economic loss, because it is made of high-manganese steel. Thus, it is urgent to develop an efficient and automatic algorithm for detecting broken teeth. However, existing methods for detecting broken teeth have little effect and most research studies depended on sensor skills, which will be disturbed by closed cavity in shovel and not stable in practice. In this paper, we present an intelligent computer vision system for monitoring teeth condition and detecting missing teeth. Since the pixel-level algorithm is carried out, the amount of calculation should be reduced to improve the superiority of the algorithm. To release computational pressure of subsequent work, salient detection based on deep learning is proposed for extracting the key frame images from video flow taken by the camera installed on the shovel including the teeth we intend to analyze. Additionally, in order to more efficiently monitor teeth condition and detect missing teeth, semantic segmentation based on deep learning is processed to get the relative position of the teeth in the image. Once semantic segmentation is done, floating images containing the shape of teeth are obtained. Then, to detect missing teeth effectively, image registration is proposed. Finally, the result of image registration shows whether teeth are missing or not, and the system will immediately alert staff to check the shovel when teeth fall off. Through sufficient experiments, statistical result had demonstrated superiority of our presented model that serves more promising prospect in mining industry.

YouTube as an information source for instrument separation in root canal treatment.

ObjectivesThe reliability and educational quality of videos on YouTube for patients seeking information regarding instrument separation in root canal treatment were evaluated.Materials and MethodsYouTube was searched for videos on instrument separation in root canal treatment. Video content was scored based on reliability in terms of 3 categories (etiology, procedure, and prognosis) and based on video flow, quality, and educational usefulness using the Global Quality Score (GQS). Descriptive statistics were obtained and the data were analyzed using analysis of variance and the Kruskal-Wallis test.ResultsThe highest mean completeness scores were obtained for videos published by dentists or specialists (1.48 ± 1.06). There was no statistically significant difference among sources of upload in terms of content completeness. The highest mean GQS was found for videos published by dentists or specialists (1.82 ± 0.96), although there was no statistically significant correlation between GQS and the source of upload.ConclusionsVideos on YouTube have incomplete and low-quality content for patients who are concerned about instrument separation during endodontic treatment, or who experience this complication during endodontic treatment.

SDN Based in-Network Two-Staged Video QoE Estimation With Measurement Error Correction for Edge Network

Network resource management is one of the key technologies needed to ensure that multiple applications in edge networks provide reliable and stable performance. Although throughput has previously been seen as the primary network performance metric, recent applications do not focus on throughput alone. Instead, Quality of Experience (QoE) is attracting significant attention as an indicator of network resource management performance because it allows a wide variety of applications to be compared within a single metric. In this study, we tackle QoE measurements for a video streaming service as a way to evaluate QoE-based network management. However, there are several problems related to measuring QoE. For example, in-network components are difficult to measure because QoE is normally measured at end-points, and several properties that are deeply related to application settings are required for those calculations. Additionally, the measurements set forth in the International Telecommunication Union’s ITU-T G.1071 standard require a certain duration, which is too long for network resource management evaluations. Therefore, this paper proposes a two-staged in-network QoE estimation method for video flows that can resolve these issues. In the first stage, we focus on producing a fast and rough QoE estimate to start forwarding the arriving flow onto an appropriate route as soon as possible. Next, the second stage is designed to produce precise QoE estimations based on careful long-duration measurements. In both stages, the proposed method uses a parameter estimation process that converts in-network information to end-point information for QoE calculations by following ITU-T G. 1071 and corrects measurement errors reducing QoE calculation errors to the greatest extent possible. Through experimental evaluations, we then demonstrate that the QoEs of all flows can be maximized by selecting appropriate routes based on the predicted QoE at the first stage, and that the accuracy of the QoE estimation at the second stage can be improved in real-time even when packet losses occur.