HDTV Research Articles

Real-Time Video Recognition via Decoder-Assisted Neural Network Acceleration Framework

Due to the restricted on-chip computing capability for deep neural network (DNN) processing, high-definition video recognition (VOR) task is not easily achievable as a real-time task in a consumer SoC. Despite the fact that many accelerators have been proposed for fast VOR, they remain isolated from a video decoder’s inherent video compression knowledge. Therefore, in this paper, we propose a video decoder-assisted neural network acceleration framework for real-time video recognition. Firstly, given the fact that the non-key frames can be dynamically reconstructed by the key frames with high fidelity during video compression, we propose the VR-DANN algorithm that reconstructs the VOR results of non-key frames in a similar way so as to save a large amount of NN computing power. In VR-DANN, we leverage motion vectors, the tempo-spatial information already available in the video decoding process to facilitate the recognition process, and propose a lightweight NN-based refinement scheme to suppress the non-pixel recognition noise. Moreover, we consider that there is numerous redundant information in the video frames because the objects of interest usually take a small portion in a video frame. We, therefore, propose the object based acceleration algorithm (Jigsaw-VOR) to avoid unnecessary computation by dropping out the redundant information in the frames before going through the computing-intensive DNN process. Concretely, we adopt the motion vectors to track the rough position for the objects of interest and then merge them into a consolidated frame for DNN processing like a jigsaw game. The acceleration comes from the processing of much fewer consolidated frames compared to the raw frames in a video stream. The VR-DANN and Jigsaw-VOR can be integrated for further speedup. From the hardware side, we propose the VR-DANN and Jigsaw-VOR architectures to respectively accelerate the VR-DANN and Jigsaw-VOR algorithms. These two architectures can be combined to gain higher performance improvement. Our experimental results show that the VR-DANN architecture achieves 2.9× performance improvement with less than 1% accuracy loss compared with the state-of-the-art “FAVOS” scheme. In addition, the experimental results show that applying Jigsaw-VOR to all frames can achieve 2.4× performance improvement with comparable accuracy compared to “FAVOS”. By combining VR-DANN and Jigsaw-VOR schemes, the performance improvement can reach up to 3.6×.

Video saliency-detection using custom spatiotemporal fusion method

There have been several researches done in the field of image saliency but not as much as in video saliency. In order to increase precision and accuracy during compression, reduce coding complexity and time consumption along with memory allocation problems with our proposed solution. It is a modified high-definition video compression (HEVC) pixel based consistent spatiotemporal diffusion with temporal uniformity. It involves taking apart the video into groups of frames, computing colour saliency, integrate temporal fusion, pixel saliency fusion is conducted and then colour information guides the diffusion process for the spatiotemporal mapping with the help of permutation matrix. The proposed solution is tested on a publicly available extensive dataset with five global saliency valuation metrics and is compared with several other state-of-the-art saliency detection methods. The results display and overall best performance amongst all other candidates.

Smart all-time vision: The battery-free video communication for urban administration and law enforcement

The Chinese government is dedicated to enhancing the level of informatization in administrative law enforcement to ensure fairness and increase credibility. Currently, law enforcement has exposed such problems as insufficient force, difficulties in collecting evidence, and low evidential power. These problems contradict the principles of rule of law and standardization. Many local governments have implemented advanced information technologies for urban administration and law enforcement, including big data, artificial intelligence, and IoT. Among these technologies, IoT is the core communication infrastructure for innovative law enforcement platforms. However, traditional video communications rely on batteries or dedicated power sources, leading to maintenance challenges and high power consumption. In this paper, we propose AT-Eye, a new video communication paradigm for all-time law enforcement video monitoring, which is battery-free and high-throughput. The key enabler of AT-Eye is ambient backscatter technology, which enables energy harvesting and video communication simultaneously. Unlike previous methods, our proposal introduces a novel CCK-based modulation for tag cameras and achieves 4-way concurrency. The modulation is simple because it uses phase difference and it is energy-efficient because generating square waves is adequate. Moreover, to ensure full compatibility with COTS WiFi, we modulate the physical service data unit. Therefore, data recovery is possible using only commercial NICs. We conduct comprehensive experiments to examine our proposal and experiment results show that AT-Eye achieves a throughput of 10.8 Mbps with COTS radios. We also simulate a 16-way battery-free tag camera system, demonstrating AT-Eye's feasibility of high-definition video communication.

8K Ultra HD TV broadcast system: challenge, architecture and implementation

The size of the audio and video (AV) content of the 8K program is four times larger than that of 4K content, providing viewers with a more ideal audiovisual experience while placing higher demands on the capability and efficiency of document preparation and processing, signal transmission, and scheduling. However, it is difficult to meet the high robustness requirements of 8K broadcast services because the existing broadcast system architecture is limited by efficiency, cost, and other factors. In this study, an 8K Ultra-High-Definition (UHD) TV program broadcast scheme was designed. The verification results show that the scheme is high quality, highly efficient, and robust. In particular, in the research, the file format normalizing module was first placed in the broadcast area instead of the file preparation area, and the low-compression transmission scheme of the all-IP signal JPEG XS was designed in the signal transmission area for improving the efficiency of the scheme. Next, to reduce the impact on the robustness of broadcast services, the broadcast control logic of the broadcast core components is optimized. Finally, a series of 8K TV program broadcasting systems have been implemented and their performance has been verified. The results show that the system meets the efficiency and robustness requirements of a high-quality 8K AV broadcast system, and thus has a high degree of practicability.

The Prospect of drone applications

As drones technology matures, it will be used in more and more applications in multiple fields. This paper focuses on the evaluation of the prospects for the application of drones. The evaluation is based on three criteria: the environment, engineering, and disaster management. Through analysis, this paper shows that drones have unique advantages in these three areas. Given the use of ground-based sensors for air and water quality testing, drones have a great positive effect on environmental management. It can also be used for large-scale engineering project management and disaster tracking with its HD video and numerous high-resolution aerial photos. However, drones need improved regulatory controls to address risks to safety, privacy, and security. Overall, this article describes the status of drone applications, which will become more popular with the enhancement of the regulatory environment.

Vacuum-deposited Rb3CeI6 for deep-blue-light-emitting diodes.

Recently, perovskite light-emitting diodes (PeLEDs) have exhibited outstanding performance in next-generation high-definition display applications. However, compared with green and red PeLEDs, the development of efficient and stable blue PeLEDs to meet the requirement for a wide color gamut has been a challenge. Herein, we vacuum thermally deposited a film of the lead-free rare earth halide Rb3CeI6, which shows deep blue emission with peaks at 427 nm and 468 nm. Due to the parity-allowed 5d-4f transition of Ce(III), the excited-state lifetime is as short as 22.3 ns (427 nm) and 25 ns (468 nm), respectively. The photoluminescence quantum yield (PLQY) is optimized to 51% by regulating the nucleation and growth of Rb3CeI6 grains. In a prototype rare earth light-emitting diode (ReLED) device, a thin insulating Al2O3 layer (5 nm) is inserted between the electron transport layer (ETL) and the emitting layer (EML, Rb3CeI6) to balance the carriers and reduce the dark current. The device shows a maximum luminance and EQE of 98 cd m-2 and 0.67%, respectively, and the electroluminescence (EL) spectrum maintains stability with changes in the operating voltage. In addition, the corresponding CIE coordinate is (0.15, 0.06), which closely matches the Rec. 2020 standard (0.131, 0.046).

Integration of Raspberry Pi and antennas for multiplexing digital signals over a fiber optical communication system

A Fiber Optical Communication System (FOCS) is used to experimentally demonstrate the transmission of multi-channel information of two High Definition (HD) video signals and 18 digital TV channels. These signals are supplied using commercial Raspberry Pi boards and digital TV Antennas, respectively. Both digital signals and lightwaves of a couple of Distributed Feedback (DFB) lasers with wavelengths located at 1547.5 and 1552.5 nm interact with two Mach-Zehnder Intensity Modulators (MZ-IM). The resulting modulated optical signals from each modulator are combined by using an optical coupler. The combined optical field is amplified and transmitted through 30 km of single-mode optical fiber. To demultiplex the combined optical signals, a bandpass optical filter is used, then a PIN-photodetector is connected to recover HD video signals and the 18 digital TV channels. The measured electrical spectrum of the received signals shows that the transmission is performed without interference and the multi-channel information is successfully received in an HD display. The use of wavelengths with linewidths of 10 MHz and an optical fiber with a chromatic dispersion of 17 ps/nm-km allows for a maximum bit rate of approximately 11 Gbps to be achieved numerically. This result guarantees that HD video signals can be experimentally transmitted successfully with Bit Error Rate (BER) values between 10-6 and 10-15 when the optical power of lasers is tuned between 7 and 9 dBm.

Visual Perception Based Intra Coding Algorithm for H.266/VVC

The latest international video coding standard, H.266/Versatile Video Coding (VVC), supports high-definition videos, with resolutions from 4 K to 8 K or even larger. It offers a higher compression ratio than its predecessor, H.265/High Efficiency Video Coding (HEVC). In addition to the quadtree partition structure of H.265/HEVC, the nested multi-type tree (MTT) structure of H.266/VVC provides more diverse splits through binary and ternary trees. It also includes many new coding tools, which tremendously increases the encoding complexity. This paper proposes a fast intra coding algorithm for H.266/VVC based on visual perception analysis. The algorithm applies the factor of average background luminance for just-noticeable-distortion to identify the visually distinguishable (VD) pixels within a coding unit (CU). We propose calculating the variances of the numbers of VD pixels in various MTT splits of a CU. Intra sub-partitions and matrix weighted intra prediction are turned off conditionally based on the variance of the four variances for MTT splits and a thresholding criterion. The fast horizontal/vertical splitting decisions for binary and ternary trees are proposed by utilizing random forest classifiers of machine learning techniques, which use the information of VD pixels and the quantization parameter. Experimental results show that the proposed algorithm achieves around 47.26% encoding time reduction with a Bjøntegaard Delta Bitrate (BDBR) of 1.535% on average under the All Intra configuration. Overall, this algorithm can significantly speed up H.266/VVC intra coding and outperform previous studies.

Streaming From the Air : Enabling Drone-Sourced Video Streaming Applications on 5G Open-RAN Architectures

Enabling high data-rate uplink cellular connectivity for drones is a challenging problem, since a flying drone has a higher likelihood of having line-of-sight propagation to base stations that terrestrial UEs normally do not have line-of-sight to. This may result in uplink inter-cell interference and uplink performance degradation for the neighboring ground UEs when drones transmit at high data-rates (e.g., video streaming). We address this problem from a cellular operator's standpoint to support drone-sourced video streaming of a point of interest. We propose a low-complexity, closed-loop control system for Open-RAN architectures that jointly optimizes the drone's location in space and its transmission directionality to support video streaming and minimize its uplink interference impact on the network. We prototype and experimentally evaluate the proposed control system on a dedicated outdoor multi-cell RAN testbed, which is the first measurement campaign of its kind. Furthermore, we perform a large-scale simulation assessment of the proposed control system using the actual cell deployment topologies and cell load profiles of a major US cellular carrier. The proposed Open-RAN control scheme achieves an average 19% network capacity gain over traditional BS-constrained control solutions and satisfies the application data-rate requirements of the drone (e.g., to stream an HD video).

A Highly Pipelined and Highly Parallel VLSI Architecture of CABAC Encoder for UHDTV Applications.

Recently, specifically designed video codecs have been preferred due to the expansion of video data in Internet of Things (IoT) devices. Context Adaptive Binary Arithmetic Coding (CABAC) is the entropy coding module widely used in recent video coding standards such as HEVC/H.265 and VVC/H.266. CABAC is a well known throughput bottleneck due to its strong data dependencies. Because the required context model of the current bin often depends on the results of the previous bin, the context model cannot be prefetched early enough and then results in pipeline stalls. To solve this problem, we propose a prediction-based context model prefetching strategy, effectively eliminating the clock consumption of the contextual model for accessing data in memory. Moreover, we offer multi-result context model update (MCMU) to reduce the critical path delay of context model updates in multi-bin/clock architecture. Furthermore, we apply pre-range update and pre-renormalize techniques to reduce the multiplex BAE's route delay due to the incomplete reliance on the encoding process. Moreover, to further speed up the processing, we propose to process four regular and several bypass bins in parallel with a variable bypass bin incorporation (VBBI) technique. Finally, a quad-loop cache is developed to improve the compatibility of data interactions between the entropy encoder and other video encoder modules. As a result, the pipeline architecture based on the context model prefetching strategy can remove up to 45.66% of the coding time due to stalls of the regular bin, and the parallel architecture can also save 29.25% of the coding time due to model update on average under the condition that the Quantization Parameter (QP) is equal to 22. At the same time, the throughput of our proposed parallel architecture can reach 2191 Mbin/s, which is sufficient to meet the requirements of 8 K Ultra High Definition Television (UHDTV). Additionally, the hardware efficiency (Mbins/s per k gates) of the proposed architecture is higher than that of existing advanced pipeline and parallel architectures.

A long distance telesurgical demonstration on robotic surgery phantoms over 5G.

Using robotic technology and communications infrastructure to remotely perform surgery has been a persistent goal in medical research in the past three decades. The recent deployment of the Fifth-Generation Wireless Networks has revitalized the research efforts in the telesurgery paradigm. Offering low latency and high bandwidth communication, they are well suited for applications that require real-time data transmission and can allow smoother communication between surgeon and patient, making it possible to remotely perform complex surgeries. In this paper, we investigate the effects of the 5G network on surgical performance during a telesurgical demonstration where the surgeon and the robot are separated by nearly 300km. The surgeon performed surgical exercises on a robotic surgery training phantom using a novel telesurgical platform. The master controllers were connected to the local site on a 5G network, teleoperating the robot remotely in a hospital. A video feed of the remote site was also streamed. The surgeon performed various tasks on the phantom such as cutting, dissection, pick-and-place and ring tower transfer. To assess the usefulness, usability and image quality of the system, the surgeon was subsequently interviewed using three structured questionnaires. All tasks were completed successfully. The low latency and high bandwidth of the network resulted into a latency of 18 ms for the motion commands while the video delay was about 350 ms. This enabled the surgeon to operate smoothly with a high-definition video from about 300km away. The surgeon viewed the system's usability in a neutral to positive way while the video image was rated as of good quality. 5G networks provide significant advancement in the field of telecommunications, offering faster speeds and lower latency than previous generations of wireless technology. They can serve as an enabling technology for telesurgery and further advance its application and adoption.

A GAN Based Soft Failure Detection and Identification Framework for Long-Haul Coherent Optical Communication Systems

The rapid progress of 5G, the internet of things (IoT), high-definition online video, and cloud computing have raised high requirements for the capacity of optical networks. To improve capacity, recent works begin to focus on the low-margin optical network. However, reduced margin may lead to soft failures caused by impairments of the physical layer, and if they are not handled in time, link disruptions may be induced. Consequently, an effective soft failure management system is of great significance. To build such a system, machine learning (ML) techniques have been studied and used. However, for the training of ML, massive labeled soft failure samples are needed, which are rare in practical systems. As a result, current algorithms are highly dependent on simulation systems or laboratory environments, which may be quite different from practical systems, leading to insufficient confidence to deploy them into practical optical networks. To solve this problem, we propose a generative adversarial network (GAN) based scheme for soft failure detection and identification. For soft failure detection, only normal samples are needed for the training, and for soft failure identification, with very few soft failure samples, a high identification accuracy can be achieved. To verify the proposed framework, we conducted simulations and experiments, where the filter shift and filter tightening are studied. Both numerical simulation and experiment demonstrate the superior performance of the proposed scheme.

Clinical practice standard and specifications for wireless intelligent ultra high-definition endoscopic surgery in urology

The wireless intelligent ultra-high-definition endoscope adopts a high speed wireless image transmission chip to achieve low-latency wireless transmission, storage,annotation and analysis of high-definition images with a resolution above 4K, thereby constructing a wireless connection, wireless transmission, high-definition image display, intelligent information exchange, and image intelligent analysis endoscopic system. It has the advantages of high clarity, easy connection, small size, and high degree of intelligence, which expands the application scenarios and target population of traditional endoscopic surgery. The wireless intelligent ultra-high-definition endoscope would bring profound changes to the minimally invasive treatment of urological diseases.

Transmission quality evaluation of multistreaming video data from the UAV to the ground station in network simulator 3 simulation environment using WI-FI standards

The article presents the results of transmitting video data simulation in real time from video cameras on board Unmanned Aerial Vehicles (UAVs) to a ground station (GS). The main purpose of the article was to evaluate the impact of the flying source node number on Quality of Service (QoS) metrics, such as Packet Delivery Ratio and Goodput at OSI model application layer. A scenario was considered when hovering over UAVs, in the zone of reliable communication, transmitted a stream of video data to a ground station, then the distance between the UAV and the GS increased to repeat the experiment. The bitrate was maintained at the same level, close to the bitrate of real high-definition video. The experiment was carried out in the Network Simulator 3 (NS-3) simulation environment for scenarios with one, two, four, and eight source nodes. Simulation results have shown the negative impact of the increasing the number of flying source nodes on Quality of Service (QoS) metrics such as Packet Delivery Rate (PDR) and Goodput. Recommendations regarding the applicability of different standards of the 802.11 family to scenarios for using UAVs in the multistreaming video data transmission mode are given. A change in the relationship of useful throughput on the number of source nodes by 15 % was also found.

Bibliometric analysis of holographic data storage literature

Objectives. Snapshots of data can be stored in a holographic medium at varying depths. Data can be written via a spiral data channel in spinning holographic media in the form of circular disks like CDs or DVDs. This data is then read by shining a reference beam through the refraction following writing. However, holographic storage is distinct from CD/DVD media in the sense that information is encoded in all three dimensions. Two-dimensional data is written using a single laser beam that spirals around the material. Prototype holographic storage solutions use minuscule cones formed by individual snapshots or pages to store one million pixels. As compared with magnetic disks and tapes, which have a finite lifespan of 50 years at most, the longevity and dependability of optical media storage is advantageous for long-term archiving. Holographic technology allows for the portability of data-intensive media such as broadcast or high-definition video. However, the shelf life of holographic media remains low due to its sensitivity to light. The primary goals of most storage devices are more storage space and faster data transport. Holographic storage devices have the potential to outperform traditional optical storage devices both in terms of capacity and performance. The present paper aims to evaluate the current international research trends in Holographic Data Storage (HDS) and produce a graphical mapping of co-authorship and countries.Methods. The major outputs of the dataset were authors, document type, publication, institution, nation, and citations. After exporting 1052 data sources, HistCite software was used to analyze the citations; visualization mapping was carried out using VOSviewer software and R programming language for the analysis of the authorcountry-title association on Holographic Storage Devices.Results. The most prominent authors, papers, journals, organizations, and nations in the field of HDS were identified in HistCite. Then, four clusters were investigated using VOSviewer based on author keywords, citation collaboration networks among different organizations, countries, and the HDS co-authorship network.Conclusions. During the study period from 2000–2020 (21 years), 4636 authors contributed to 1052 publications. The highest number of publications was in 2009, with a linear adjustment of R2 = 0.0136. The most prolific author, Lee J., published 3.14% of the articles on this subject. In terms of country distribution, Japan took first-place ranking, claiming 16.54% of the total number of articles. The “holographic” keyword was used in 62.55% of the articles.

Time distancing to avoid network microbursts from drones’ high-definition video streams

Maintenance of social infrastructure, such as utility poles and bridges, is a major challenge in the era of declining labor force. While remote maintenance with drones is expected to solve this problem, it requires high-quality images for error-free decisions by a remote maintainer and low-latency to prevent many retries of remote operations since they directly affect maintenance efficiency. For that purpose, low-compression video with low encoding delay and small distortion is a leading candidate. However, we found that such traffic with high-burstiness causes a microburst, which is a short-time congestion experienced at the aggregation point even though the network capacity seems to be sufficient. We also propose a congestion avoidance method by designating appropriate timing to the encoders without losing image quality and report latency reduction in 5G-NR simulations.

PD34-07 CAN CONVOLUTIONAL NEURAL NETWORK BE APPLIED TO THE PREDICTION OF URINARY STONE COMPOSITION IN SINGLE-USE FLEXIBLE URETEROSCOPIC IMAGES?

You have accessJournal of UrologyCME1 Apr 2023PD34-07 CAN CONVOLUTIONAL NEURAL NETWORK BE APPLIED TO THE PREDICTION OF URINARY STONE COMPOSITION IN SINGLE-USE FLEXIBLE URETEROSCOPIC IMAGES? Kyung Tak Oh, Dae Young Jun, Jae Young Choi, Dae Chul Jung, and Joo Yong Lee Kyung Tak OhKyung Tak Oh More articles by this author , Dae Young JunDae Young Jun More articles by this author , Jae Young ChoiJae Young Choi More articles by this author , Dae Chul JungDae Chul Jung More articles by this author , and Joo Yong LeeJoo Yong Lee More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000003327.07AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: This study investigated whether Convolutional neural network (CNN) can show decent results in predicting urinary stone composition even in single-use flexible ureterorenoscopic (fURS) images with relatively low resolution. METHODS: This study retrospectively used surgical videos of fURS performed by a single surgeon using single-use scope (LithoVue) between 2018 and 2021. Digital images of the surface of the stone before laser fragmentation were captured in the surgical full HD video clips. Cases were divided into two groups according to whether they contained any calcium oxalate (Calcium group) or not (Non-calcium group). Among total 512 cases, 207 of stone surface images were finally included. Among total images, 25 were first designated as the test set, then augmentation for Non-calcium group was performed. The train set and validation set were divided by random split in an 8 to 2 ratio. In the CNN model, Resnet-18 model was used, and only endoscopic digital images and stone classification data were input to achieve minimal supervised learning (Fig 1). RESULTS: There were 175 cases in the Calcium group, and 32 cases in the Non-calcium group. After whole training, in validation set, the total accuracy was 82.0%, and recall, specificity and precision for Calcium group was 80.0%, 83.3% and 76.2%, and for Non-calcium group, it was 83.3%, 80.0% and 86.2%, respectively. Area under ROC curve of the model, which represents the classification performance of the model, was 0.863. After training and validation, the model was tested using the test set, and the total accuracy was 84.0%. Recall, specificity and precision of the test result was 80.0%, 100.0% and 100.0% in Calcium group, and 100.0%, 80.0% and 55.6% in Non-calcium group, respectively (Fig 2). CONCLUSIONS: As far as we know, this study is the first artificial intelligence study using a single-use fURS images. Source of Funding: None. © 2023 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 209Issue Supplement 4April 2023Page: e922 Advertisement Copyright & Permissions© 2023 by American Urological Association Education and Research, Inc.MetricsAuthor Information Kyung Tak Oh More articles by this author Dae Young Jun More articles by this author Jae Young Choi More articles by this author Dae Chul Jung More articles by this author Joo Yong Lee More articles by this author Expand All Advertisement PDF downloadLoading ...

A Cloud Computing Based Deep Compression Framework for UHD Video Delivery

Ultra-high-definition (UHD) videos has increased popularity. However, the data size of UHD videos is 4-16 times larger of HD videos. This brings many challenges to existing video delivery systems, such as the shortage of network bandwidth resources and longer network transmission latency. In this paper, we propose a cloud computing based deep compression framework named Pearl, which utilizes the power of deep learning and cloud computing to compress UHD videos. Pearl compresses UHD videos from two respects: the frame resolution and the colorful information. In pearl, an optimal compact representation of the original UHD video is learned with two deep convolutional neural networks (DCNNs): super resolution CNN (SR-CNN) and colorization CNN (CL-CNN). SR-CNN is used to reconstruct a high-resolution video from a low-resolution video, while CL-CNN is adopted to preserve the color information of the video. Pearl focuses on video content compression in two new directions. Thus, it can be integrated with any existing video compression system. We evaluate the performance of Pearl with a wide variety of network conditions, quality of experience metrics, and video properties. In all considered scenarios, Pearl can further compress 84% of video size and reduce 73% of network transmission latency.

52.2: Research on Industrial Application and Standards of Ultra HD Video

Ultra high definition(UHD) industrial applications play a huge role, which can improve production efficiency, enhance product quality, and reduce resource waste. In the future, the industrial application of UHD video will be more extensive, but UHD is a long way to go to achieve total popularity. Therefore, there is an urgent need to develop a unified and open standard to promote the industrialization of UHD video. In this paper, we summarize the key technical aspects of UHD video industrial applications from the requirements of the UHD video industry. The standardization needs of industrial application areas are analyzed. According to the common problems and constraints in UHD video application, the standard system of UHD video industrial application is proposed, which contains five aspects: basic commonality, testing and certification, business presentation, auxiliary management, and field application. Finally, the shortcomings of UHD video industrial applications are pointed out, and possible solutions are given.

A smart packet type identification scheme for selective discard of video packets

In recent years, due to the growth of social networks and development of video sharing platforms, transmission of video content has increased dramatically. This huge amount of data imposes a heavy load on the limited bandwidth of the networks. As a result, data loss will be inevitable. Nevertheless, since some types of video frames, such as B-frames are more resilient to packet loss, discarding them can ease network congestion while maintaining QoE. However, frame-type information is only available in the packet payload. Limited processing power of devices in high-speed networks, data encryption and user credibility issues, make finding the frame types a costly operation. Therefore, an intelligent router with fast and reliable decision-making is proposed to model live video streams structures and recognize the importance of video packets at the network level. This information enables the network routers to discard insignificant video packets ahead of congestion. The proposed method does not need to read the IP layer payload and uses only the packet header data for decision making. Experimental results show an intelligent router, at the worst scenario can classify packet type with better than 95.1% accuracy, as if packet types are marked at the source without any bias. Tests on various HD video, with 1–10% packet drop rates, shows while the proposed packet discarding scheme is 0.8–2.7 dB inferior to ground truth method, it is still 6–10 dB better than dropping packets at random.