基于MPEG-4视频流的QoS映射研究

基于XVID和实时传输协议(RTP)提出了一种MPEG-4视频流的服务质量(QoS)映射管理方法。分析了MPEG-4视频流特点、编解码软件和QoS分层管理方法,提出了基于RTP协议的QoS管理逻辑结构、不同层次上的QoS参数,即应用层和系统层QoS参数,以及应用层到系统层QoS参数的映射算法。在模拟网络环境下的实验结果表明这种QoS参数的映射算法能够保证MPEG-4视频流的服务质量。     

Cloud-based video analytics using convolutional neural networks

Object classification is a vital part of any video analytics system, which could aid in complex applications such as object monitoring and management. Traditional video analytics systems work on shallow networks and are unable to harness the power of distributed processing for training and inference. We propose a cloud-based video analytics system based on an optimally tuned convolutional neural network to classify objects from video streams. The tuning of convolutional neural network is empowered by in-memory distributed computing. The object classification is performed by comparing the target object with the prestored trained patterns, generating a set of matching scores. The matching scores greater than an empirically determined threshold reveal the classification of the target object. The proposed system proved to be robust to classification errors with an accuracy and precision of 97% and 96%, respectively, and can be used as a general-purpose video analytics system.     

多媒体传感器网络中的视频流传输质量分析与评估

在NS2平台上仿真实现了多媒体传感器网络的视频流传输,并在NS2-myEvalvid模型的基础上通过比较PSRN值分析了压缩量化参数、GOP类型、封包长度和封包错误率对视频流传输质量的影响。仿真实验表明,压缩量化参数、GOP长度或封包错误率取值越小,视频流的传输效果越好;而封包长度取值越小,视频流的传输效果越差。     

Two-chip MPEG-2 video encoder

Our two-chip, real time, MPEG-2, simple-profile-at-main-level encoder supports NTSC 4:2:0 video signals with only three external memories. We have developed a compact encoder chip set. The key features of this chip set are a low encoding delay based on a simple profile at main level; wide-range motion estimation, which it performs using a hierarchical search; a flexible, macroblock level pipeline architecture based on RISC CPUs; and three small peripherals with no glue logic: a VRAM, synchronous DRAM, and FIFO DRAM     

On the impact of adaptive RED in IP networks transporting H.264/MPEG-4 AVC video streams

This paper investigate the impact on the QoS offered by IP networks that transport real-time H.264/MPEG-4 AVC video streams when applying adaptive random early detection (ARED) as an active queue management technique instead of traditional drop-tail. Simulation results indicate that the ARED technique reduces the loss of video packets but degrades a higher number of video frames if compared to the drop-tail technique, while showing a small qualitative gain regarding delay and jitter. From these results it may be reasonably concluded that H.264/MPEG-4 AVC video streams do not benefit from employing ARED technique as VoIP streams do.     

Dejittering in the transport of MPEG-2 and MPEG-4 video

When multimedia information is transported over a packet-switched network, the quality of presentation can be degraded due to network delay variation or jitter. This paper presents a dejittering scheme that can be used in the transport of MPEG-4 and MPEG-2 video to absorb any introduced network jitter, thus preserving the presentation quality of transported media streams. The dejittering scheme is based on the statistical approximation of delay variation in the arrival times of video packets carrying encoded clock reference values and a filtering and re-stamping mechanism. In addition, a brief overview of the MPEG-4 system is presented.     

Efficient video quality assessment for on-demand video transcoding using intensity variation analysis

The Journal of Supercomputing - Due to the wide spread usage of smart devices, adopting video contents service to the diverse end user’s service environment is an essential process. The...     

Modeling packet-loss visibility in MPEG-2 video

We consider the problem of predicting packet loss visibility in MPEG-2 video. We use two modeling approaches: CART and GLM. The former classifies each packet loss as visible or not; the latter predicts the probability that a packet loss is visible. For each modeling approach, we develop three methods, which differ in the amount of information available to them. A reduced reference method has access to limited information based on the video at the encoder's side and has access to the video at the decoder's side. A no-reference pixel-based method has access to the video at the decoder's side but lacks access to information at the encoder's side. A no-reference bitstream-based method does not have access to the decoded video either; it has access only to the compressed video bitstream, potentially affected by packet losses. We design our models using the results of a subjective test based on 1080 packet losses in 72 minutes of video.     

SuperENC: MPEG-2 video encoder chip

Thanks to increased market acceptance of applications such as digital versatile disks (DVDs), HDTV, and digital satellite broadcasting, the MPEG-2 (Moving Picture Experts Group-2) standard is becoming widely used. The MPEG-2 video standard, established in 1934, provides for a high-quality video compression format that, through high bit rates and frame rates, yields high-resolution video images. Emerging multimedia applications, such as digital versatile disk and high-definition television, demand higher quality video than ever before. In response, our MPEG-2 video encoder chip supports multiple profiles and levels     

Foveated video quality assessment

Most image and video compression algorithms that have been proposed to improve picture quality relative to compression efficiency have either been designed based on objective criteria such as signal-to-noise-ratio (SNR) or have been evaluated, post-design, against competing methods using an objective sample measure. However, existing quantitative design criteria and numerical measurements of image and video quality both fail to adequately capture those attributes deemed important by the human visual system, except, perhaps, at very low error rates. We present a framework for assessing the quality of and determining the efficiency of foveated and compressed images and video streams. Image foveation is a process of nonuniform sampling that accords with the acquisition of visual information at the human retina. Foveated image/video compression algorithms seek to exploit this reduction of sensed information by nonuniformly reducing the resolution of the visual data. We develop unique algorithms for assessing the quality of foveated image/video data using a model of human visual response. We demonstrate these concepts on foveated, compressed video streams using modified (foveated) versions of H.263 that are standard-compliant. We rind that quality vs. compression is enhanced considerably by the foveation approach     

Prediction of urban stormwater quality using artificial neural networks

There are a vast number of complex, interrelated processes influencing urban stormwater quality. However, the lack of measured fundamental variables prevents the construction of process-based models. Furthermore, hybrid models such as the buildup-washoff models are generally crude simplifications of reality. This has created the need for statistical models, capable of making use of the readily accessible data. In this paper, artificial neural networks (ANN) were used to predict stormwater quality at urbanized catchments located throughout the United States. Five constituents were analysed: chemical oxygen demand (COD), lead (Pb), suspended solids (SS), total Kjeldhal nitrogen (TKN) and total phosphorus (TP). Multiple linear regression equations were initially constructed upon logarithmically transformed data. Input variables were primarily selected using a stepwise regression approach, combined with process knowledge. Variables found significant in the regression models were then used to construct ANN models. Other important network parameters such as learning rate, momentum and the number of hidden nodes were optimized using a trial and error approach. The final ANN models were then compared with the multiple linear regression models. In summary, ANN models were generally less accurate than the regression models and more time consuming to construct. This infers that ANN models are not more applicable than regression models when predicting urban stormwater quality.     

Sound quality analysis of cars using hybrid neural networks

In this paper, a procedure of testing and evaluation on the sound quality of cars are proposed and sound quality is analysed through the cars’ road running test on the providing ground, which was carried out with varying running speed. In addition to this experimental analysis, a neural network predictor is also designed to model the system for possible experimental applications. The proposed neural network is a recurrent type network, which consists of two types of neuron function in the hidden layer. As basic factors for sound quality, only objective factors are considered such as loudness, sharpness, speech intelligibility, and sound pressure level. The correlation between sound pressure level and another factor are discussed from a point of view of running speed dependency. Results of both computer simulations and experiments show that the neural predictor algorithm gives good results at accommodating different cases and provides superior prediction on two cars’ sound analysis.     

基于MPEG-4 FGS视频的流式多播传输

根据流体流量控制机制和MPEG-4 FGS编码视频流精细分级的特点,提出了流式多播方法,该方法中数据不用分层组织且没有加入实验,极大地减少了网络开销.同时,针对视频图像组帧间编码的依赖关系,修正了视频质量PSNR的计算公式,较好地评价视频网络传输质量.对分层多播和流式多播的对比仿真实验表明,流式多播的性能稳定、扩展灵活,便于大规模扩展应用.     

Foveated convolutional neural networks for video summarization

With the proliferation of video data, video summarization is an ideal tool for users to browse video content rapidly. In this paper, we propose a novel foveated convolutional neural networks for dynamic video summarization. We are the first to integrate gaze information into a deep learning network for video summarization. Foveated images are constructed based on subjects’ eye movements to represent the spatial information of the input video. Multi-frame motion vectors are stacked across several adjacent frames to convey the motion clues. To evaluate the proposed method, experiments are conducted on two video summarization benchmark datasets. The experimental results validate the effectiveness of the gaze information for video summarization despite the fact that the eye movements are collected from different subjects from those who generated summaries. Empirical validations also demonstrate that our proposed foveated convolutional neural networks for video summarization can achieve state-of-the-art performances on these benchmark datasets.     

Consistent-degradation macroblock grouping for parallel video streams over DiffServ networks

This paper presents a consistent-degradation macroblock grouping scheme for improving loss resilience of parallel video streams over a two-class DiffServ network. By jointly exploiting the H.264 flexible macroblock ordering (FMO) tool, a multi-stream macroblock ordering framework is designed to classify all macroblocks of a super-frame into two categories: important macroblocks as high-reliability traffic class and unimportant macroblocks as best-effort traffic class. To ensure efficiency and fairness of multi-stream macroblock ordering, the compound transmission distortion is introduced to measure both worst-case and average-case loss resilience of parallel video streams. The proposed consistent-degradation macroblock grouping scheme aims to further reduce the compound transmission distortion based on a GOP-level macroblock importance metric, which is adopted to timely estimate the error-propagation effect of macroblock loss on video quality degradation. With finer macroblock classification, the proposed scheme can find out an optimal grouping policy for each super-frame under the given transmission resource constraints. Both the theoretical analysis and simulation results show that the proposed scheme can effectively reduce the compound transmission distortion of parallel video streams over a two-class DiffServ network, and thus provide more consistent loss resilience and better utilization of transmission resources.     

A fast, FPGA-based MPEG-2 video encoder with a novel automatic quality control scheme

A novel video encoder that controls image quality on the fly is presented along with its FPGA implementation. As a result of this new feature, which uses a concept called pruning, the processing speed increases by a factor of two when compared to the conventional method of processing without pruning. The FPGA implementation conforms to MPEG-2 standards and is capable of processing color pictures of sizes up to 1024×768 pixels at the real time rate of 25 frames/s.     

Scalable authentication of MPEG-4 streams

This paper presents three scalable and efficient schemes for authenticating MPEG-4 streams: the Flat Authentication Scheme, the Progressive Authentication Scheme, and the Hierarchical Authentication Scheme. All the schemes allow authentication of MPEG-4 streams over lossy networks by integrating seamlessly digital signatures and erasure correction coding with MPEG-4's fine granular scalability. A prominent feature of our schemes is their "sign once, verify many ways" property, i.e., they generate only one digital signature per compressed MPEG-4 object group, but allow clients to verify the authenticity of any down-scaled version of the original signed object group.     

Perceptual quality assessment of nighttime video

The quality of nighttime videos is important for consumer photography and monitoring of video clearness. However, little work has been done on the study of nighttime video quality assessment. In this paper, to the best of our knowledge, we explore the study on the nighttime video quality assessment for the first time. First, we build a real-world nighttime video quality assessment database (NVQA) containing 200 videos with abundant content and diverse distortion. Additionally, we carry out subjective tests to rate all nighttime videos in the NVQA database. Thereafter, we proposed a blind nighttime video quality assessment model based on feature fusion and conducted experiments to evaluate the performance and efficiency of our proposed model. The experiment results demonstrate that our model outperforms most traditional methods.     

Parallel neural networks for multimodal video genre classification

Improvements in digital technology have made possible the production and distribution of huge quantities of digital multimedia data. Tools for high-level multimedia documentation are becoming indispensable to efficiently access and retrieve desired content from such data. In this context, automatic genre classification provides a simple and effective solution to describe multimedia contents in a structured and well understandable way. We propose in this article a methodology for classifying the genre of television programmes. Features are extracted from four informative sources, which include visual-perceptual information (colour, texture and motion), structural information (shot length, shot distribution, shot rhythm, shot clusters duration and saturation), cognitive information (face properties, such as number, positions and dimensions) and aural information (transcribed text, sound characteristics). These features are used for training a parallel neural network system able to distinguish between seven video genres: football, cartoons, music, weather forecast, newscast, talk show and commercials. Experiments conducted on more than 100 h of audiovisual material confirm the effectiveness of the proposed method, which reaches a classification accuracy rate of 95%.

低复杂度的MPEG-2到H.264快速转码算法

提出一种新的MPEG-2到H.264快速转码算法,利用H.264宏块（MB）模式选择与MPEG-2运动补偿残差间的相关性,将H.264宏块模式的选择转化为数据分类;在MPEG-2解码时,保存相关的宏块信息,包括MB编码模式、编码块类型（CBPC）、MB残差的均值和方差,解码后采用标准的H.264编码器对YUV图像编码,并保存H.264宏块的编码模式,采用机器学习算法得到决策树,用于H.264编码模式的分类,从而大大提高转码效率。