Video quality based link adaptation for low latency video transmission over WLANs

Wireless Local Area Networks (WLANs) such as IEEE 802.11a/g and Hiperlan/2 utilise numerous transmission modes, each providing different throughputs and reliability levels. Many link adaptation algorithms proposed in the literature either maximise the error-free data throughput based on channel conditions or are based on the number of failed transmissions. However, these algo- rithms do not take into account the content of the data stream and strongly rely on the use of Automatic Repeat Requests (ARQs). Low latency video applications such as real-time video transmission may require no retransmission, or only a limited number of retrans- missions. Moreover, completely error-free communication is not essential, especially if robust video compression techniques are applied. In such scenarios, improved decoded video quality can be obtained with a video stream transmitted at a higher bit rate using a higher link speed but with some degree of transmission error, rather than an error-free video stream at a lower bit rate using a lower link speed. In this work, we investigate a link adaptation scheme that improves the Quality of Service (QoS) for video transmission, based on the overall received video quality (Peak Signal to Noise Ratio, PSNR), rather than by maximising the error-free throughput. We also study a practical link adaptation approach that uses PER thresholds at the PHY layer. An empirical study showed that thresholds for switching from one mode to another are much lower (almost error free) than those currently used by throughput based schemes. We show that traditional link adaptation strategies are not appropriate for real-time video transmission with no retransmis- sion. Simulation results using the H.264 video compression standard over IEEE 802.11a are presented.

A RNN-based objective video quality measurement

Technology used to automatically assess video quality plays a significant role in video processing areas. Because of the complexity of video media, there are great limitations to assess video quality with only one factor. We propose a new method using artificial random neural networks （RNNs） with motion evaluation as an estimation of perceived visual distortion. The results are obtained through a nonlinear fitting procedure and well correlated with human perception. Compared with other methods, the proposed method performs more adaptable and accurate predictions.

Quality of experience models for network video quality

Nowadays,the service of network video is increasing explosively.But the quality of experience(QoE)model of network video quality is not stable.The video quality may be impaired by many factors.This paper proposes QoE models for network video quality.It consists of two components:1)the perceptual video quality model considering the impair factors related to video content as well as distortion caused by content and transmission.Next the model is built through a decision tree using a set of measured features form the network video.This proposed model can qualitatively give the grade of video quality and improve the accuracy of prediction.2)Based on the above model,another model is proposed to give the concrete objective score of video quality.It also considers original impair factors and predicts the video quality using fuzzy decision tree.The two models have their own advantages.The first model has a good computational complexity;the second model is more precise.All the models are simulated by actual experiments.They can improve the accuracy of objective model.The detail results are shown.

QI-BRiCE: Quality Index for Bleeding Regions in Capsule Endoscopy Videos

With the advent in services such as telemedicine and telesurgery,provision of continuous quality monitoring for these services has become a challenge for the network operators.Quality standards for provision of such services are application specic as medical imagery is quite different than general purpose images and videos.This paper presents a novel full reference objective video quality metric that focuses on estimating the quality of wireless capsule endoscopy(WCE)videos containing bleeding regions.Bleeding regions in gastrointestinal tract have been focused in this research,as bleeding is one of the major reasons behind several diseases within the tract.The method jointly estimates the diagnostic as well as perceptual quality of WCE videos,and accurately predicts the quality,which is in high correlation with the subjective differential mean opinion scores(DMOS).The proposed combines motion quality estimates,bleeding regions’quality estimates based on support vector machine(SVM)and perceptual quality estimates using the pristine and impaired WCE videos.Our method Quality Index for Bleeding Regions in Capsule Endoscopy(QI-BRiCE)videos is one of its kind and the results show high correlation in terms of Pearson’s linear correlation coefcient(PLCC)and Spearman’s rank order correlation coefcient(SROCC).An F-test is also provided in the results section to prove the statistical signicance of our proposed method.

Suitability of VVC and HEVC for Video Telehealth Systems

Video compression in medical video streaming is one of the key technologies associated with mobile healthcare.Seamless delivery of medical video streams over a resource constrained network emphasizes the need of a video codec that requires minimum bitrates and maintains high perceptual quality.This paper presents a comparative study between High Efciency Video Coding(HEVC)and its potential successor Versatile Video Coding(VVC)in the context of healthcare.A large-scale subjective experiment comprising of twenty-four non-expert participants is presented for eight different test conditions in Full High Denition(FHD)videos.The presented analysis highlights the impact of compression artefacts on the perceptual quality of HEVC and VVC processed videos.Our results and ndings show that VVC clearly outperforms HEVC in terms of achieving higher compression,while maintaining high quality in FHD videos.VVC requires upto 40%less bitrate for encoding an FHD video at excellent perceptual quality.We have provided rate-quality curves for both encoders and a degree of overlap across both codecs in terms of perceptual quality.Overall,there is a 71%degree of overlap in terms of quality between VVC and HEVC compressed videos for eight different test conditions.

Evaluating quality of motion for unsupervised video object segmentation

Current mainstream unsupervised video object segmentation(UVOS) approaches typically incorporate optical flow as motion information to locate the primary objects in coherent video frames. However, they fuse appearance and motion information without evaluating the quality of the optical flow. When poor-quality optical flow is used for the interaction with the appearance information, it introduces significant noise and leads to a decline in overall performance. To alleviate this issue, we first employ a quality evaluation module(QEM) to evaluate the optical flow. Then, we select high-quality optical flow as motion cues to fuse with the appearance information, which can prevent poor-quality optical flow from diverting the network's attention. Moreover, we design an appearance-guided fusion module(AGFM) to better integrate appearance and motion information. Extensive experiments on several widely utilized datasets, including DAVIS-16, FBMS-59, and You Tube-Objects, demonstrate that the proposed method outperforms existing methods.

3DV quality model based depth maps for view synthesis in FTV system

Depth maps are used for synthesis virtual view in free-viewpoint television （FTV） systems. When depth maps are derived using existing depth estimation methods, the depth distortions will cause undesirable artifacts in the synthesized views. To solve this problem, a 3D video quality model base depth maps （D-3DV） for virtual view synthesis and depth map coding in the FTV applications is proposed. First, the relationships between distortions in coded depth map and rendered view are derived. Then, a precisely 3DV quality model based depth characteristics is develop for the synthesized virtual views. Finally, based on D-3DV model, a multilateral filtering is applied as a pre-processed filter to reduce rendering artifacts. The experimental results evaluated by objective and subjective methods indicate that the proposed D-3DV model can reduce bit-rate of depth coding and achieve better rendering quality.

QoE Assessment and Prediction Method for HighDefinition Video Stream Using Image Damage Accumulation

The accuracy of the traditional assessment method of the quality of experience(Qo E) has been facing challenges with the growth of high-definition(HD) video streaming services.Image display-quality damage is the main factor that affects the Qo E in HD video services through UDP network transmission.In this paper,we introduce a novel objective factor known as image damage accumulation(IDA) to assess user's Qo E in HD video services.First,this paper quantitatively analyzed the effect on user quality of experience by IDA and established a mapping relationship between mean opinion scores and IDA.Furthermore,the probability of image damage caused by compression and transmission were analyzed.Based on this analysis,an objective Qo E assessment and prediction method for HD video stream service that evaluated the user experience according to IDA are proposed.The proposed method can achieve assessment and prediction accuracy on three distinct subjective tests.

INFLUENCE OF STOCHASTIC NOISE STATISTICS ON KALMAN FILTER PERFORMANCE BASED ON VIDEO TARGET TRACKING

The system stochastic noises involved in Kalman filtering are preconditioned on being ideally white and Gaussian distributed. In this research, efforts are exerted on exploring the influence of the noise statistics on Kalman filtering from the perspective of video target tracking quality. The correlation of tracking precision to both the process and measurement noise covariance is investigated; the signal-to-noise power density ratio is defined; the contribution of predicted states and measured outputs to Kalman filter behavior is discussed; the tracking precision relative sensitivity is derived and applied in this study case. The findings are expected to pave the way for future study on how the actual noise statistics deviating from the assumed ones impacts on the Kalman filter optimality and degra-dation in the application of video tracking.

STOCHASTIC NOISE TOLERANCE:ENHANCED FULL STATE OBSERVER VS. KALMAN FILTER FROM VIDEO TRACKING PERSPECTIVE

A control-based full state observer scheme is explored for video target tracking application, and is enhanced with a lowpass filter for improving the tracking precision, thus forming an Enhanced Full State Observer (EFSO). The whole design is based on the given lab-generated video sequence with motion of an articulate target. To evaluate the EFSO’s stochastic noise tolerance, a Kalman Filter (KF) is intentionally employed in tracking the same target with the given Gaussian white noises. The comparison results indicate that, for system noises of certain statistics, the proposed EFSO has its own noise resistance capacity that is superior to that of KF and is more advantageous for implementation.

Recent Advances and Challenges of Visual Signal Quality Assessment

While quality assessment is essential for testing, optimizing, benchmarking, monitoring, and inspecting related systems and services, it also plays an essential role in the design of virtually all visual signal processing and communication algorithms, as well as various related decision-making processes. In this paper, we first provide an overview of recently derived quality assessment approaches for traditional visual signals (i.e., 2D images/videos), with highlights for new trends (such as machine learning approaches). On the other hand, with the ongoing development of devices and multimedia services, newly emerged visual signals (e.g., mobile/3D videos) are becoming more and more popular. This work focuses on recent progresses of quality metrics, which have been reviewed for the newly emerged forms of visual signals, which include scalable and mobile videos, High Dynamic Range (HDR) images, image segmentation results, 3D images/videos, and retargeted images.