Context: The newest standard in video coding High Efficiency Video Coding (HEVC) should have an appropriate coder to fully use its potential. There are a lot of video quality assessment methods. These methods are necessary to establish the quality of the video. Objectives: This thesis is a comparison of video quality assessment methods. Objective is to find out which objective method is the most similar to the subjective method. Videos used in tests are encoded in the H.265/HEVC standard. Methods: For testing MSE, PSNR, SSIM methods there is special software created in MATLAB. For VQM method downloaded software was used for testing. Results and conclusions: For videos watched on mobile device: PSNR is the most similar to subjective metric. However for videos watched on television screen: VQM is the most similar to subjective metric. Keywords: Video Quality Assessment, Video Quality Prediction, Video Compression, Video Quality Metrics

Transmission of video content over wireless access networks (in particular, Wireless Local Area Networks (WLAN) and Third Generation Universal Mobile Telecommunication System (3G UMTS)) is growing exponentially and gaining popularity, and is predicted to expose new revenue streams for mobile network operators. However, the success of these video applications over wireless access networks very much depend on meeting the user’s Quality of Service (QoS) requirements. Thus, it is highly desirable to be able to predict and, if appropriate, to control video quality to meet user’s QoS requirements. Video quality is affected by distortions caused by the encoder and the wireless access network. The impact of these distortions is content dependent, but this feature has not been widely used in existing video quality prediction models. The main aim of the project is the development of novel and efficient models for video quality prediction in a non-intrusive way for low bitrate and resolution videos and to demonstrate their application in QoS-driven adaptation schemes for mobile video streaming applications. This led to five main contributions of the thesis as follows:(1) A thorough understanding of the relationships between video quality, wireless access network (UMTS and WLAN) parameters (e.g. packet/block loss, mean burst length and link bandwidth), encoder parameters (e.g. sender bitrate, frame rate) and content type is provided. An understanding of the relationships and interactions between them and their impact on video quality is important as it provides a basis for the development of non-intrusive video quality prediction models.(2) A new content classification method was proposed based on statistical tools as content type was found to be the most important parameter. (3) Efficient regression-based and artificial neural network-based learning models were developed for video quality prediction over WLAN and UMTS access networks. The models are light weight (can be implemented in real time monitoring), provide a measure for user perceived quality, without time consuming subjective tests. The models have potential applications in several other areas, including QoS control and optimization in network planning and content provisioning for network/service providers.(4) The applications of the proposed regression-based models were investigated in (i) optimization of content provisioning and network resource utilization and (ii) A new fuzzy sender bitrate adaptation scheme was presented at the sender side over WLAN and UMTS access networks. (5) Finally, Internet-based subjective tests that captured distortions caused by the encoder and the wireless access network for different types of contents were designed. The database of subjective results has been made available to research community as there is a lack of subjective video quality assessment databases.

This diploma thesis deals with standard objective and subjective video quality assessments and with analysis of their applicability to HEVC. Also basic description of video compression standard H.265/HEVC is presented. The main focus of the thesis is a creation of the database of compressed video sequences. Important parameters and features of the reference encoder HM-12 are discussed. Selected methods of objective video quality assessments are implemented on the created database. A part of this thesis is also a suggestion of method for objective video quality assessment, application of this method and associated data collection. Final data is statistically analyzed and it’s correlation with objective tests is discussed.

No description available.

With the rapid development of network visual communication technologies, digital video has become ubiquitous and indispensable in our everyday lives. Video acquisition, communication, and processing systems introduce various types of distortions, which may have major impact on perceived video quality by human observers. Effective and efficient objective video quality assessment (VQA) methods that can predict perceptual video quality are highly desirable in modern visual communication systems for performance evaluation, quality control and resource allocation purposes. Moreover, perceptual VQA measures may also be employed to optimize a wide variety of video processing algorithms and systems for best perceptual quality. This thesis exploits several novel ideas in the areas of video quality assessment and enhancement. Firstly, by considering a video signal as a 3D volume image, we propose a 3D structural similarity (SSIM) based full-reference (FR) VQA approach, which also incorporates local information content and local distortion-based pooling methods. Secondly, a reduced-reference (RR) VQA scheme is developed by tracing the evolvement of local phase structures over time in the complex wavelet domain. Furthermore, we propose a quality-aware video system which combines spatial and temporal quality measures with a robust video watermarking technique, such that RR-VQA can be performed without transmitting RR features via an ancillary lossless channel. Finally, a novel strategy for enhancing video denoising algorithms, namely poly-view fusion, is developed by examining a video sequence as a 3D volume image from multiple (front, side, top) views. This leads to significant and consistent gain in terms of both peak signal-to-noise ratio (PSNR) and SSIM performance, especially at high noise levels.

As digital communication of television content becomes more pervasive, and as networks supporting such communication become increasingly diverse, the long-standing problem of assessing video quality by objective measurements becomes particularly important. Content owners as well as content distributors stand to benefit from rapid objective measurements that correlate well with subjective assessments, and further, do not depend on the availability of the original reference video. This thesis investigates different techniques of subjective and objective video evaluation. Our research recommends a functional quality metric called Mean Time Between Failures (MTBF) where failure refers to video artifacts deemed to be perceptually noticeable, and investigates objective measurements that correlate well with subjective evaluations of MTBF. Work has been done for determining the usefulness of some existing objective metric by noting their correlation with MTBF. The research also includes experimentation with network-induced artifacts, and a study on statistical methods for correlating candidate objective measurements with the subjective metric. The statistical significance and spread properties for the correlations are studied, and a comparison of subjective MTBF with the existing subjective measure of MOS is performed. These results suggest that MTBF has a direct and predictable relationship with MOS, and that they have similar variations across different viewers. The research is particularly concerned with the development of new no-reference objective metrics that are easy to compute in real time, as well as correlate better than current metrics with the intuitively appealing MTBF measure. The approach to obtaining greater subjective relevance has included the study of better spatial-temporal models for noise-masking and test data pooling in video perception. A new objective metric, 'Automatic Video Quality' metric (AVQ) is described and shown to be implemented in real time with a high degree of correlation with actual subjective scores, with the correlation values approaching the correlations of metrics that use full or partial reference. This is metric does not need any reference to the original video, and when used to display MPEG2 streams, calculates and indicates the video quality in terms of MTBF. Certain diagnostics like the amount of compression and network artifacts are also shown.

With the rapid development of network visual communication technologies, digital video has become ubiquitous and indispensable in our everyday lives. Video acquisition, communication, and processing systems introduce various types of distortions, which may have major impact on perceived video quality by human observers. Effective and efficient objective video quality assessment (VQA) methods that can predict perceptual video quality are highly desirable in modern visual communication systems for performance evaluation, quality control and resource allocation purposes. Moreover, perceptual VQA measures may also be employed to optimize a wide variety of video processing algorithms and systems for best perceptual quality. This thesis exploits several novel ideas in the areas of video quality assessment and enhancement. Firstly, by considering a video signal as a 3D volume image, we propose a 3D structural similarity (SSIM) based full-reference (FR) VQA approach, which also incorporates local information content and local distortion-based pooling methods. Secondly, a reduced-reference (RR) VQA scheme is developed by tracing the evolvement of local phase structures over time in the complex wavelet domain. Furthermore, we propose a quality-aware video system which combines spatial and temporal quality measures with a robust video watermarking technique, such that RR-VQA can be performed without transmitting RR features via an ancillary lossless channel. Finally, a novel strategy for enhancing video denoising algorithms, namely poly-view fusion, is developed by examining a video sequence as a 3D volume image from multiple (front, side, top) views. This leads to significant and consistent gain in terms of both peak signal-to-noise ratio (PSNR) and SSIM performance, especially at high noise levels.

The research reported in this thesis investigates the performance of the transport layer Stream Control Transfer Protocol (SCTP) for streaming video over CDMA2000 cellphone and data wireless networks. The main measure of performance was quality of the received video at a given buffer size, as cellphones have memory of limited capacity. The hypothesis was that SCTP would be able to improve the quality of streamed video over UDP under the same memory requirements. Our study involved two series of simulation experiments and measurements in a testbed on the Telecom NZ CDMA2000 network, to test the performance of video streaming under SCTP and under UDP. It was found that SCTP did not improve the quality in streamed video with up to 5 second buffers. While other scenarios that have been tested by other people with high packet loss or congestion have shown that SCTP can improve the quality, the CDMA2000 network does not suffer from the impairments that SCTP could neutralise, and because of that, in this scenario, the quality of video streaming under SCTP and UDP are similar. The complexity that SCTP adds does not correspond to an increase in quality.

The overwhelming trend of the usage of multimedia services has raised the consumers' awareness about quality. Both service providers and consumers are interested in the delivered level of perceptual quality. The perceptual quality of an original video signal can get degraded due to compression and due to its transmission over a lossy network. Video quality assessment (VQA) has to be performed in order to gauge the level of video quality. Generally, it can be performed by following subjective methods, where a panel of humans judges the quality of video, or by using objective methods, where a computational model yields an estimate of the quality. Objective methods and specifically No-Reference (NR) or Reduced-Reference (RR) methods are preferable because they are practical for implementation in real-time scenarios. This doctoral thesis begins with a review of existing approaches proposed in the area of NR image and video quality assessment. In the review, recently proposed methods of visual quality assessment are classified into three categories. This is followed by the chapters related to the description of studies on the development of NR and RR methods as well as on conducting subjective experiments of VQA. In the case of NR methods, the required features are extracted from the coded bitstream of a video, and in the case of RR methods additional pixel-based information is used. Specifically, NR methods are developed with the help of suitable techniques of regression using artificial neural networks and least-squares support vector machines. Subsequently, in a later study, linear regression techniques are used to elaborate the interpretability of NR and RR models with respect to the selection of perceptually significant features. The presented studies on subjective experiments are performed using laboratory based and crowdsourcing platforms. In the laboratory based experiments, the focus has been on using standardized methods in order to generate datasets that can be used to validate objective methods of VQA. The subjective experiments performed through crowdsourcing relate to the investigation of non-standard methods in order to determine perceptual preference of various adaptation scenarios in the context of adaptive streaming of high-definition videos. Lastly, the use of adaptive gain equalizer in the modulation frequency domain for speech enhancement has been examined. To this end, two methods of demodulating speech signals namely spectral center of gravity carrier estimation and convex optimization have been studied.

<div>First-person videos (FPVs) captured by wearable cameras provide a huge amount of visual data. FPVs have different characteristics compared to broadcast videos and mobile videos. The video quality of FPVs are influenced by motion blur, tilt, rolling shutter and exposure distortions. In this work, we design image and video assessment methods applicable for FPVs. </div><div><br></div><div>Our video quality assessment mainly focuses on three quality problems. The first problem is the video frame artifacts including motion blur, tilt, rolling shutter, that are caused by the heavy and unstructured motion in FPVs. The second problem is the exposure distortions. Videos suffer from exposure distortions when the camera sensor is not exposed to the proper amount of light, which often caused by bad environmental lighting or capture angles. The third problem is the increased blurriness after video stabilization. The stabilized video is perceptually more blurry than its original because the masking effect of motion is no longer present. </div><div><br></div><div>To evaluate video frame artifacts, we introduce a new strategy for image quality estimation, called mutual reference (MR), which uses the information provided by overlapping content to estimate the image quality. The MR strategy is applied to FPVs by partitioning temporally nearby frames with similar content into sets, and estimating their visual quality using their mutual information. We propose one MR quality estimator, Local Visual Information (LVI), that estimates the relative quality between two images which overlap.</div><div><br></div><div>To alleviate exposure distortions, we propose a controllable illumination enhancement method that adjusts the amount of enhancement with a single knob. The knob can be controlled by our proposed over-enhancement measure, Lightness Order Measure (LOM). Since the visual quality is an inverted U-shape function of the amount of enhancement, our design is to control the amount of enhancement so that the image is enhanced to the peak visual quality. </div><div><br></div><div>To estimate the increased blurriness after stabilization, we propose a visibility-inspired temporal pooling (VTP) mechanism. VTP mechanism models the motion masking effect on perceived video blurriness as the influence of the visibility of a frame on the temporal pooling weight of the frame quality score. The measure for visibility is estimated as the proportion of spatial details that is visible for human observers.</div>