A no-reference machine learning based video quality predictor

Shahid, Muhammad; Rossholm, Andreas; Lövström, Benny

doi:10.1109/qomex.2013.6603233

Cited by 21 publications

(20 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The present work moves beyond the works existing in the literature and extends our previous work, 10 proposing a NR model for estimating the quality of H.264/AVC video sequences, affected by both compression artifacts and packet losses. The concept is based on the extraction of a large set of quality-relevant features from impaired bitstreams.…”

Section: Introductionmentioning

confidence: 80%

A no-reference bitstream-based perceptual model for video quality estimation of videos affected by coding artifacts and packet losses

Pandremmenou

Shahid

Kondi

et al. 2015

Human Vision and Electronic Imaging XX

View full text Add to dashboard Cite

In this work, we propose a No-Reference (NR) bitstream-based model for predicting the quality of H.264/AVC video sequences, affected by both compression artifacts and transmission impairments. The proposed model is based on a feature extraction procedure, where a large number of features are calculated from the packet-loss impaired bitstream. Many of the features are firstly proposed in this work, and the specific set of the features as a whole is applied for the first time for making NR video quality predictions. All feature observations are taken as input to the Least Absolute Shrinkage and Selection Operator (LASSO) regression method. LASSO indicates the most important features, and using only them, it is possible to estimate the Mean Opinion Score (MOS) with high accuracy. Indicatively, we point out that only 13 features are able to produce a Pearson Correlation Coefficient of 0.92 with the MOS. Interestingly, the performance statistics we computed in order to assess our method for predicting the Structural Similarity Index and the Video Quality Metric are equally good. Thus, the obtained experimental results verified the suitability of the features selected by LASSO as well as the ability of LASSO in making accurate predictions through sparse modeling.

show abstract

Section: Introductionmentioning

confidence: 80%

A no-reference bitstream-based perceptual model for video quality estimation of videos affected by coding artifacts and packet losses

Pandremmenou

Shahid

Kondi

et al. 2015

Human Vision and Electronic Imaging XX

View full text Add to dashboard Cite

show abstract

“…As mentioned earlier, LS-SVM was employed in [20], SVR was chosen in [22], DBN was selected in [21]. In this work, we choose SAE as a tool for feature handling.…”

Section: Stacked Auto-encodermentioning

confidence: 99%

“…In [19], a novel VQA metric was proposed through visual perception and visual attention. Shahid et al [20] presented a model based on LS-SVM (least Square Support Vector Machines), which attained more robust features. In [21], DBN (Deep Belief Nets) was introduced to make more accurate predictions.…”

mentioning

confidence: 99%

Flexible Actuator With Variable Stiffness and Its Decoupling Control Algorithm: Principle Prototype Design and Experimental Verification

Jin

Yang²,

Zhang

et al. 2018

IEEE/ASME Trans. Mechatron.

View full text Add to dashboard Cite

“…An improvement of this approach is presented in [154] where the required number of parameters has been reduced for computational efficiency and the prediction accuracy has been improved by the virtue of the usage of an ANN. A further improvement is found in [155] where a larger features set is used and the prediction of subjective MOS is also performed. A set of 48 bitstream parameters related to slice coding type, coding modes, various statistics of motion vectors, and QP value was used in [156] to predict the quality of high-definition television (HDTV) video encoded by H.264/AVC.…”

Section: Bitstream Layer Modelmentioning

confidence: 99%

No-reference image and video quality assessment: a classification and review of recent approaches

et al. 2014

Self Cite

View full text Add to dashboard Cite

The field of perceptual quality assessment has gone through a wide range of developments and it is still growing. In particular, the area of no-reference (NR) image and video quality assessment has progressed rapidly during the last decade. In this article, we present a classification and review of latest published research work in the area of NR image and video quality assessment. The NR methods of visual quality assessment considered for review are structured into categories and subcategories based on the types of methodologies used for the underlying processing employed for quality estimation. Overall, the classification has been done into three categories, namely, pixel-based methods, bitstream-based methods, and hybrid methods of the aforementioned two categories. We believe that the review presented in this article will be helpful for practitioners as well as for researchers to keep abreast of the recent developments in the area of NR image and video quality assessment. This article can be used for various purposes such as gaining a structured overview of the field and to carry out performance comparisons for the state-of-the-art methods. Keywords:No-reference; Image quality assessment; Video quality assessment; Perceptual quality 1 Review IntroductionThere has been a tremendous progress recently in the usage of digital images and videos for an increasing number of applications. Multimedia services that have gained wide interest include digital television broadcasts, video streaming applications, and real-time audio and video services over the Internet. The global mobile data traffic grew by 81% in 2013, and during 2014, the number of mobileconnected devices will exceed the number of people on earth, according to predictions made by Cisco. The video portion of the mobile data traffic was 53% in 2013 and is expected to exceed 67% by 2018 [1]. With this huge increase in the exposure of image and video to the human eye, the interest in delivering quality of experience (QoE) may increase naturally. The quality of visual media can get degraded during capturing, compression, transmission, reproduction, and displaying due to the distortions that might occur at any of these stages. The legitimate judges of visual quality are humans as end users, the opinions of whom can be obtained by subjective experiments. Subjective experiments involve a panel of participants which are usually non-experts, also referred to as test subjects, to assess the perceptual quality of given test material such as a sequence of images or videos. Subjective experiments are typically conducted in a controlled laboratory environment. Careful planning and several factors including assessment method, selection of test material, viewing conditions, grading scale, and timing of presentation have to be considered prior to a subjective experiment. For example, Recommendation (ITU-R) BT.500 [2] provides detailed guidelines for conducting subjective experiments for the assessment of quality of television pictures. The outcomes of a subjectiv...

show abstract

A no-reference machine learning based video quality predictor

Cited by 21 publications

References 18 publications

A no-reference bitstream-based perceptual model for video quality estimation of videos affected by coding artifacts and packet losses

A no-reference bitstream-based perceptual model for video quality estimation of videos affected by coding artifacts and packet losses

Flexible Actuator With Variable Stiffness and Its Decoupling Control Algorithm: Principle Prototype Design and Experimental Verification

No-reference image and video quality assessment: a classification and review of recent approaches

Contact Info

Product

Resources

About