Deep learning and video quality analysis: towards a unified VQA

2020 ◽  
Author(s):  
Pankaj Topiwala ◽  
W. Dai ◽  
J. Pian
Keyword(s):  
Deep Learning ◽  
Video Quality ◽  
Quality Analysis

Deep learning and video quality analysis

2019 ◽  
Author(s):  
Pankaj Topiwala ◽  
Madhu Krishnan ◽  
Wei Dai
Keyword(s):  
Deep Learning ◽  
Video Quality ◽  
Quality Analysis

Evaluation of quality and reliability of musculoskeletal ultrasound videos on YouTube

2021 ◽  
Author(s):  
Nihan Cüzdan ◽  
İpek Türk
Keyword(s):  
Video Quality ◽  
Musculoskeletal Ultrasound ◽  
Quality Analysis ◽  
Competency Assessment ◽  
Exclusion Criteria ◽  
Educational Value ◽  
European League Against Rheumatism ◽  
Ultrasound Findings ◽  
Training Programmes

ABSTRACT Objectives To evaluate musculoskeletal ultrasound (MSUS) video contents on YouTube, regarding their quality, reliability, and educational value. Method The first three pages for the keywords ‘Musculoskeletal Ultrasound’, ‘joint ultrasound’, and ‘articular ultrasound’ were searched through YouTube website. The quality of the videos was assessed according to the European League Against Rheumatism (EULAR) Guidelines and EULAR Competency Assessment in MSUS. The reliability was evaluated with modified DISCERN tool. Results After the exclusion criteria applied, 58 videos were evaluated. The video quality analysis showed that probe holding (68.9%; median: 5, range: 0–5), scanning technique (63.8%; median: 4, range: 0–5), identification of anatomic structures (72.4%; median: 4, range: 0–5), and description of ultrasound findings (65.5%; median: 4, range: 0–5) were found to be sufficient, whereas ultrasound machine settings adjustments (1.7%; median: 0, range: 0–4) and final ultrasound diagnosis (12.1%; median: 0, range: 0–5) were insufficient. The total median value of the modified DISCERN scale was 2 (percentile: 2–2, range: 0–3). Conclusion MSUS video contents on YouTube are insufficient for educational purposes on MSUS training. There is a need for affordable, easily accessed, standardized, and peer-reviewed online training programmes on MSUS and MSUS-guided injections.

Automatic Content Based Video Quality Analysis for Media Production and Delivery Processes

2009 ◽  
Author(s):  
Peter Schallauer ◽  
Hannes Fassold ◽  
Martin Winter ◽  
Werner Bailer ◽  
Georg Thallinger ◽  
...  
Keyword(s):  
Video Quality ◽  
Quality Analysis ◽  
Media Production

Perceptual Video Quality Analysis for HEVC in Packet Loss Environment

2014 ◽  
Author(s):  
Bhupender Kumar ◽  
Shekhar Madnani ◽  
Advait Mogre ◽  
Muneesh Sharma ◽  
Shailesh Kumar
Keyword(s):  
Packet Loss ◽  
Video Quality ◽  
Quality Analysis ◽  
Perceptual Video Quality

scholarly journals VVC In-Loop Filtering Based on Deep Convolutional Neural Network

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Soulef Bouaafia ◽  
Seifeddine Messaoud ◽  
Randa Khemiri ◽  
Fatma Elzahra Sayadi
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Video Coding ◽  
Convolutional Neural Network ◽  
Video Streaming ◽  
High Efficiency ◽  
Dynamic Range ◽  
Video Quality ◽  
Deep Convolutional Neural Network ◽  
Frame Rate

With the rapid advancement in many multimedia applications, such as video gaming, computer vision applications, and video streaming and surveillance, video quality remains an open challenge. Despite the existence of the standardized video quality as well as high definition (HD) and ultrahigh definition (UHD), enhancing the quality for the video compression standard will improve the video streaming resolution and satisfy end user’s quality of service (QoS). Versatile video coding (VVC) is the latest video coding standard that achieves significant coding efficiency. VVC will help spread high-quality video services and emerging applications, such as high dynamic range (HDR), high frame rate (HFR), and omnidirectional 360-degree multimedia compared to its predecessor high efficiency video coding (HEVC). Given its valuable results, the emerging field of deep learning is attracting the attention of scientists and prompts them to solve many contributions. In this study, we investigate the deep learning efficiency to the new VVC standard in order to improve video quality. However, in this work, we propose a wide-activated squeeze-and-excitation deep convolutional neural network (WSE-DCNN) technique-based video quality enhancement for VVC. Thus, the VVC conventional in-loop filtering will be replaced by the suggested WSE-DCNN technique that is expected to eliminate the compression artifacts in order to improve visual quality. Numerical results demonstrate the efficacy of the proposed model achieving approximately − 2.85 % , − 8.89 % , and − 10.05 % BD-rate reduction of the luma (Y) and both chroma (U, V) components, respectively, under random access profile.

scholarly journals Improving Water Quality Assessment through Anomaly Detection Using Hybrid Convolutional Neural Network Approach

2021 ◽  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Water Quality ◽  
Deep Learning ◽  
Anomaly Detection ◽  
Convolutional Neural Network ◽  
Quality Assessment ◽  
Water Quality Assessment ◽  
Machine Learning Algorithms ◽  
Quality Analysis

<p>Water being a precious commodity for every person around the world needs to be quality monitored continuously for ensuring safety whilst usage. The water data collected from sensors in water plants are used for water quality assessment. The anomaly present in the water data seriously affects the performance of water quality assessment. Hence it needs to be addressed. In this regard, water data collected from sensors have been subjected to various anomaly detection approaches guided by Machine Learning (ML) and Deep Learning framework. Standard machine learning algorithms have been used extensively in water quality analysis and these algorithms in general converge quickly. Considering the fact that manual feature selection has to be done for ML algorithms, Deep Learning (DL) algorithm is proposed which involve implicit feature learning. A hybrid model is formulated that takes advantage of both and presented it is data invariant too. This novel Hybrid Convolutional Neural Network (CNN) and Extreme Learning Machine (ELM) approach is used to detect presence of anomalies in sensor collected water data. The experiment of the proposed CNN-ELM model is carried out using the publicly available dataset GECCO 2019. The findings proved that the model has improved the water quality assessment of the sensor water data collected by detecting the anomalies efficiently and achieves F1 score of 0.92. This model can be implemented in water quality assessment.</p>

scholarly journals A Quality Analysis Of Low Back Pain Videos On Youtube

2020 ◽  
Author(s):  
Muhammet Arif Özbek ◽  
Oguz Baran ◽  
Şevket Evran ◽  
Ahmet Kayhan ◽  
Tahsin Saygı ◽  
...  
Keyword(s):  
Low Back Pain ◽  
Back Pain ◽  
Medical Information ◽  
Average Length ◽  
Video Quality ◽  
Scoring Systems ◽  
Quality Analysis ◽  
Low Back ◽  
The Subject ◽  
Youtube Videos

Abstract Background: Most people face low back pain problems at least once in their lifetimes. With the advancing technology, people have been consulting the internet regarding their diagnoses more and more over the last 20 years. This study aims to evaluate the accuracy and reliability of YouTube videos on low back pain. Methods: The keyword “Low Back Pain” was used in our search on YouTube. The first 50 videos to come up in the search results were evaluated using JAMA, DISCERN, and GQS scoring systems. The individual correlation of each video and the correlation between the aforementioned scoring systems were statistically analyzed. Results: The average length of the 50 videos that were analyzed is 7,57 minutes (0,34 – 48,23 minutes), and the average daily view count of the videos is 331,14. Generally, video quality was found to be “poor”. On average, JAMA score was 1,64, DISCERN score was 1,63 and GQS score was 1,93. The most common videos found on the subject were those that were done by TV programs. And, videos by health information websites and by Hospitals / Doctors / Educational Institutions were, while still being below the threshold value, found to give higher quality information on the subject than the videos by other sources. Conclusion: Videos on YouTube regarding low back pain are of low quality, and most are created by unreliable sources. Therefore, such YouTube videos should not be recommended as patient education tools on low back pain. An important step in disseminating correct medical information to the public would be to have a platform where the accuracy and quality of given medical information are evaluated by medical experts.

Video Quality Analysis for Concert Video Mashup Generation

2010 ◽  
pp. 1-12 ◽  
Author(s):  
Prarthana Shrestha ◽  
Hans Weda ◽  
Mauro Barbieri ◽  
Peter H. N. de With
Keyword(s):  
Video Quality ◽  
Quality Analysis
Sign in / Sign up

Export Citation Format

Share Document